Dictionary learning-based CT detection of pulmonary nodules

NASA Astrophysics Data System (ADS)

Wu, Panpan; Xia, Kewen; Zhang, Yanbo; Qian, Xiaohua; Wang, Ge; Yu, Hengyong

2016-10-01

Segmentation of lung features is one of the most important steps for computer-aided detection (CAD) of pulmonary nodules with computed tomography (CT). However, irregular shapes, complicated anatomical background and poor pulmonary nodule contrast make CAD a very challenging problem. Here, we propose a novel scheme for feature extraction and classification of pulmonary nodules through dictionary learning from training CT images, which does not require accurately segmented pulmonary nodules. Specifically, two classification-oriented dictionaries and one background dictionary are learnt to solve a two-category problem. In terms of the classification-oriented dictionaries, we calculate sparse coefficient matrices to extract intrinsic features for pulmonary nodule classification. The support vector machine (SVM) classifier is then designed to optimize the performance. Our proposed methodology is evaluated with the lung image database consortium and image database resource initiative (LIDC-IDRI) database, and the results demonstrate that the proposed strategy is promising.

Deep learning application: rubbish classification with aid of an android device

NASA Astrophysics Data System (ADS)

Liu, Sijiang; Jiang, Bo; Zhan, Jie

2017-06-01

Deep learning is a very hot topic currently in pattern recognition and artificial intelligence researches. Aiming at the practical problem that people usually don't know correct classifications some rubbish should belong to, based on the powerful image classification ability of the deep learning method, we have designed a prototype system to help users to classify kinds of rubbish. Firstly the CaffeNet Model was adopted for our classification network training on the ImageNet dataset, and the trained network was deployed on a web server. Secondly an android app was developed for users to capture images of unclassified rubbish, upload images to the web server for analyzing backstage and retrieve the feedback, so that users can obtain the classification guide by an android device conveniently. Tests on our prototype system of rubbish classification show that: an image of one single type of rubbish with origin shape can be better used to judge its classification, while an image containing kinds of rubbish or rubbish with changed shape may fail to help users to decide rubbish's classification. However, the system still shows promising auxiliary function for rubbish classification if the network training strategy can be optimized further.

Feature selection and classification of multiparametric medical images using bagging and SVM

NASA Astrophysics Data System (ADS)

Fan, Yong; Resnick, Susan M.; Davatzikos, Christos

2008-03-01

This paper presents a framework for brain classification based on multi-parametric medical images. This method takes advantage of multi-parametric imaging to provide a set of discriminative features for classifier construction by using a regional feature extraction method which takes into account joint correlations among different image parameters; in the experiments herein, MRI and PET images of the brain are used. Support vector machine classifiers are then trained based on the most discriminative features selected from the feature set. To facilitate robust classification and optimal selection of parameters involved in classification, in view of the well-known "curse of dimensionality", base classifiers are constructed in a bagging (bootstrap aggregating) framework for building an ensemble classifier and the classification parameters of these base classifiers are optimized by means of maximizing the area under the ROC (receiver operating characteristic) curve estimated from their prediction performance on left-out samples of bootstrap sampling. This classification system is tested on a sex classification problem, where it yields over 90% classification rates for unseen subjects. The proposed classification method is also compared with other commonly used classification algorithms, with favorable results. These results illustrate that the methods built upon information jointly extracted from multi-parametric images have the potential to perform individual classification with high sensitivity and specificity.

Scattering features for lung cancer detection in fibered confocal fluorescence microscopy images.

PubMed

Rakotomamonjy, Alain; Petitjean, Caroline; Salaün, Mathieu; Thiberville, Luc

2014-06-01

To assess the feasibility of lung cancer diagnosis using fibered confocal fluorescence microscopy (FCFM) imaging technique and scattering features for pattern recognition. FCFM imaging technique is a new medical imaging technique for which interest has yet to be established for diagnosis. This paper addresses the problem of lung cancer detection using FCFM images and, as a first contribution, assesses the feasibility of computer-aided diagnosis through these images. Towards this aim, we have built a pattern recognition scheme which involves a feature extraction stage and a classification stage. The second contribution relies on the features used for discrimination. Indeed, we have employed the so-called scattering transform for extracting discriminative features, which are robust to small deformations in the images. We have also compared and combined these features with classical yet powerful features like local binary patterns (LBP) and their variants denoted as local quinary patterns (LQP). We show that scattering features yielded to better recognition performances than classical features like LBP and their LQP variants for the FCFM image classification problems. Another finding is that LBP-based and scattering-based features provide complementary discriminative information and, in some situations, we empirically establish that performance can be improved when jointly using LBP, LQP and scattering features. In this work we analyze the joint capability of FCFM images and scattering features for lung cancer diagnosis. The proposed method achieves a good recognition rate for such a diagnosis problem. It also performs well when used in conjunction with other features for other classical medical imaging classification problems. Copyright © 2014 Elsevier B.V. All rights reserved.

Visual Recognition Software for Binary Classification and Its Application to Spruce Pollen Identification

PubMed Central

Tcheng, David K.; Nayak, Ashwin K.; Fowlkes, Charless C.; Punyasena, Surangi W.

2016-01-01

Discriminating between black and white spruce (Picea mariana and Picea glauca) is a difficult palynological classification problem that, if solved, would provide valuable data for paleoclimate reconstructions. We developed an open-source visual recognition software (ARLO, Automated Recognition with Layered Optimization) capable of differentiating between these two species at an accuracy on par with human experts. The system applies pattern recognition and machine learning to the analysis of pollen images and discovers general-purpose image features, defined by simple features of lines and grids of pixels taken at different dimensions, size, spacing, and resolution. It adapts to a given problem by searching for the most effective combination of both feature representation and learning strategy. This results in a powerful and flexible framework for image classification. We worked with images acquired using an automated slide scanner. We first applied a hash-based “pollen spotting” model to segment pollen grains from the slide background. We next tested ARLO’s ability to reconstruct black to white spruce pollen ratios using artificially constructed slides of known ratios. We then developed a more scalable hash-based method of image analysis that was able to distinguish between the pollen of black and white spruce with an estimated accuracy of 83.61%, comparable to human expert performance. Our results demonstrate the capability of machine learning systems to automate challenging taxonomic classifications in pollen analysis, and our success with simple image representations suggests that our approach is generalizable to many other object recognition problems. PMID:26867017

Parallel-hierarchical processing and classification of laser beam profile images based on the GPU-oriented architecture

NASA Astrophysics Data System (ADS)

Yarovyi, Andrii A.; Timchenko, Leonid I.; Kozhemiako, Volodymyr P.; Kokriatskaia, Nataliya I.; Hamdi, Rami R.; Savchuk, Tamara O.; Kulyk, Oleksandr O.; Surtel, Wojciech; Amirgaliyev, Yedilkhan; Kashaganova, Gulzhan

2017-08-01

The paper deals with a problem of insufficient productivity of existing computer means for large image processing, which do not meet modern requirements posed by resource-intensive computing tasks of laser beam profiling. The research concentrated on one of the profiling problems, namely, real-time processing of spot images of the laser beam profile. Development of a theory of parallel-hierarchic transformation allowed to produce models for high-performance parallel-hierarchical processes, as well as algorithms and software for their implementation based on the GPU-oriented architecture using GPGPU technologies. The analyzed performance of suggested computerized tools for processing and classification of laser beam profile images allows to perform real-time processing of dynamic images of various sizes.

Exploring Deep Learning and Sparse Matrix Format Selection

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zhao, Y.; Liao, C.; Shen, X.

We proposed to explore the use of Deep Neural Networks (DNN) for addressing the longstanding barriers. The recent rapid progress of DNN technology has created a large impact in many fields, which has significantly improved the prediction accuracy over traditional machine learning techniques in image classifications, speech recognitions, machine translations, and so on. To some degree, these tasks resemble the decision makings in many HPC tasks, including the aforementioned format selection for SpMV and linear solver selection. For instance, sparse matrix format selection is akin to image classification—such as, to tell whether an image contains a dog or a cat;more » in both problems, the right decisions are primarily determined by the spatial patterns of the elements in an input. For image classification, the patterns are of pixels, and for sparse matrix format selection, they are of non-zero elements. DNN could be naturally applied if we regard a sparse matrix as an image and the format selection or solver selection as classification problems.« less

Using machine learning techniques to automate sky survey catalog generation

NASA Technical Reports Server (NTRS)

Fayyad, Usama M.; Roden, J. C.; Doyle, R. J.; Weir, Nicholas; Djorgovski, S. G.

1993-01-01

We describe the application of machine classification techniques to the development of an automated tool for the reduction of a large scientific data set. The 2nd Palomar Observatory Sky Survey provides comprehensive photographic coverage of the northern celestial hemisphere. The photographic plates are being digitized into images containing on the order of 10(exp 7) galaxies and 10(exp 8) stars. Since the size of this data set precludes manual analysis and classification of objects, our approach is to develop a software system which integrates independently developed techniques for image processing and data classification. Image processing routines are applied to identify and measure features of sky objects. Selected features are used to determine the classification of each object. GID3* and O-BTree, two inductive learning techniques, are used to automatically learn classification decision trees from examples. We describe the techniques used, the details of our specific application, and the initial encouraging results which indicate that our approach is well-suited to the problem. The benefits of the approach are increased data reduction throughput, consistency of classification, and the automated derivation of classification rules that will form an objective, examinable basis for classifying sky objects. Furthermore, astronomers will be freed from the tedium of an intensely visual task to pursue more challenging analysis and interpretation problems given automatically cataloged data.

Application of Convolutional Neural Network in Classification of High Resolution Agricultural Remote Sensing Images

NASA Astrophysics Data System (ADS)

Yao, C.; Zhang, Y.; Zhang, Y.; Liu, H.

2017-09-01

With the rapid development of Precision Agriculture (PA) promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN). For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66 % after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.

Online image classification under monotonic decision boundary constraint

NASA Astrophysics Data System (ADS)

Lu, Cheng; Allebach, Jan; Wagner, Jerry; Pitta, Brandi; Larson, David; Guo, Yandong

2015-01-01

Image classification is a prerequisite for copy quality enhancement in all-in-one (AIO) device that comprises a printer and scanner, and which can be used to scan, copy and print. Different processing pipelines are provided in an AIO printer. Each of the processing pipelines is designed specifically for one type of input image to achieve the optimal output image quality. A typical approach to this problem is to apply Support Vector Machine to classify the input image and feed it to its corresponding processing pipeline. The online training SVM can help users to improve the performance of classification as input images accumulate. At the same time, we want to make quick decision on the input image to speed up the classification which means sometimes the AIO device does not need to scan the entire image to make a final decision. These two constraints, online SVM and quick decision, raise questions regarding: 1) what features are suitable for classification; 2) how we should control the decision boundary in online SVM training. This paper will discuss the compatibility of online SVM and quick decision capability.

Steganalysis feature improvement using expectation maximization

NASA Astrophysics Data System (ADS)

Rodriguez, Benjamin M.; Peterson, Gilbert L.; Agaian, Sos S.

2007-04-01

Images and data files provide an excellent opportunity for concealing illegal or clandestine material. Currently, there are over 250 different tools which embed data into an image without causing noticeable changes to the image. From a forensics perspective, when a system is confiscated or an image of a system is generated the investigator needs a tool that can scan and accurately identify files suspected of containing malicious information. The identification process is termed the steganalysis problem which focuses on both blind identification, in which only normal images are available for training, and multi-class identification, in which both the clean and stego images at several embedding rates are available for training. In this paper an investigation of a clustering and classification technique (Expectation Maximization with mixture models) is used to determine if a digital image contains hidden information. The steganalysis problem is for both anomaly detection and multi-class detection. The various clusters represent clean images and stego images with between 1% and 10% embedding percentage. Based on the results it is concluded that the EM classification technique is highly suitable for both blind detection and the multi-class problem.

Graph-Based Semi-Supervised Hyperspectral Image Classification Using Spatial Information

NASA Astrophysics Data System (ADS)

Jamshidpour, N.; Homayouni, S.; Safari, A.

2017-09-01

Hyperspectral image classification has been one of the most popular research areas in the remote sensing community in the past decades. However, there are still some problems that need specific attentions. For example, the lack of enough labeled samples and the high dimensionality problem are two most important issues which degrade the performance of supervised classification dramatically. The main idea of semi-supervised learning is to overcome these issues by the contribution of unlabeled samples, which are available in an enormous amount. In this paper, we propose a graph-based semi-supervised classification method, which uses both spectral and spatial information for hyperspectral image classification. More specifically, two graphs were designed and constructed in order to exploit the relationship among pixels in spectral and spatial spaces respectively. Then, the Laplacians of both graphs were merged to form a weighted joint graph. The experiments were carried out on two different benchmark hyperspectral data sets. The proposed method performed significantly better than the well-known supervised classification methods, such as SVM. The assessments consisted of both accuracy and homogeneity analyses of the produced classification maps. The proposed spectral-spatial SSL method considerably increased the classification accuracy when the labeled training data set is too scarce.When there were only five labeled samples for each class, the performance improved 5.92% and 10.76% compared to spatial graph-based SSL, for AVIRIS Indian Pine and Pavia University data sets respectively.

Multitask SVM learning for remote sensing data classification

NASA Astrophysics Data System (ADS)

Leiva-Murillo, Jose M.; Gómez-Chova, Luis; Camps-Valls, Gustavo

2010-10-01

Many remote sensing data processing problems are inherently constituted by several tasks that can be solved either individually or jointly. For instance, each image in a multitemporal classification setting could be taken as an individual task but relation to previous acquisitions should be properly considered. In such problems, different modalities of the data (temporal, spatial, angular) gives rise to changes between the training and test distributions, which constitutes a difficult learning problem known as covariate shift. Multitask learning methods aim at jointly solving a set of prediction problems in an efficient way by sharing information across tasks. This paper presents a novel kernel method for multitask learning in remote sensing data classification. The proposed method alleviates the dataset shift problem by imposing cross-information in the classifiers through matrix regularization. We consider the support vector machine (SVM) as core learner and two regularization schemes are introduced: 1) the Euclidean distance of the predictors in the Hilbert space; and 2) the inclusion of relational operators between tasks. Experiments are conducted in the challenging remote sensing problems of cloud screening from multispectral MERIS images and for landmine detection.

Automated measurement of retinal vascular tortuosity.

PubMed Central

Hart, W. E.; Goldbaum, M.; Côté, B.; Kube, P.; Nelson, M. R.

1997-01-01

Automatic measurement of blood vessel tortuosity is a useful capability for automatic ophthalmological diagnostic tools. We describe a suite of automated tortuosity measures for blood vessel segments extracted from RGB retinal images. The tortuosity measures were evaluated in two classification tasks: (1) classifying the tortuosity of blood vessel segments and (2) classifying the tortuosity of blood vessel networks. These tortuosity measures were able to achieve a classification rate of 91% for the first problem and 95% on the second problem, which confirms that they capture much of the ophthalmologists' notion of tortuosity. Images Figure 1 PMID:9357668

Semantic labeling of digital photos by classification

NASA Astrophysics Data System (ADS)

Ciocca, Gianluigi; Cusano, Claudio; Schettini, Raimondo; Brambilla, Carla

2003-01-01

The paper addresses the problem of annotating photographs with broad semantic labels. To cope with the great variety of photos available on the WEB we have designed a hierarchical classification strategy which first classifies images as pornographic or not-pornographic. Not-pornographic images are then classified as indoor, outdoor, or close-up. On a database of over 9000 images, mostly downloaded from the web, our method achieves an average accuracy of close to 90%.

Collaborative classification of hyperspectral and visible images with convolutional neural network

NASA Astrophysics Data System (ADS)

Zhang, Mengmeng; Li, Wei; Du, Qian

2017-10-01

Recent advances in remote sensing technology have made multisensor data available for the same area, and it is well-known that remote sensing data processing and analysis often benefit from multisource data fusion. Specifically, low spatial resolution of hyperspectral imagery (HSI) degrades the quality of the subsequent classification task while using visible (VIS) images with high spatial resolution enables high-fidelity spatial analysis. A collaborative classification framework is proposed to fuse HSI and VIS images for finer classification. First, the convolutional neural network model is employed to extract deep spectral features for HSI classification. Second, effective binarized statistical image features are learned as contextual basis vectors for the high-resolution VIS image, followed by a classifier. The proposed approach employs diversified data in a decision fusion, leading to an integration of the rich spectral information, spatial information, and statistical representation information. In particular, the proposed approach eliminates the potential problems of the curse of dimensionality and excessive computation time. The experiments evaluated on two standard data sets demonstrate better classification performance offered by this framework.

Using genetically modified tomato crop plants with purple leaves for absolute weed/crop classification.

PubMed

Lati, Ran N; Filin, Sagi; Aly, Radi; Lande, Tal; Levin, Ilan; Eizenberg, Hanan

2014-07-01

Weed/crop classification is considered the main problem in developing precise weed-management methodologies, because both crops and weeds share similar hues. Great effort has been invested in the development of classification models, most based on expensive sensors and complicated algorithms. However, satisfactory results are not consistently obtained due to imaging conditions in the field. We report on an innovative approach that combines advances in genetic engineering and robust image-processing methods to detect weeds and distinguish them from crop plants by manipulating the crop's leaf color. We demonstrate this on genetically modified tomato (germplasm AN-113) which expresses a purple leaf color. An autonomous weed/crop classification is performed using an invariant-hue transformation that is applied to images acquired by a standard consumer camera (visible wavelength) and handles variations in illumination intensities. The integration of these methodologies is simple and effective, and classification results were accurate and stable under a wide range of imaging conditions. Using this approach, we simplify the most complicated stage in image-based weed/crop classification models. © 2013 Society of Chemical Industry.

Combining convolutional neural networks and Hough Transform for classification of images containing lines

NASA Astrophysics Data System (ADS)

Sheshkus, Alexander; Limonova, Elena; Nikolaev, Dmitry; Krivtsov, Valeriy

2017-03-01

In this paper, we propose an expansion of convolutional neural network (CNN) input features based on Hough Transform. We perform morphological contrasting of source image followed by Hough Transform, and then use it as input for some convolutional filters. Thus, CNNs computational complexity and the number of units are not affected. Morphological contrasting and Hough Transform are the only additional computational expenses of introduced CNN input features expansion. Proposed approach was demonstrated on the example of CNN with very simple structure. We considered two image recognition problems, that were object classification on CIFAR-10 and printed character recognition on private dataset with symbols taken from Russian passports. Our approach allowed to reach noticeable accuracy improvement without taking much computational effort, which can be extremely important in industrial recognition systems or difficult problems utilising CNNs, like pressure ridge analysis and classification.

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Deep Learning-Based Banknote Fitness Classification Using the Reflection Images by a Visible-Light One-Dimensional Line Image Sensor

PubMed Central

Pham, Tuyen Danh; Nguyen, Dat Tien; Kim, Wan; Park, Sung Ho; Park, Kang Ryoung

2018-01-01

In automatic paper currency sorting, fitness classification is a technique that assesses the quality of banknotes to determine whether a banknote is suitable for recirculation or should be replaced. Studies on using visible-light reflection images of banknotes for evaluating their usability have been reported. However, most of them were conducted under the assumption that the denomination and input direction of the banknote are predetermined. In other words, a pre-classification of the type of input banknote is required. To address this problem, we proposed a deep learning-based fitness-classification method that recognizes the fitness level of a banknote regardless of the denomination and input direction of the banknote to the system, using the reflection images of banknotes by visible-light one-dimensional line image sensor and a convolutional neural network (CNN). Experimental results on the banknote image databases of the Korean won (KRW) and the Indian rupee (INR) with three fitness levels, and the Unites States dollar (USD) with two fitness levels, showed that our method gives better classification accuracy than other methods. PMID:29415447

Task-driven dictionary learning.

PubMed

Mairal, Julien; Bach, Francis; Ponce, Jean

2012-04-01

Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience, and signal processing. For signals such as natural images that admit such sparse representations, it is now well established that these models are well suited to restoration tasks. In this context, learning the dictionary amounts to solving a large-scale matrix factorization problem, which can be done efficiently with classical optimization tools. The same approach has also been used for learning features from data for other purposes, e.g., image classification, but tuning the dictionary in a supervised way for these tasks has proven to be more difficult. In this paper, we present a general formulation for supervised dictionary learning adapted to a wide variety of tasks, and present an efficient algorithm for solving the corresponding optimization problem. Experiments on handwritten digit classification, digital art identification, nonlinear inverse image problems, and compressed sensing demonstrate that our approach is effective in large-scale settings, and is well suited to supervised and semi-supervised classification, as well as regression tasks for data that admit sparse representations.

GENIE: a hybrid genetic algorithm for feature classification in multispectral images

NASA Astrophysics Data System (ADS)

Perkins, Simon J.; Theiler, James P.; Brumby, Steven P.; Harvey, Neal R.; Porter, Reid B.; Szymanski, John J.; Bloch, Jeffrey J.

2000-10-01

We consider the problem of pixel-by-pixel classification of a multi- spectral image using supervised learning. Conventional spuervised classification techniques such as maximum likelihood classification and less conventional ones s uch as neural networks, typically base such classifications solely on the spectral components of each pixel. It is easy to see why: the color of a pixel provides a nice, bounded, fixed dimensional space in which these classifiers work well. It is often the case however, that spectral information alone is not sufficient to correctly classify a pixel. Maybe spatial neighborhood information is required as well. Or maybe the raw spectral components do not themselves make for easy classification, but some arithmetic combination of them would. In either of these cases we have the problem of selecting suitable spatial, spectral or spatio-spectral features that allow the classifier to do its job well. The number of all possible such features is extremely large. How can we select a suitable subset? We have developed GENIE, a hybrid learning system that combines a genetic algorithm that searches a space of image processing operations for a set that can produce suitable feature planes, and a more conventional classifier which uses those feature planes to output a final classification. In this paper we show that the use of a hybrid GA provides significant advantages over using either a GA alone or more conventional classification methods alone. We present results using high-resolution IKONOS data, looking for regions of burned forest and for roads.

Brain tumor segmentation based on local independent projection-based classification.

PubMed

Huang, Meiyan; Yang, Wei; Wu, Yao; Jiang, Jun; Chen, Wufan; Feng, Qianjin

2014-10-01

Brain tumor segmentation is an important procedure for early tumor diagnosis and radiotherapy planning. Although numerous brain tumor segmentation methods have been presented, enhancing tumor segmentation methods is still challenging because brain tumor MRI images exhibit complex characteristics, such as high diversity in tumor appearance and ambiguous tumor boundaries. To address this problem, we propose a novel automatic tumor segmentation method for MRI images. This method treats tumor segmentation as a classification problem. Additionally, the local independent projection-based classification (LIPC) method is used to classify each voxel into different classes. A novel classification framework is derived by introducing the local independent projection into the classical classification model. Locality is important in the calculation of local independent projections for LIPC. Locality is also considered in determining whether local anchor embedding is more applicable in solving linear projection weights compared with other coding methods. Moreover, LIPC considers the data distribution of different classes by learning a softmax regression model, which can further improve classification performance. In this study, 80 brain tumor MRI images with ground truth data are used as training data and 40 images without ground truth data are used as testing data. The segmentation results of testing data are evaluated by an online evaluation tool. The average dice similarities of the proposed method for segmenting complete tumor, tumor core, and contrast-enhancing tumor on real patient data are 0.84, 0.685, and 0.585, respectively. These results are comparable to other state-of-the-art methods.

Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification

NASA Technical Reports Server (NTRS)

Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin

1990-01-01

Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.

Consensus embedding: theory, algorithms and application to segmentation and classification of biomedical data

PubMed Central

2012-01-01

Background Dimensionality reduction (DR) enables the construction of a lower dimensional space (embedding) from a higher dimensional feature space while preserving object-class discriminability. However several popular DR approaches suffer from sensitivity to choice of parameters and/or presence of noise in the data. In this paper, we present a novel DR technique known as consensus embedding that aims to overcome these problems by generating and combining multiple low-dimensional embeddings, hence exploiting the variance among them in a manner similar to ensemble classifier schemes such as Bagging. We demonstrate theoretical properties of consensus embedding which show that it will result in a single stable embedding solution that preserves information more accurately as compared to any individual embedding (generated via DR schemes such as Principal Component Analysis, Graph Embedding, or Locally Linear Embedding). Intelligent sub-sampling (via mean-shift) and code parallelization are utilized to provide for an efficient implementation of the scheme. Results Applications of consensus embedding are shown in the context of classification and clustering as applied to: (1) image partitioning of white matter and gray matter on 10 different synthetic brain MRI images corrupted with 18 different combinations of noise and bias field inhomogeneity, (2) classification of 4 high-dimensional gene-expression datasets, (3) cancer detection (at a pixel-level) on 16 image slices obtained from 2 different high-resolution prostate MRI datasets. In over 200 different experiments concerning classification and segmentation of biomedical data, consensus embedding was found to consistently outperform both linear and non-linear DR methods within all applications considered. Conclusions We have presented a novel framework termed consensus embedding which leverages ensemble classification theory within dimensionality reduction, allowing for application to a wide range of high-dimensional biomedical data classification and segmentation problems. Our generalizable framework allows for improved representation and classification in the context of both imaging and non-imaging data. The algorithm offers a promising solution to problems that currently plague DR methods, and may allow for extension to other areas of biomedical data analysis. PMID:22316103

Peculiarities of use of ECOC and AdaBoost based classifiers for thematic processing of hyperspectral data

NASA Astrophysics Data System (ADS)

Dementev, A. O.; Dmitriev, E. V.; Kozoderov, V. V.; Egorov, V. D.

2017-10-01

Hyperspectral imaging is up-to-date promising technology widely applied for the accurate thematic mapping. The presence of a large number of narrow survey channels allows us to use subtle differences in spectral characteristics of objects and to make a more detailed classification than in the case of using standard multispectral data. The difficulties encountered in the processing of hyperspectral images are usually associated with the redundancy of spectral information which leads to the problem of the curse of dimensionality. Methods currently used for recognizing objects on multispectral and hyperspectral images are usually based on standard base supervised classification algorithms of various complexity. Accuracy of these algorithms can be significantly different depending on considered classification tasks. In this paper we study the performance of ensemble classification methods for the problem of classification of the forest vegetation. Error correcting output codes and boosting are tested on artificial data and real hyperspectral images. It is demonstrates, that boosting gives more significant improvement when used with simple base classifiers. The accuracy in this case in comparable the error correcting output code (ECOC) classifier with Gaussian kernel SVM base algorithm. However the necessity of boosting ECOC with Gaussian kernel SVM is questionable. It is demonstrated, that selected ensemble classifiers allow us to recognize forest species with high enough accuracy which can be compared with ground-based forest inventory data.

Automated Processing of Imaging Data through Multi-tiered Classification of Biological Structures Illustrated Using Caenorhabditis elegans.

PubMed

Zhan, Mei; Crane, Matthew M; Entchev, Eugeni V; Caballero, Antonio; Fernandes de Abreu, Diana Andrea; Ch'ng, QueeLim; Lu, Hang

2015-04-01

Quantitative imaging has become a vital technique in biological discovery and clinical diagnostics; a plethora of tools have recently been developed to enable new and accelerated forms of biological investigation. Increasingly, the capacity for high-throughput experimentation provided by new imaging modalities, contrast techniques, microscopy tools, microfluidics and computer controlled systems shifts the experimental bottleneck from the level of physical manipulation and raw data collection to automated recognition and data processing. Yet, despite their broad importance, image analysis solutions to address these needs have been narrowly tailored. Here, we present a generalizable formulation for autonomous identification of specific biological structures that is applicable for many problems. The process flow architecture we present here utilizes standard image processing techniques and the multi-tiered application of classification models such as support vector machines (SVM). These low-level functions are readily available in a large array of image processing software packages and programming languages. Our framework is thus both easy to implement at the modular level and provides specific high-level architecture to guide the solution of more complicated image-processing problems. We demonstrate the utility of the classification routine by developing two specific classifiers as a toolset for automation and cell identification in the model organism Caenorhabditis elegans. To serve a common need for automated high-resolution imaging and behavior applications in the C. elegans research community, we contribute a ready-to-use classifier for the identification of the head of the animal under bright field imaging. Furthermore, we extend our framework to address the pervasive problem of cell-specific identification under fluorescent imaging, which is critical for biological investigation in multicellular organisms or tissues. Using these examples as a guide, we envision the broad utility of the framework for diverse problems across different length scales and imaging methods.

Adipose Tissue Quantification by Imaging Methods: A Proposed Classification

PubMed Central

Shen, Wei; Wang, ZiMian; Punyanita, Mark; Lei, Jianbo; Sinav, Ahmet; Kral, John G.; Imielinska, Celina; Ross, Robert; Heymsfield, Steven B.

2007-01-01

Recent advances in imaging techniques and understanding of differences in the molecular biology of adipose tissue has rendered classical anatomy obsolete, requiring a new classification of the topography of adipose tissue. Adipose tissue is one of the largest body compartments, yet a classification that defines specific adipose tissue depots based on their anatomic location and related functions is lacking. The absence of an accepted taxonomy poses problems for investigators studying adipose tissue topography and its functional correlates. The aim of this review was to critically examine the literature on imaging of whole body and regional adipose tissue and to create the first systematic classification of adipose tissue topography. Adipose tissue terminology was examined in over 100 original publications. Our analysis revealed inconsistencies in the use of specific definitions, especially for the compartment termed “visceral” adipose tissue. This analysis leads us to propose an updated classification of total body and regional adipose tissue, providing a well-defined basis for correlating imaging studies of specific adipose tissue depots with molecular processes. PMID:12529479

Classification of Tree Species in Overstorey Canopy of Subtropical Forest Using QuickBird Images.

PubMed

Lin, Chinsu; Popescu, Sorin C; Thomson, Gavin; Tsogt, Khongor; Chang, Chein-I

2015-01-01

This paper proposes a supervised classification scheme to identify 40 tree species (2 coniferous, 38 broadleaf) belonging to 22 families and 36 genera in high spatial resolution QuickBird multispectral images (HMS). Overall kappa coefficient (OKC) and species conditional kappa coefficients (SCKC) were used to evaluate classification performance in training samples and estimate accuracy and uncertainty in test samples. Baseline classification performance using HMS images and vegetation index (VI) images were evaluated with an OKC value of 0.58 and 0.48 respectively, but performance improved significantly (up to 0.99) when used in combination with an HMS spectral-spatial texture image (SpecTex). One of the 40 species had very high conditional kappa coefficient performance (SCKC ≥ 0.95) using 4-band HMS and 5-band VIs images, but, only five species had lower performance (0.68 ≤ SCKC ≤ 0.94) using the SpecTex images. When SpecTex images were combined with a Visible Atmospherically Resistant Index (VARI), there was a significant improvement in performance in the training samples. The same level of improvement could not be replicated in the test samples indicating that a high degree of uncertainty exists in species classification accuracy which may be due to individual tree crown density, leaf greenness (inter-canopy gaps), and noise in the background environment (intra-canopy gaps). These factors increase uncertainty in the spectral texture features and therefore represent potential problems when using pixel-based classification techniques for multi-species classification.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jurrus, Elizabeth R.; Hodas, Nathan O.; Baker, Nathan A.

Forensic analysis of nanoparticles is often conducted through the collection and identifi- cation of electron microscopy images to determine the origin of suspected nuclear material. Each image is carefully studied by experts for classification of materials based on texture, shape, and size. Manually inspecting large image datasets takes enormous amounts of time. However, automatic classification of large image datasets is a challenging problem due to the complexity involved in choosing image features, the lack of training data available for effective machine learning methods, and the availability of user interfaces to parse through images. Therefore, a significant need exists for automatedmore » and semi-automated methods to help analysts perform accurate image classification in large image datasets. We present INStINCt, our Intelligent Signature Canvas, as a framework for quickly organizing image data in a web based canvas framework. Images are partitioned using small sets of example images, chosen by users, and presented in an optimal layout based on features derived from convolutional neural networks.« less

Effective Sequential Classifier Training for SVM-Based Multitemporal Remote Sensing Image Classification

NASA Astrophysics Data System (ADS)

Guo, Yiqing; Jia, Xiuping; Paull, David

2018-06-01

The explosive availability of remote sensing images has challenged supervised classification algorithms such as Support Vector Machines (SVM), as training samples tend to be highly limited due to the expensive and laborious task of ground truthing. The temporal correlation and spectral similarity between multitemporal images have opened up an opportunity to alleviate this problem. In this study, a SVM-based Sequential Classifier Training (SCT-SVM) approach is proposed for multitemporal remote sensing image classification. The approach leverages the classifiers of previous images to reduce the required number of training samples for the classifier training of an incoming image. For each incoming image, a rough classifier is firstly predicted based on the temporal trend of a set of previous classifiers. The predicted classifier is then fine-tuned into a more accurate position with current training samples. This approach can be applied progressively to sequential image data, with only a small number of training samples being required from each image. Experiments were conducted with Sentinel-2A multitemporal data over an agricultural area in Australia. Results showed that the proposed SCT-SVM achieved better classification accuracies compared with two state-of-the-art model transfer algorithms. When training data are insufficient, the overall classification accuracy of the incoming image was improved from 76.18% to 94.02% with the proposed SCT-SVM, compared with those obtained without the assistance from previous images. These results demonstrate that the leverage of a priori information from previous images can provide advantageous assistance for later images in multitemporal image classification.

Learning discriminative features from RGB-D images for gender and ethnicity identification

NASA Astrophysics Data System (ADS)

Azzakhnini, Safaa; Ballihi, Lahoucine; Aboutajdine, Driss

2016-11-01

The development of sophisticated sensor technologies gave rise to an interesting variety of data. With the appearance of affordable devices, such as the Microsoft Kinect, depth-maps and three-dimensional data became easily accessible. This attracted many computer vision researchers seeking to exploit this information in classification and recognition tasks. In this work, the problem of face classification in the context of RGB images and depth information (RGB-D images) is addressed. The purpose of this paper is to study and compare some popular techniques for gender recognition and ethnicity classification to understand how much depth data can improve the quality of recognition. Furthermore, we investigate which combination of face descriptors, feature selection methods, and learning techniques is best suited to better exploit RGB-D images. The experimental results show that depth data improve the recognition accuracy for gender and ethnicity classification applications in many use cases.

Visual attention based bag-of-words model for image classification

NASA Astrophysics Data System (ADS)

Wang, Qiwei; Wan, Shouhong; Yue, Lihua; Wang, Che

2014-04-01

Bag-of-words is a classical method for image classification. The core problem is how to count the frequency of the visual words and what visual words to select. In this paper, we propose a visual attention based bag-of-words model (VABOW model) for image classification task. The VABOW model utilizes visual attention method to generate a saliency map, and uses the saliency map as a weighted matrix to instruct the statistic process for the frequency of the visual words. On the other hand, the VABOW model combines shape, color and texture cues and uses L1 regularization logistic regression method to select the most relevant and most efficient features. We compare our approach with traditional bag-of-words based method on two datasets, and the result shows that our VABOW model outperforms the state-of-the-art method for image classification.

Recognition of Banknote Fitness Based on a Fuzzy System Using Visible Light Reflection and Near-infrared Light Transmission Images.

PubMed

Kwon, Seung Yong; Pham, Tuyen Danh; Park, Kang Ryoung; Jeong, Dae Sik; Yoon, Sungsoo

2016-06-11

Fitness classification is a technique to assess the quality of banknotes in order to determine whether they are usable. Banknote classification techniques are useful in preventing problems that arise from the circulation of substandard banknotes (such as recognition failures, or bill jams in automated teller machines (ATMs) or bank counting machines). By and large, fitness classification continues to be carried out by humans, and this can cause the problem of varying fitness classifications for the same bill by different evaluators, and requires a lot of time. To address these problems, this study proposes a fuzzy system-based method that can reduce the processing time needed for fitness classification, and can determine the fitness of banknotes through an objective, systematic method rather than subjective judgment. Our algorithm was an implementation to actual banknote counting machine. Based on the results of tests on 3856 banknotes in United States currency (USD), 3956 in Korean currency (KRW), and 2300 banknotes in Indian currency (INR) using visible light reflection (VR) and near-infrared light transmission (NIRT) imaging, the proposed method was found to yield higher accuracy than prevalent banknote fitness classification methods. Moreover, it was confirmed that the proposed algorithm can operate in real time, not only in a normal PC environment, but also in an embedded system environment of a banknote counting machine.

Recognition of Banknote Fitness Based on a Fuzzy System Using Visible Light Reflection and Near-infrared Light Transmission Images

PubMed Central

Kwon, Seung Yong; Pham, Tuyen Danh; Park, Kang Ryoung; Jeong, Dae Sik; Yoon, Sungsoo

2016-01-01

Fitness classification is a technique to assess the quality of banknotes in order to determine whether they are usable. Banknote classification techniques are useful in preventing problems that arise from the circulation of substandard banknotes (such as recognition failures, or bill jams in automated teller machines (ATMs) or bank counting machines). By and large, fitness classification continues to be carried out by humans, and this can cause the problem of varying fitness classifications for the same bill by different evaluators, and requires a lot of time. To address these problems, this study proposes a fuzzy system-based method that can reduce the processing time needed for fitness classification, and can determine the fitness of banknotes through an objective, systematic method rather than subjective judgment. Our algorithm was an implementation to actual banknote counting machine. Based on the results of tests on 3856 banknotes in United States currency (USD), 3956 in Korean currency (KRW), and 2300 banknotes in Indian currency (INR) using visible light reflection (VR) and near-infrared light transmission (NIRT) imaging, the proposed method was found to yield higher accuracy than prevalent banknote fitness classification methods. Moreover, it was confirmed that the proposed algorithm can operate in real time, not only in a normal PC environment, but also in an embedded system environment of a banknote counting machine. PMID:27294940

Sunspot Pattern Classification using PCA and Neural Networks (Poster)

NASA Technical Reports Server (NTRS)

Rajkumar, T.; Thompson, D. E.; Slater, G. L.

2005-01-01

The sunspot classification scheme presented in this paper is considered as a 2-D classification problem on archived datasets, and is not a real-time system. As a first step, it mirrors the Zuerich/McIntosh historical classification system and reproduces classification of sunspot patterns based on preprocessing and neural net training datasets. Ultimately, the project intends to move from more rudimentary schemes, to develop spatial-temporal-spectral classes derived by correlating spatial and temporal variations in various wavelengths to the brightness fluctuation spectrum of the sun in those wavelengths. Once the approach is generalized, then the focus will naturally move from a 2-D to an n-D classification, where "n" includes time and frequency. Here, the 2-D perspective refers both to the actual SOH0 Michelson Doppler Imager (MDI) images that are processed, but also refers to the fact that a 2-D matrix is created from each image during preprocessing. The 2-D matrix is the result of running Principal Component Analysis (PCA) over the selected dataset images, and the resulting matrices and their eigenvalues are the objects that are stored in a database, classified, and compared. These matrices are indexed according to the standard McIntosh classification scheme.

CP-CHARM: segmentation-free image classification made accessible.

PubMed

Uhlmann, Virginie; Singh, Shantanu; Carpenter, Anne E

2016-01-27

Automated classification using machine learning often relies on features derived from segmenting individual objects, which can be difficult to automate. WND-CHARM is a previously developed classification algorithm in which features are computed on the whole image, thereby avoiding the need for segmentation. The algorithm obtained encouraging results but requires considerable computational expertise to execute. Furthermore, some benchmark sets have been shown to be subject to confounding artifacts that overestimate classification accuracy. We developed CP-CHARM, a user-friendly image-based classification algorithm inspired by WND-CHARM in (i) its ability to capture a wide variety of morphological aspects of the image, and (ii) the absence of requirement for segmentation. In order to make such an image-based classification method easily accessible to the biological research community, CP-CHARM relies on the widely-used open-source image analysis software CellProfiler for feature extraction. To validate our method, we reproduced WND-CHARM's results and ensured that CP-CHARM obtained comparable performance. We then successfully applied our approach on cell-based assay data and on tissue images. We designed these new training and test sets to reduce the effect of batch-related artifacts. The proposed method preserves the strengths of WND-CHARM - it extracts a wide variety of morphological features directly on whole images thereby avoiding the need for cell segmentation, but additionally, it makes the methods easily accessible for researchers without computational expertise by implementing them as a CellProfiler pipeline. It has been demonstrated to perform well on a wide range of bioimage classification problems, including on new datasets that have been carefully selected and annotated to minimize batch effects. This provides for the first time a realistic and reliable assessment of the whole image classification strategy.

A classification model of Hyperion image base on SAM combined decision tree

NASA Astrophysics Data System (ADS)

Wang, Zhenghai; Hu, Guangdao; Zhou, YongZhang; Liu, Xin

2009-10-01

Monitoring the Earth using imaging spectrometers has necessitated more accurate analyses and new applications to remote sensing. A very high dimensional input space requires an exponentially large amount of data to adequately and reliably represent the classes in that space. On the other hand, with increase in the input dimensionality the hypothesis space grows exponentially, which makes the classification performance highly unreliable. Traditional classification algorithms Classification of hyperspectral images is challenging. New algorithms have to be developed for hyperspectral data classification. The Spectral Angle Mapper (SAM) is a physically-based spectral classification that uses an ndimensional angle to match pixels to reference spectra. The algorithm determines the spectral similarity between two spectra by calculating the angle between the spectra, treating them as vectors in a space with dimensionality equal to the number of bands. The key and difficulty is that we should artificial defining the threshold of SAM. The classification precision depends on the rationality of the threshold of SAM. In order to resolve this problem, this paper proposes a new automatic classification model of remote sensing image using SAM combined with decision tree. It can automatic choose the appropriate threshold of SAM and improve the classify precision of SAM base on the analyze of field spectrum. The test area located in Heqing Yunnan was imaged by EO_1 Hyperion imaging spectrometer using 224 bands in visual and near infrared. The area included limestone areas, rock fields, soil and forests. The area was classified into four different vegetation and soil types. The results show that this method choose the appropriate threshold of SAM and eliminates the disturbance and influence of unwanted objects effectively, so as to improve the classification precision. Compared with the likelihood classification by field survey data, the classification precision of this model heightens 9.9%.

Original and Mirror Face Images and Minimum Squared Error Classification for Visible Light Face Recognition.

PubMed

Wang, Rong

2015-01-01

In real-world applications, the image of faces varies with illumination, facial expression, and poses. It seems that more training samples are able to reveal possible images of the faces. Though minimum squared error classification (MSEC) is a widely used method, its applications on face recognition usually suffer from the problem of a limited number of training samples. In this paper, we improve MSEC by using the mirror faces as virtual training samples. We obtained the mirror faces generated from original training samples and put these two kinds of samples into a new set. The face recognition experiments show that our method does obtain high accuracy performance in classification.

Spatial Uncertainty Modeling of Fuzzy Information in Images for Pattern Classification

PubMed Central

Pham, Tuan D.

2014-01-01

The modeling of the spatial distribution of image properties is important for many pattern recognition problems in science and engineering. Mathematical methods are needed to quantify the variability of this spatial distribution based on which a decision of classification can be made in an optimal sense. However, image properties are often subject to uncertainty due to both incomplete and imprecise information. This paper presents an integrated approach for estimating the spatial uncertainty of vagueness in images using the theory of geostatistics and the calculus of probability measures of fuzzy events. Such a model for the quantification of spatial uncertainty is utilized as a new image feature extraction method, based on which classifiers can be trained to perform the task of pattern recognition. Applications of the proposed algorithm to the classification of various types of image data suggest the usefulness of the proposed uncertainty modeling technique for texture feature extraction. PMID:25157744

Evaluation of Multiple Kernel Learning Algorithms for Crop Mapping Using Satellite Image Time-Series Data

NASA Astrophysics Data System (ADS)

Niazmardi, S.; Safari, A.; Homayouni, S.

2017-09-01

Crop mapping through classification of Satellite Image Time-Series (SITS) data can provide very valuable information for several agricultural applications, such as crop monitoring, yield estimation, and crop inventory. However, the SITS data classification is not straightforward. Because different images of a SITS data have different levels of information regarding the classification problems. Moreover, the SITS data is a four-dimensional data that cannot be classified using the conventional classification algorithms. To address these issues in this paper, we presented a classification strategy based on Multiple Kernel Learning (MKL) algorithms for SITS data classification. In this strategy, initially different kernels are constructed from different images of the SITS data and then they are combined into a composite kernel using the MKL algorithms. The composite kernel, once constructed, can be used for the classification of the data using the kernel-based classification algorithms. We compared the computational time and the classification performances of the proposed classification strategy using different MKL algorithms for the purpose of crop mapping. The considered MKL algorithms are: MKL-Sum, SimpleMKL, LPMKL and Group-Lasso MKL algorithms. The experimental tests of the proposed strategy on two SITS data sets, acquired by SPOT satellite sensors, showed that this strategy was able to provide better performances when compared to the standard classification algorithm. The results also showed that the optimization method of the used MKL algorithms affects both the computational time and classification accuracy of this strategy.

Non-parametric analysis of LANDSAT maps using neural nets and parallel computers

NASA Technical Reports Server (NTRS)

Salu, Yehuda; Tilton, James

1991-01-01

Nearest neighbor approaches and a new neural network, the Binary Diamond, are used for the classification of images of ground pixels obtained by LANDSAT satellite. The performances are evaluated by comparing classifications of a scene in the vicinity of Washington DC. The problem of optimal selection of categories is addressed as a step in the classification process.

Cell dynamic morphology classification using deep convolutional neural networks.

PubMed

Li, Heng; Pang, Fengqian; Shi, Yonggang; Liu, Zhiwen

2018-05-15

Cell morphology is often used as a proxy measurement of cell status to understand cell physiology. Hence, interpretation of cell dynamic morphology is a meaningful task in biomedical research. Inspired by the recent success of deep learning, we here explore the application of convolutional neural networks (CNNs) to cell dynamic morphology classification. An innovative strategy for the implementation of CNNs is introduced in this study. Mouse lymphocytes were collected to observe the dynamic morphology, and two datasets were thus set up to investigate the performances of CNNs. Considering the installation of deep learning, the classification problem was simplified from video data to image data, and was then solved by CNNs in a self-taught manner with the generated image data. CNNs were separately performed in three installation scenarios and compared with existing methods. Experimental results demonstrated the potential of CNNs in cell dynamic morphology classification, and validated the effectiveness of the proposed strategy. CNNs were successfully applied to the classification problem, and outperformed the existing methods in the classification accuracy. For the installation of CNNs, transfer learning was proved to be a promising scheme. © 2018 International Society for Advancement of Cytometry. © 2018 International Society for Advancement of Cytometry.

Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia.

PubMed

Tohka, Jussi; Moradi, Elaheh; Huttunen, Heikki

2016-07-01

We present a comparative split-half resampling analysis of various data driven feature selection and classification methods for the whole brain voxel-based classification analysis of anatomical magnetic resonance images. We compared support vector machines (SVMs), with or without filter based feature selection, several embedded feature selection methods and stability selection. While comparisons of the accuracy of various classification methods have been reported previously, the variability of the out-of-training sample classification accuracy and the set of selected features due to independent training and test sets have not been previously addressed in a brain imaging context. We studied two classification problems: 1) Alzheimer's disease (AD) vs. normal control (NC) and 2) mild cognitive impairment (MCI) vs. NC classification. In AD vs. NC classification, the variability in the test accuracy due to the subject sample did not vary between different methods and exceeded the variability due to different classifiers. In MCI vs. NC classification, particularly with a large training set, embedded feature selection methods outperformed SVM-based ones with the difference in the test accuracy exceeding the test accuracy variability due to the subject sample. The filter and embedded methods produced divergent feature patterns for MCI vs. NC classification that suggests the utility of the embedded feature selection for this problem when linked with the good generalization performance. The stability of the feature sets was strongly correlated with the number of features selected, weakly correlated with the stability of classification accuracy, and uncorrelated with the average classification accuracy.

Satellite Image Classification of Building Damages Using Airborne and Satellite Image Samples in a Deep Learning Approach

NASA Astrophysics Data System (ADS)

Duarte, D.; Nex, F.; Kerle, N.; Vosselman, G.

2018-05-01

The localization and detailed assessment of damaged buildings after a disastrous event is of utmost importance to guide response operations, recovery tasks or for insurance purposes. Several remote sensing platforms and sensors are currently used for the manual detection of building damages. However, there is an overall interest in the use of automated methods to perform this task, regardless of the used platform. Owing to its synoptic coverage and predictable availability, satellite imagery is currently used as input for the identification of building damages by the International Charter, as well as the Copernicus Emergency Management Service for the production of damage grading and reference maps. Recently proposed methods to perform image classification of building damages rely on convolutional neural networks (CNN). These are usually trained with only satellite image samples in a binary classification problem, however the number of samples derived from these images is often limited, affecting the quality of the classification results. The use of up/down-sampling image samples during the training of a CNN, has demonstrated to improve several image recognition tasks in remote sensing. However, it is currently unclear if this multi resolution information can also be captured from images with different spatial resolutions like satellite and airborne imagery (from both manned and unmanned platforms). In this paper, a CNN framework using residual connections and dilated convolutions is used considering both manned and unmanned aerial image samples to perform the satellite image classification of building damages. Three network configurations, trained with multi-resolution image samples are compared against two benchmark networks where only satellite image samples are used. Combining feature maps generated from airborne and satellite image samples, and refining these using only the satellite image samples, improved nearly 4 % the overall satellite image classification of building damages.

Design and optimal control of multi-spacecraft interferometric imaging systems

NASA Astrophysics Data System (ADS)

Chakravorty, Suman

The objective of the proposed NASA Origins mission, Planet Imager, is the high-resolution imaging of exo-solar planets and similar high resolution astronomical imaging applications. The imaging is to be accomplished through the design of multi-spacecraft interferometric imaging systems (MSIIS). In this dissertation, we study the design of MSIIS. Assuming that the ultimate goal of imaging is the correct classification of the formed images, we formulate the design problem as minimization of some resource utilization of the system subject to the constraint that the probability of misclassification of any given image is below a pre-specified level. We model the process of image formation in an MSIIS and show that the Modulation Transfer function of and the noise corrupting the synthesized optical instrument are dependent on the trajectories of the constituent spacecraft. Assuming that the final goal of imaging is the correct classification of the formed image based on a given feature (a real valued function of the image variable), and a threshold on the feature, we find conditions on the noise corrupting the measurements such that the probability of misclassification is below some pre-specified level. These conditions translate into constraints on the trajectories of the constituent spacecraft. Thus, the design problem reduces to minimizing some resource utilization of the system, while satisfying the constraints placed on the system by the imaging requirements. We study the problem of designing minimum time maneuvers for MSIIS. We transform the time minimization problem into a "painting problem". The painting problem involves painting a large disk with smaller paintbrushes (coverage disks). We show that spirals form the dominant set for the solution to the painting problem. We frame the time minimization in the subspace of spirals and obtain a bilinear program, the double pantograph problem, in the design parameters of the spiral, the spiraling rate and the angular rate. We show that the solution of this problem is given by the solution to two associated linear programs. We illustrate our results through a simulation where the banded appearance of a fictitious exo-solar planet at a distance of 8 parsecs is detected.

A framework for farmland parcels extraction based on image classification

NASA Astrophysics Data System (ADS)

Liu, Guoying; Ge, Wenying; Song, Xu; Zhao, Hongdan

2018-03-01

It is very important for the government to build an accurate national basic cultivated land database. In this work, farmland parcels extraction is one of the basic steps. However, during the past years, people had to spend much time on determining an area is a farmland parcel or not, since they were bounded to understand remote sensing images only from the mere visual interpretation. In order to overcome this problem, in this study, a method was proposed to extract farmland parcels by means of image classification. In the proposed method, farmland areas and ridge areas of the classification map are semantically processed independently and the results are fused together to form the final results of farmland parcels. Experiments on high spatial remote sensing images have shown the effectiveness of the proposed method.

Seeing is believing: video classification for computed tomographic colonography using multiple-instance learning.

PubMed

Wang, Shijun; McKenna, Matthew T; Nguyen, Tan B; Burns, Joseph E; Petrick, Nicholas; Sahiner, Berkman; Summers, Ronald M

2012-05-01

In this paper, we present development and testing results for a novel colonic polyp classification method for use as part of a computed tomographic colonography (CTC) computer-aided detection (CAD) system. Inspired by the interpretative methodology of radiologists using 3-D fly-through mode in CTC reading, we have developed an algorithm which utilizes sequences of images (referred to here as videos) for classification of CAD marks. For each CAD mark, we created a video composed of a series of intraluminal, volume-rendered images visualizing the detection from multiple viewpoints. We then framed the video classification question as a multiple-instance learning (MIL) problem. Since a positive (negative) bag may contain negative (positive) instances, which in our case depends on the viewing angles and camera distance to the target, we developed a novel MIL paradigm to accommodate this class of problems. We solved the new MIL problem by maximizing a L2-norm soft margin using semidefinite programming, which can optimize relevant parameters automatically. We tested our method by analyzing a CTC data set obtained from 50 patients from three medical centers. Our proposed method showed significantly better performance compared with several traditional MIL methods.

Seeing is Believing: Video Classification for Computed Tomographic Colonography Using Multiple-Instance Learning

PubMed Central

Wang, Shijun; McKenna, Matthew T.; Nguyen, Tan B.; Burns, Joseph E.; Petrick, Nicholas; Sahiner, Berkman

2012-01-01

In this paper we present development and testing results for a novel colonic polyp classification method for use as part of a computed tomographic colonography (CTC) computer-aided detection (CAD) system. Inspired by the interpretative methodology of radiologists using 3D fly-through mode in CTC reading, we have developed an algorithm which utilizes sequences of images (referred to here as videos) for classification of CAD marks. For each CAD mark, we created a video composed of a series of intraluminal, volume-rendered images visualizing the detection from multiple viewpoints. We then framed the video classification question as a multiple-instance learning (MIL) problem. Since a positive (negative) bag may contain negative (positive) instances, which in our case depends on the viewing angles and camera distance to the target, we developed a novel MIL paradigm to accommodate this class of problems. We solved the new MIL problem by maximizing a L2-norm soft margin using semidefinite programming, which can optimize relevant parameters automatically. We tested our method by analyzing a CTC data set obtained from 50 patients from three medical centers. Our proposed method showed significantly better performance compared with several traditional MIL methods. PMID:22552333

Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

NASA Astrophysics Data System (ADS)

Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

2017-01-01

We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

Brain tumour classification and abnormality detection using neuro-fuzzy technique and Otsu thresholding.

PubMed

Renjith, Arokia; Manjula, P; Mohan Kumar, P

2015-01-01

Brain tumour is one of the main causes for an increase in transience among children and adults. This paper proposes an improved method based on Magnetic Resonance Imaging (MRI) brain image classification and image segmentation approach. Automated classification is encouraged by the need of high accuracy when dealing with a human life. The detection of the brain tumour is a challenging problem, due to high diversity in tumour appearance and ambiguous tumour boundaries. MRI images are chosen for detection of brain tumours, as they are used in soft tissue determinations. First of all, image pre-processing is used to enhance the image quality. Second, dual-tree complex wavelet transform multi-scale decomposition is used to analyse texture of an image. Feature extraction extracts features from an image using gray-level co-occurrence matrix (GLCM). Then, the Neuro-Fuzzy technique is used to classify the stages of brain tumour as benign, malignant or normal based on texture features. Finally, tumour location is detected using Otsu thresholding. The classifier performance is evaluated based on classification accuracies. The simulated results show that the proposed classifier provides better accuracy than previous method.

Semi-supervised manifold learning with affinity regularization for Alzheimer's disease identification using positron emission tomography imaging.

PubMed

Lu, Shen; Xia, Yong; Cai, Tom Weidong; Feng, David Dagan

2015-01-01

Dementia, Alzheimer's disease (AD) in particular is a global problem and big threat to the aging population. An image based computer-aided dementia diagnosis method is needed to providing doctors help during medical image examination. Many machine learning based dementia classification methods using medical imaging have been proposed and most of them achieve accurate results. However, most of these methods make use of supervised learning requiring fully labeled image dataset, which usually is not practical in real clinical environment. Using large amount of unlabeled images can improve the dementia classification performance. In this study we propose a new semi-supervised dementia classification method based on random manifold learning with affinity regularization. Three groups of spatial features are extracted from positron emission tomography (PET) images to construct an unsupervised random forest which is then used to regularize the manifold learning objective function. The proposed method, stat-of-the-art Laplacian support vector machine (LapSVM) and supervised SVM are applied to classify AD and normal controls (NC). The experiment results show that learning with unlabeled images indeed improves the classification performance. And our method outperforms LapSVM on the same dataset.

The Radon cumulative distribution transform and its application to image classification

PubMed Central

Kolouri, Soheil; Park, Se Rim; Rohde, Gustavo K.

2016-01-01

Invertible image representation methods (transforms) are routinely employed as low-level image processing operations based on which feature extraction and recognition algorithms are developed. Most transforms in current use (e.g. Fourier, Wavelet, etc.) are linear transforms, and, by themselves, are unable to substantially simplify the representation of image classes for classification. Here we describe a nonlinear, invertible, low-level image processing transform based on combining the well known Radon transform for image data, and the 1D Cumulative Distribution Transform proposed earlier. We describe a few of the properties of this new transform, and with both theoretical and experimental results show that it can often render certain problems linearly separable in transform space. PMID:26685245

NOTE: Fluoroscopic gating without implanted fiducial markers for lung cancer radiotherapy based on support vector machines

NASA Astrophysics Data System (ADS)

Cui, Ying; Dy, Jennifer G.; Alexander, Brian; Jiang, Steve B.

2008-08-01

Various problems with the current state-of-the-art techniques for gated radiotherapy have prevented this new treatment modality from being widely implemented in clinical routine. These problems are caused mainly by applying various external respiratory surrogates. There might be large uncertainties in deriving the tumor position from external respiratory surrogates. While tracking implanted fiducial markers has sufficient accuracy, this procedure may not be widely accepted due to the risk of pneumothorax. Previously, we have developed a technique to generate gating signals from fluoroscopic images without implanted fiducial markers using template matching methods (Berbeco et al 2005 Phys. Med. Biol. 50 4481-90, Cui et al 2007b Phys. Med. Biol. 52 741-55). In this note, our main contribution is to provide a totally different new view of the gating problem by recasting it as a classification problem. Then, we solve this classification problem by a well-studied powerful classification method called a support vector machine (SVM). Note that the goal of an automated gating tool is to decide when to turn the beam ON or OFF. We treat ON and OFF as the two classes in our classification problem. We create our labeled training data during the patient setup session by utilizing the reference gating signal, manually determined by a radiation oncologist. We then pre-process these labeled training images and build our SVM prediction model. During treatment delivery, fluoroscopic images are continuously acquired, pre-processed and sent as an input to the SVM. Finally, our SVM model will output the predicted labels as gating signals. We test the proposed technique on five sequences of fluoroscopic images from five lung cancer patients against the reference gating signal as ground truth. We compare the performance of the SVM to our previous template matching method (Cui et al 2007b Phys. Med. Biol. 52 741-55). We find that the SVM is slightly more accurate on average (1-3%) than the template matching method, when delivering the target dose. And the average duty cycle is 4-6% longer. Given the very limited patient dataset, we cannot conclude that the SVM is more accurate and efficient than the template matching method. However, our preliminary results show that the SVM is a potentially precise and efficient algorithm for generating gating signals for radiotherapy. This work demonstrates that the gating problem can be considered as a classification problem and solved accordingly.

Data Mining Technologies Inspired from Visual Principle

NASA Astrophysics Data System (ADS)

Xu, Zongben

In this talk we review the recent work done by our group on data mining (DM) technologies deduced from simulating visual principle. Through viewing a DM problem as a cognition problems and treading a data set as an image with each light point located at a datum position, we developed a series of high efficient algorithms for clustering, classification and regression via mimicking visual principles. In pattern recognition, human eyes seem to possess a singular aptitude to group objects and find important structure in an efficient way. Thus, a DM algorithm simulating visual system may solve some basic problems in DM research. From this point of view, we proposed a new approach for data clustering by modeling the blurring effect of lateral retinal interconnections based on scale space theory. In this approach, as the data image blurs, smaller light blobs merge into large ones until the whole image becomes one light blob at a low enough level of resolution. By identifying each blob with a cluster, the blurring process then generates a family of clustering along the hierarchy. The proposed approach provides unique solutions to many long standing problems, such as the cluster validity and the sensitivity to initialization problems, in clustering. We extended such an approach to classification and regression problems, through combatively employing the Weber's law in physiology and the cell response classification facts. The resultant classification and regression algorithms are proven to be very efficient and solve the problems of model selection and applicability to huge size of data set in DM technologies. We finally applied the similar idea to the difficult parameter setting problem in support vector machine (SVM). Viewing the parameter setting problem as a recognition problem of choosing a visual scale at which the global and local structures of a data set can be preserved, and the difference between the two structures be maximized in the feature space, we derived a direct parameter setting formula for the Gaussian SVM. The simulations and applications show that the suggested formula significantly outperforms the known model selection methods in terms of efficiency and precision.

A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification

PubMed Central

Xie, Jin; Zhang, Lei; You, Jane; Zhang, David; Qu, Xiaofeng

2012-01-01

Human hand back skin texture (HBST) is often consistent for a person and distinctive from person to person. In this paper, we study the HBST pattern recognition problem with applications to personal identification and gender classification. A specially designed system is developed to capture HBST images, and an HBST image database was established, which consists of 1,920 images from 80 persons (160 hands). An efficient texton learning based method is then presented to classify the HBST patterns. First, textons are learned in the space of filter bank responses from a set of training images using the l1 -minimization based sparse representation (SR) technique. Then, under the SR framework, we represent the feature vector at each pixel over the learned dictionary to construct a representation coefficient histogram. Finally, the coefficient histogram is used as skin texture feature for classification. Experiments on personal identification and gender classification are performed by using the established HBST database. The results show that HBST can be used to assist human identification and gender classification. PMID:23012512

Computer vision for microscopy diagnosis of malaria.

PubMed

Tek, F Boray; Dempster, Andrew G; Kale, Izzet

2009-07-13

This paper reviews computer vision and image analysis studies aiming at automated diagnosis or screening of malaria infection in microscope images of thin blood film smears. Existing works interpret the diagnosis problem differently or propose partial solutions to the problem. A critique of these works is furnished. In addition, a general pattern recognition framework to perform diagnosis, which includes image acquisition, pre-processing, segmentation, and pattern classification components, is described. The open problems are addressed and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.

A novel underwater dam crack detection and classification approach based on sonar images

PubMed Central

Shi, Pengfei; Fan, Xinnan; Ni, Jianjun; Khan, Zubair; Li, Min

2017-01-01

Underwater dam crack detection and classification based on sonar images is a challenging task because underwater environments are complex and because cracks are quite random and diverse in nature. Furthermore, obtainable sonar images are of low resolution. To address these problems, a novel underwater dam crack detection and classification approach based on sonar imagery is proposed. First, the sonar images are divided into image blocks. Second, a clustering analysis of a 3-D feature space is used to obtain the crack fragments. Third, the crack fragments are connected using an improved tensor voting method. Fourth, a minimum spanning tree is used to obtain the crack curve. Finally, an improved evidence theory combined with fuzzy rule reasoning is proposed to classify the cracks. Experimental results show that the proposed approach is able to detect underwater dam cracks and classify them accurately and effectively under complex underwater environments. PMID:28640925

A novel underwater dam crack detection and classification approach based on sonar images.

PubMed

Shi, Pengfei; Fan, Xinnan; Ni, Jianjun; Khan, Zubair; Li, Min

2017-01-01

Underwater dam crack detection and classification based on sonar images is a challenging task because underwater environments are complex and because cracks are quite random and diverse in nature. Furthermore, obtainable sonar images are of low resolution. To address these problems, a novel underwater dam crack detection and classification approach based on sonar imagery is proposed. First, the sonar images are divided into image blocks. Second, a clustering analysis of a 3-D feature space is used to obtain the crack fragments. Third, the crack fragments are connected using an improved tensor voting method. Fourth, a minimum spanning tree is used to obtain the crack curve. Finally, an improved evidence theory combined with fuzzy rule reasoning is proposed to classify the cracks. Experimental results show that the proposed approach is able to detect underwater dam cracks and classify them accurately and effectively under complex underwater environments.

Hybrid Optimization of Object-Based Classification in High-Resolution Images Using Continous ANT Colony Algorithm with Emphasis on Building Detection

NASA Astrophysics Data System (ADS)

Tamimi, E.; Ebadi, H.; Kiani, A.

2017-09-01

Automatic building detection from High Spatial Resolution (HSR) images is one of the most important issues in Remote Sensing (RS). Due to the limited number of spectral bands in HSR images, using other features will lead to improve accuracy. By adding these features, the presence probability of dependent features will be increased, which leads to accuracy reduction. In addition, some parameters should be determined in Support Vector Machine (SVM) classification. Therefore, it is necessary to simultaneously determine classification parameters and select independent features according to image type. Optimization algorithm is an efficient method to solve this problem. On the other hand, pixel-based classification faces several challenges such as producing salt-paper results and high computational time in high dimensional data. Hence, in this paper, a novel method is proposed to optimize object-based SVM classification by applying continuous Ant Colony Optimization (ACO) algorithm. The advantages of the proposed method are relatively high automation level, independency of image scene and type, post processing reduction for building edge reconstruction and accuracy improvement. The proposed method was evaluated by pixel-based SVM and Random Forest (RF) classification in terms of accuracy. In comparison with optimized pixel-based SVM classification, the results showed that the proposed method improved quality factor and overall accuracy by 17% and 10%, respectively. Also, in the proposed method, Kappa coefficient was improved by 6% rather than RF classification. Time processing of the proposed method was relatively low because of unit of image analysis (image object). These showed the superiority of the proposed method in terms of time and accuracy.

Classification of underground pipe scanned images using feature extraction and neuro-fuzzy algorithm.

PubMed

Sinha, S K; Karray, F

2002-01-01

Pipeline surface defects such as holes and cracks cause major problems for utility managers, particularly when the pipeline is buried under the ground. Manual inspection for surface defects in the pipeline has a number of drawbacks, including subjectivity, varying standards, and high costs. Automatic inspection system using image processing and artificial intelligence techniques can overcome many of these disadvantages and offer utility managers an opportunity to significantly improve quality and reduce costs. A recognition and classification of pipe cracks using images analysis and neuro-fuzzy algorithm is proposed. In the preprocessing step the scanned images of pipe are analyzed and crack features are extracted. In the classification step the neuro-fuzzy algorithm is developed that employs a fuzzy membership function and error backpropagation algorithm. The idea behind the proposed approach is that the fuzzy membership function will absorb variation of feature values and the backpropagation network, with its learning ability, will show good classification efficiency.

Purification of Training Samples Based on Spectral Feature and Superpixel Segmentation

NASA Astrophysics Data System (ADS)

Guan, X.; Qi, W.; He, J.; Wen, Q.; Chen, T.; Wang, Z.

2018-04-01

Remote sensing image classification is an effective way to extract information from large volumes of high-spatial resolution remote sensing images. Generally, supervised image classification relies on abundant and high-precision training data, which is often manually interpreted by human experts to provide ground truth for training and evaluating the performance of the classifier. Remote sensing enterprises accumulated lots of manually interpreted products from early lower-spatial resolution remote sensing images by executing their routine research and business programs. However, these manually interpreted products may not match the very high resolution (VHR) image properly because of different dates or spatial resolution of both data, thus, hindering suitability of manually interpreted products in training classification models, or small coverage area of these manually interpreted products. We also face similar problems in our laboratory in 21st Century Aerospace Technology Co. Ltd (short for 21AT). In this work, we propose a method to purify the interpreted product to match newly available VHRI data and provide the best training data for supervised image classifiers in VHR image classification. And results indicate that our proposed method can efficiently purify the input data for future machine learning use.

A Survey on Sentiment Classification in Face Recognition

NASA Astrophysics Data System (ADS)

Qian, Jingyu

2018-01-01

Face recognition has been an important topic for both industry and academia for a long time. K-means clustering, autoencoder, and convolutional neural network, each representing a design idea for face recognition method, are three popular algorithms to deal with face recognition problems. It is worthwhile to summarize and compare these three different algorithms. This paper will focus on one specific face recognition problem-sentiment classification from images. Three different algorithms for sentiment classification problems will be summarized, including k-means clustering, autoencoder, and convolutional neural network. An experiment with the application of these algorithms on a specific dataset of human faces will be conducted to illustrate how these algorithms are applied and their accuracy. Finally, the three algorithms are compared based on the accuracy result.

A Neural Relevance Model for Feature Extraction from Hyperspectral Images, and Its Application in the Wavelet Domain

DTIC Science & Technology

2006-08-01

Nikolas Avouris. Evaluation of classifiers for an uneven class distribution problem. Applied Artificial Intellegence , pages 1-24, 2006. Draft manuscript...data by a hybrid artificial neural network so we may evaluate the classification capabilities of the baseline GRLVQ and our improved GRLVQI. Chapter 4...performance of GRLVQ(I), we compare the results against a baseline classification of the 23-class problem with a hybrid artificial neural network (ANN

A Two-Stream Deep Fusion Framework for High-Resolution Aerial Scene Classification

PubMed Central

Liu, Fuxian

2018-01-01

One of the challenging problems in understanding high-resolution remote sensing images is aerial scene classification. A well-designed feature representation method and classifier can improve classification accuracy. In this paper, we construct a new two-stream deep architecture for aerial scene classification. First, we use two pretrained convolutional neural networks (CNNs) as feature extractor to learn deep features from the original aerial image and the processed aerial image through saliency detection, respectively. Second, two feature fusion strategies are adopted to fuse the two different types of deep convolutional features extracted by the original RGB stream and the saliency stream. Finally, we use the extreme learning machine (ELM) classifier for final classification with the fused features. The effectiveness of the proposed architecture is tested on four challenging datasets: UC-Merced dataset with 21 scene categories, WHU-RS dataset with 19 scene categories, AID dataset with 30 scene categories, and NWPU-RESISC45 dataset with 45 challenging scene categories. The experimental results demonstrate that our architecture gets a significant classification accuracy improvement over all state-of-the-art references. PMID:29581722

A Two-Stream Deep Fusion Framework for High-Resolution Aerial Scene Classification.

PubMed

Yu, Yunlong; Liu, Fuxian

2018-01-01

One of the challenging problems in understanding high-resolution remote sensing images is aerial scene classification. A well-designed feature representation method and classifier can improve classification accuracy. In this paper, we construct a new two-stream deep architecture for aerial scene classification. First, we use two pretrained convolutional neural networks (CNNs) as feature extractor to learn deep features from the original aerial image and the processed aerial image through saliency detection, respectively. Second, two feature fusion strategies are adopted to fuse the two different types of deep convolutional features extracted by the original RGB stream and the saliency stream. Finally, we use the extreme learning machine (ELM) classifier for final classification with the fused features. The effectiveness of the proposed architecture is tested on four challenging datasets: UC-Merced dataset with 21 scene categories, WHU-RS dataset with 19 scene categories, AID dataset with 30 scene categories, and NWPU-RESISC45 dataset with 45 challenging scene categories. The experimental results demonstrate that our architecture gets a significant classification accuracy improvement over all state-of-the-art references.

Attribute-based classification for zero-shot visual object categorization.

PubMed

Lampert, Christoph H; Nickisch, Hannes; Harmeling, Stefan

2014-03-01

We study the problem of object recognition for categories for which we have no training examples, a task also called zero--data or zero-shot learning. This situation has hardly been studied in computer vision research, even though it occurs frequently; the world contains tens of thousands of different object classes, and image collections have been formed and suitably annotated for only a few of them. To tackle the problem, we introduce attribute-based classification: Objects are identified based on a high-level description that is phrased in terms of semantic attributes, such as the object's color or shape. Because the identification of each such property transcends the specific learning task at hand, the attribute classifiers can be prelearned independently, for example, from existing image data sets unrelated to the current task. Afterward, new classes can be detected based on their attribute representation, without the need for a new training phase. In this paper, we also introduce a new data set, Animals with Attributes, of over 30,000 images of 50 animal classes, annotated with 85 semantic attributes. Extensive experiments on this and two more data sets show that attribute-based classification indeed is able to categorize images without access to any training images of the target classes.

Multi-task linear programming discriminant analysis for the identification of progressive MCI individuals.

PubMed

Yu, Guan; Liu, Yufeng; Thung, Kim-Han; Shen, Dinggang

2014-01-01

Accurately identifying mild cognitive impairment (MCI) individuals who will progress to Alzheimer's disease (AD) is very important for making early interventions. Many classification methods focus on integrating multiple imaging modalities such as magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET). However, the main challenge for MCI classification using multiple imaging modalities is the existence of a lot of missing data in many subjects. For example, in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, almost half of the subjects do not have PET images. In this paper, we propose a new and flexible binary classification method, namely Multi-task Linear Programming Discriminant (MLPD) analysis, for the incomplete multi-source feature learning. Specifically, we decompose the classification problem into different classification tasks, i.e., one for each combination of available data sources. To solve all different classification tasks jointly, our proposed MLPD method links them together by constraining them to achieve the similar estimated mean difference between the two classes (under classification) for those shared features. Compared with the state-of-the-art incomplete Multi-Source Feature (iMSF) learning method, instead of constraining different classification tasks to choose a common feature subset for those shared features, MLPD can flexibly and adaptively choose different feature subsets for different classification tasks. Furthermore, our proposed MLPD method can be efficiently implemented by linear programming. To validate our MLPD method, we perform experiments on the ADNI baseline dataset with the incomplete MRI and PET images from 167 progressive MCI (pMCI) subjects and 226 stable MCI (sMCI) subjects. We further compared our method with the iMSF method (using incomplete MRI and PET images) and also the single-task classification method (using only MRI or only subjects with both MRI and PET images). Experimental results show very promising performance of our proposed MLPD method.

Multi-Task Linear Programming Discriminant Analysis for the Identification of Progressive MCI Individuals

PubMed Central

Yu, Guan; Liu, Yufeng; Thung, Kim-Han; Shen, Dinggang

2014-01-01

Accurately identifying mild cognitive impairment (MCI) individuals who will progress to Alzheimer's disease (AD) is very important for making early interventions. Many classification methods focus on integrating multiple imaging modalities such as magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET). However, the main challenge for MCI classification using multiple imaging modalities is the existence of a lot of missing data in many subjects. For example, in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, almost half of the subjects do not have PET images. In this paper, we propose a new and flexible binary classification method, namely Multi-task Linear Programming Discriminant (MLPD) analysis, for the incomplete multi-source feature learning. Specifically, we decompose the classification problem into different classification tasks, i.e., one for each combination of available data sources. To solve all different classification tasks jointly, our proposed MLPD method links them together by constraining them to achieve the similar estimated mean difference between the two classes (under classification) for those shared features. Compared with the state-of-the-art incomplete Multi-Source Feature (iMSF) learning method, instead of constraining different classification tasks to choose a common feature subset for those shared features, MLPD can flexibly and adaptively choose different feature subsets for different classification tasks. Furthermore, our proposed MLPD method can be efficiently implemented by linear programming. To validate our MLPD method, we perform experiments on the ADNI baseline dataset with the incomplete MRI and PET images from 167 progressive MCI (pMCI) subjects and 226 stable MCI (sMCI) subjects. We further compared our method with the iMSF method (using incomplete MRI and PET images) and also the single-task classification method (using only MRI or only subjects with both MRI and PET images). Experimental results show very promising performance of our proposed MLPD method. PMID:24820966

Music algorithm for imaging of a sound-hard arc in limited-view inverse scattering problem

NASA Astrophysics Data System (ADS)

Park, Won-Kwang

2017-07-01

MUltiple SIgnal Classification (MUSIC) algorithm for a non-iterative imaging of sound-hard arc in limited-view inverse scattering problem is considered. In order to discover mathematical structure of MUSIC, we derive a relationship between MUSIC and an infinite series of Bessel functions of integer order. This structure enables us to examine some properties of MUSIC in limited-view problem. Numerical simulations are performed to support the identified structure of MUSIC.

Deep feature extraction and combination for synthetic aperture radar target classification

NASA Astrophysics Data System (ADS)

Amrani, Moussa; Jiang, Feng

2017-10-01

Feature extraction has always been a difficult problem in the classification performance of synthetic aperture radar automatic target recognition (SAR-ATR). It is very important to select discriminative features to train a classifier, which is a prerequisite. Inspired by the great success of convolutional neural network (CNN), we address the problem of SAR target classification by proposing a feature extraction method, which takes advantage of exploiting the extracted deep features from CNNs on SAR images to introduce more powerful discriminative features and robust representation ability for them. First, the pretrained VGG-S net is fine-tuned on moving and stationary target acquisition and recognition (MSTAR) public release database. Second, after a simple preprocessing is performed, the fine-tuned network is used as a fixed feature extractor to extract deep features from the processed SAR images. Third, the extracted deep features are fused by using a traditional concatenation and a discriminant correlation analysis algorithm. Finally, for target classification, K-nearest neighbors algorithm based on LogDet divergence-based metric learning triplet constraints is adopted as a baseline classifier. Experiments on MSTAR are conducted, and the classification accuracy results demonstrate that the proposed method outperforms the state-of-the-art methods.

ISBDD Model for Classification of Hyperspectral Remote Sensing Imagery

PubMed Central

Li, Na; Xu, Zhaopeng; Zhao, Huijie; Huang, Xinchen; Drummond, Jane; Wang, Daming

2018-01-01

The diverse density (DD) algorithm was proposed to handle the problem of low classification accuracy when training samples contain interference such as mixed pixels. The DD algorithm can learn a feature vector from training bags, which comprise instances (pixels). However, the feature vector learned by the DD algorithm cannot always effectively represent one type of ground cover. To handle this problem, an instance space-based diverse density (ISBDD) model that employs a novel training strategy is proposed in this paper. In the ISBDD model, DD values of each pixel are computed instead of learning a feature vector, and as a result, the pixel can be classified according to its DD values. Airborne hyperspectral data collected by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor and the Push-broom Hyperspectral Imager (PHI) are applied to evaluate the performance of the proposed model. Results show that the overall classification accuracy of ISBDD model on the AVIRIS and PHI images is up to 97.65% and 89.02%, respectively, while the kappa coefficient is up to 0.97 and 0.88, respectively. PMID:29510547

Steganalysis using logistic regression

NASA Astrophysics Data System (ADS)

Lubenko, Ivans; Ker, Andrew D.

2011-02-01

We advocate Logistic Regression (LR) as an alternative to the Support Vector Machine (SVM) classifiers commonly used in steganalysis. LR offers more information than traditional SVM methods - it estimates class probabilities as well as providing a simple classification - and can be adapted more easily and efficiently for multiclass problems. Like SVM, LR can be kernelised for nonlinear classification, and it shows comparable classification accuracy to SVM methods. This work is a case study, comparing accuracy and speed of SVM and LR classifiers in detection of LSB Matching and other related spatial-domain image steganography, through the state-of-art 686-dimensional SPAM feature set, in three image sets.

Large deformation image classification using generalized locality-constrained linear coding.

PubMed

Zhang, Pei; Wee, Chong-Yaw; Niethammer, Marc; Shen, Dinggang; Yap, Pew-Thian

2013-01-01

Magnetic resonance (MR) imaging has been demonstrated to be very useful for clinical diagnosis of Alzheimer's disease (AD). A common approach to using MR images for AD detection is to spatially normalize the images by non-rigid image registration, and then perform statistical analysis on the resulting deformation fields. Due to the high nonlinearity of the deformation field, recent studies suggest to use initial momentum instead as it lies in a linear space and fully encodes the deformation field. In this paper we explore the use of initial momentum for image classification by focusing on the problem of AD detection. Experiments on the public ADNI dataset show that the initial momentum, together with a simple sparse coding technique-locality-constrained linear coding (LLC)--can achieve a classification accuracy that is comparable to or even better than the state of the art. We also show that the performance of LLC can be greatly improved by introducing proper weights to the codebook.

Histopathological Image Classification using Discriminative Feature-oriented Dictionary Learning

PubMed Central

Vu, Tiep Huu; Mousavi, Hojjat Seyed; Monga, Vishal; Rao, Ganesh; Rao, UK Arvind

2016-01-01

In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available. PMID:26513781

Confidence level estimation in multi-target classification problems

NASA Astrophysics Data System (ADS)

Chang, Shi; Isaacs, Jason; Fu, Bo; Shin, Jaejeong; Zhu, Pingping; Ferrari, Silvia

2018-04-01

This paper presents an approach for estimating the confidence level in automatic multi-target classification performed by an imaging sensor on an unmanned vehicle. An automatic target recognition algorithm comprised of a deep convolutional neural network in series with a support vector machine classifier detects and classifies targets based on the image matrix. The joint posterior probability mass function of target class, features, and classification estimates is learned from labeled data, and recursively updated as additional images become available. Based on the learned joint probability mass function, the approach presented in this paper predicts the expected confidence level of future target classifications, prior to obtaining new images. The proposed approach is tested with a set of simulated sonar image data. The numerical results show that the estimated confidence level provides a close approximation to the actual confidence level value determined a posteriori, i.e. after the new image is obtained by the on-board sensor. Therefore, the expected confidence level function presented in this paper can be used to adaptively plan the path of the unmanned vehicle so as to optimize the expected confidence levels and ensure that all targets are classified with satisfactory confidence after the path is executed.

Elimination of RF inhomogeneity effects in segmentation.

PubMed

Agus, Onur; Ozkan, Mehmed; Aydin, Kubilay

2007-01-01

There are various methods proposed for the segmentation and analysis of MR images. However the efficiency of these techniques is effected by various artifacts that occur in the imaging system. One of the most encountered problems is the intensity variation across an image. To overcome this problem different methods are used. In this paper we propose a method for the elimination of intensity artifacts in segmentation of MRI images. Inter imager variations are also minimized to produce the same tissue segmentation for the same patient. A well-known multivariate classification algorithm, maximum likelihood is employed to illustrate the enhancement in segmentation.

Characterisation of Feature Points in Eye Fundus Images

NASA Astrophysics Data System (ADS)

Calvo, D.; Ortega, M.; Penedo, M. G.; Rouco, J.

The retinal vessel tree adds decisive knowledge in the diagnosis of numerous opthalmologic pathologies such as hypertension or diabetes. One of the problems in the analysis of the retinal vessel tree is the lack of information in terms of vessels depth as the image acquisition usually leads to a 2D image. This situation provokes a scenario where two different vessels coinciding in a point could be interpreted as a vessel forking into a bifurcation. That is why, for traking and labelling the retinal vascular tree, bifurcations and crossovers of vessels are considered feature points. In this work a novel method for these retinal vessel tree feature points detection and classification is introduced. The method applies image techniques such as filters or thinning to obtain the adequate structure to detect the points and sets a classification of these points studying its environment. The methodology is tested using a standard database and the results show high classification capabilities.

Automated classification of multiphoton microscopy images of ovarian tissue using deep learning.

PubMed

Huttunen, Mikko J; Hassan, Abdurahman; McCloskey, Curtis W; Fasih, Sijyl; Upham, Jeremy; Vanderhyden, Barbara C; Boyd, Robert W; Murugkar, Sangeeta

2018-06-01

Histopathological image analysis of stained tissue slides is routinely used in tumor detection and classification. However, diagnosis requires a highly trained pathologist and can thus be time-consuming, labor-intensive, and potentially risk bias. Here, we demonstrate a potential complementary approach for diagnosis. We show that multiphoton microscopy images from unstained, reproductive tissues can be robustly classified using deep learning techniques. We fine-train four pretrained convolutional neural networks using over 200 murine tissue images based on combined second-harmonic generation and two-photon excitation fluorescence contrast, to classify the tissues either as healthy or associated with high-grade serous carcinoma with over 95% sensitivity and 97% specificity. Our approach shows promise for applications involving automated disease diagnosis. It could also be readily applied to other tissues, diseases, and related classification problems. (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).

Information theoretic approach for assessing image fidelity in photon-counting arrays.

PubMed

Narravula, Srikanth R; Hayat, Majeed M; Javidi, Bahram

2010-02-01

The method of photon-counting integral imaging has been introduced recently for three-dimensional object sensing, visualization, recognition and classification of scenes under photon-starved conditions. This paper presents an information-theoretic model for the photon-counting imaging (PCI) method, thereby providing a rigorous foundation for the merits of PCI in terms of image fidelity. This, in turn, can facilitate our understanding of the demonstrated success of photon-counting integral imaging in compressive imaging and classification. The mutual information between the source and photon-counted images is derived in a Markov random field setting and normalized by the source-image's entropy, yielding a fidelity metric that is between zero and unity, which respectively corresponds to complete loss of information and full preservation of information. Calculations suggest that the PCI fidelity metric increases with spatial correlation in source image, from which we infer that the PCI method is particularly effective for source images with high spatial correlation; the metric also increases with the reduction in photon-number uncertainty. As an application to the theory, an image-classification problem is considered showing a congruous relationship between the fidelity metric and classifier's performance.

Minimization of annotation work: diagnosis of mammographic masses via active learning

NASA Astrophysics Data System (ADS)

Zhao, Yu; Zhang, Jingyang; Xie, Hongzhi; Zhang, Shuyang; Gu, Lixu

2018-06-01

The prerequisite for establishing an effective prediction system for mammographic diagnosis is the annotation of each mammographic image. The manual annotation work is time-consuming and laborious, which becomes a great hindrance for researchers. In this article, we propose a novel active learning algorithm that can adequately address this problem, leading to the minimization of the labeling costs on the premise of guaranteed performance. Our proposed method is different from the existing active learning methods designed for the general problem as it is specifically designed for mammographic images. Through its modified discriminant functions and improved sample query criteria, the proposed method can fully utilize the pairing of mammographic images and select the most valuable images from both the mediolateral and craniocaudal views. Moreover, in order to extend active learning to the ordinal regression problem, which has no precedent in existing studies, but is essential for mammographic diagnosis (mammographic diagnosis is not only a classification task, but also an ordinal regression task for predicting an ordinal variable, viz. the malignancy risk of lesions), multiple sample query criteria need to be taken into consideration simultaneously. We formulate it as a criteria integration problem and further present an algorithm based on self-adaptive weighted rank aggregation to achieve a good solution. The efficacy of the proposed method was demonstrated on thousands of mammographic images from the digital database for screening mammography. The labeling costs of obtaining optimal performance in the classification and ordinal regression task respectively fell to 33.8 and 19.8 percent of their original costs. The proposed method also generated 1228 wins, 369 ties and 47 losses for the classification task, and 1933 wins, 258 ties and 185 losses for the ordinal regression task compared to the other state-of-the-art active learning algorithms. By taking the particularities of mammographic images, the proposed AL method can indeed reduce the manual annotation work to a great extent without sacrificing the performance of the prediction system for mammographic diagnosis.

Minimization of annotation work: diagnosis of mammographic masses via active learning.

PubMed

Zhao, Yu; Zhang, Jingyang; Xie, Hongzhi; Zhang, Shuyang; Gu, Lixu

2018-05-22

The prerequisite for establishing an effective prediction system for mammographic diagnosis is the annotation of each mammographic image. The manual annotation work is time-consuming and laborious, which becomes a great hindrance for researchers. In this article, we propose a novel active learning algorithm that can adequately address this problem, leading to the minimization of the labeling costs on the premise of guaranteed performance. Our proposed method is different from the existing active learning methods designed for the general problem as it is specifically designed for mammographic images. Through its modified discriminant functions and improved sample query criteria, the proposed method can fully utilize the pairing of mammographic images and select the most valuable images from both the mediolateral and craniocaudal views. Moreover, in order to extend active learning to the ordinal regression problem, which has no precedent in existing studies, but is essential for mammographic diagnosis (mammographic diagnosis is not only a classification task, but also an ordinal regression task for predicting an ordinal variable, viz. the malignancy risk of lesions), multiple sample query criteria need to be taken into consideration simultaneously. We formulate it as a criteria integration problem and further present an algorithm based on self-adaptive weighted rank aggregation to achieve a good solution. The efficacy of the proposed method was demonstrated on thousands of mammographic images from the digital database for screening mammography. The labeling costs of obtaining optimal performance in the classification and ordinal regression task respectively fell to 33.8 and 19.8 percent of their original costs. The proposed method also generated 1228 wins, 369 ties and 47 losses for the classification task, and 1933 wins, 258 ties and 185 losses for the ordinal regression task compared to the other state-of-the-art active learning algorithms. By taking the particularities of mammographic images, the proposed AL method can indeed reduce the manual annotation work to a great extent without sacrificing the performance of the prediction system for mammographic diagnosis.

Feature detection in satellite images using neural network technology

NASA Technical Reports Server (NTRS)

Augusteijn, Marijke F.; Dimalanta, Arturo S.

1992-01-01

A feasibility study of automated classification of satellite images is described. Satellite images were characterized by the textures they contain. In particular, the detection of cloud textures was investigated. The method of second-order gray level statistics, using co-occurrence matrices, was applied to extract feature vectors from image segments. Neural network technology was employed to classify these feature vectors. The cascade-correlation architecture was successfully used as a classifier. The use of a Kohonen network was also investigated but this architecture could not reliably classify the feature vectors due to the complicated structure of the classification problem. The best results were obtained when data from different spectral bands were fused.

Semi-Supervised Marginal Fisher Analysis for Hyperspectral Image Classification

NASA Astrophysics Data System (ADS)

Huang, H.; Liu, J.; Pan, Y.

2012-07-01

The problem of learning with both labeled and unlabeled examples arises frequently in Hyperspectral image (HSI) classification. While marginal Fisher analysis is a supervised method, which cannot be directly applied for Semi-supervised classification. In this paper, we proposed a novel method, called semi-supervised marginal Fisher analysis (SSMFA), to process HSI of natural scenes, which uses a combination of semi-supervised learning and manifold learning. In SSMFA, a new difference-based optimization objective function with unlabeled samples has been designed. SSMFA preserves the manifold structure of labeled and unlabeled samples in addition to separating labeled samples in different classes from each other. The semi-supervised method has an analytic form of the globally optimal solution, and it can be computed based on eigen decomposition. Classification experiments with a challenging HSI task demonstrate that this method outperforms current state-of-the-art HSI-classification methods.

Analysis of x-ray hand images for bone age assessment

NASA Astrophysics Data System (ADS)

Serrat, Joan; Vitria, Jordi M.; Villanueva, Juan J.

1990-09-01

In this paper we describe a model-based system for the assessment of skeletal maturity on hand radiographs by the TW2 method. The problem consists in classiflying a set of bones appearing in an image in one of several stages described in an atlas. A first approach consisting in pre-processing segmentation and classification independent phases is also presented. However it is only well suited for well contrasted low noise images without superimposed bones were the edge detection by zero crossing of second directional derivatives is able to extract all bone contours maybe with little gaps and few false edges on the background. Hence the use of all available knowledge about the problem domain is needed to build a rather general system. We have designed a rule-based system for narrow down the rank of possible stages for each bone and guide the analysis process. It calls procedures written in conventional languages for matching stage models against the image and getting features needed in the classification process.

A Study for Texture Feature Extraction of High-Resolution Satellite Images Based on a Direction Measure and Gray Level Co-Occurrence Matrix Fusion Algorithm

PubMed Central

Zhang, Xin; Cui, Jintian; Wang, Weisheng; Lin, Chao

2017-01-01

To address the problem of image texture feature extraction, a direction measure statistic that is based on the directionality of image texture is constructed, and a new method of texture feature extraction, which is based on the direction measure and a gray level co-occurrence matrix (GLCM) fusion algorithm, is proposed in this paper. This method applies the GLCM to extract the texture feature value of an image and integrates the weight factor that is introduced by the direction measure to obtain the final texture feature of an image. A set of classification experiments for the high-resolution remote sensing images were performed by using support vector machine (SVM) classifier with the direction measure and gray level co-occurrence matrix fusion algorithm. Both qualitative and quantitative approaches were applied to assess the classification results. The experimental results demonstrated that texture feature extraction based on the fusion algorithm achieved a better image recognition, and the accuracy of classification based on this method has been significantly improved. PMID:28640181

Classification of Urban Feature from Unmanned Aerial Vehicle Images Using Gasvm Integration and Multi-Scale Segmentation

NASA Astrophysics Data System (ADS)

Modiri, M.; Salehabadi, A.; Mohebbi, M.; Hashemi, A. M.; Masumi, M.

2015-12-01

The use of UAV in the application of photogrammetry to obtain cover images and achieve the main objectives of the photogrammetric mapping has been a boom in the region. The images taken from REGGIOLO region in the province of, Italy Reggio -Emilia by UAV with non-metric camera Canon Ixus and with an average height of 139.42 meters were used to classify urban feature. Using the software provided SURE and cover images of the study area, to produce dense point cloud, DSM and Artvqvtv spatial resolution of 10 cm was prepared. DTM area using Adaptive TIN filtering algorithm was developed. NDSM area was prepared with using the difference between DSM and DTM and a separate features in the image stack. In order to extract features, using simultaneous occurrence matrix features mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation for each of the RGB band image was used Orthophoto area. Classes used to classify urban problems, including buildings, trees and tall vegetation, grass and vegetation short, paved road and is impervious surfaces. Class consists of impervious surfaces such as pavement conditions, the cement, the car, the roof is stored. In order to pixel-based classification and selection of optimal features of classification was GASVM pixel basis. In order to achieve the classification results with higher accuracy and spectral composition informations, texture, and shape conceptual image featureOrthophoto area was fencing. The segmentation of multi-scale segmentation method was used.it belonged class. Search results using the proposed classification of urban feature, suggests the suitability of this method of classification complications UAV is a city using images. The overall accuracy and kappa coefficient method proposed in this study, respectively, 47/93% and 84/91% was.

Galaxy Classifications with Deep Learning

NASA Astrophysics Data System (ADS)

Lukic, Vesna; Brüggen, Marcus

2017-06-01

Machine learning techniques have proven to be increasingly useful in astronomical applications over the last few years, for example in object classification, estimating redshifts and data mining. One example of object classification is classifying galaxy morphology. This is a tedious task to do manually, especially as the datasets become larger with surveys that have a broader and deeper search-space. The Kaggle Galaxy Zoo competition presented the challenge of writing an algorithm to find the probability that a galaxy belongs in a particular class, based on SDSS optical spectroscopy data. The use of convolutional neural networks (convnets), proved to be a popular solution to the problem, as they have also produced unprecedented classification accuracies in other image databases such as the database of handwritten digits (MNIST †) and large database of images (CIFAR ‡). We experiment with the convnets that comprised the winning solution, but using broad classifications. The effect of changing the number of layers is explored, as well as using a different activation function, to help in developing an intuition of how the networks function and to see how they can be applied to radio galaxy images.

Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification

NASA Astrophysics Data System (ADS)

Anwer, Rao Muhammad; Khan, Fahad Shahbaz; van de Weijer, Joost; Molinier, Matthieu; Laaksonen, Jorma

2018-04-01

Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene classification.

Random-Forest Classification of High-Resolution Remote Sensing Images and Ndsm Over Urban Areas

NASA Astrophysics Data System (ADS)

Sun, X. F.; Lin, X. G.

2017-09-01

As an intermediate step between raw remote sensing data and digital urban maps, remote sensing data classification has been a challenging and long-standing research problem in the community of remote sensing. In this work, an effective classification method is proposed for classifying high-resolution remote sensing data over urban areas. Starting from high resolution multi-spectral images and 3D geometry data, our method proceeds in three main stages: feature extraction, classification, and classified result refinement. First, we extract color, vegetation index and texture features from the multi-spectral image and compute the height, elevation texture and differential morphological profile (DMP) features from the 3D geometry data. Then in the classification stage, multiple random forest (RF) classifiers are trained separately, then combined to form a RF ensemble to estimate each sample's category probabilities. Finally the probabilities along with the feature importance indicator outputted by RF ensemble are used to construct a fully connected conditional random field (FCCRF) graph model, by which the classification results are refined through mean-field based statistical inference. Experiments on the ISPRS Semantic Labeling Contest dataset show that our proposed 3-stage method achieves 86.9% overall accuracy on the test data.

Classification of weld defect based on information fusion technology for radiographic testing system

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jiang, Hongquan; Liang, Zeming, E-mail: heavenlzm@126.com; Gao, Jianmin

Improving the efficiency and accuracy of weld defect classification is an important technical problem in developing the radiographic testing system. This paper proposes a novel weld defect classification method based on information fusion technology, Dempster–Shafer evidence theory. First, to characterize weld defects and improve the accuracy of their classification, 11 weld defect features were defined based on the sub-pixel level edges of radiographic images, four of which are presented for the first time in this paper. Second, we applied information fusion technology to combine different features for weld defect classification, including a mass function defined based on the weld defectmore » feature information and the quartile-method-based calculation of standard weld defect class which is to solve a sample problem involving a limited number of training samples. A steam turbine weld defect classification case study is also presented herein to illustrate our technique. The results show that the proposed method can increase the correct classification rate with limited training samples and address the uncertainties associated with weld defect classification.« less

Classification of weld defect based on information fusion technology for radiographic testing system.

PubMed

Jiang, Hongquan; Liang, Zeming; Gao, Jianmin; Dang, Changying

2016-03-01

Improving the efficiency and accuracy of weld defect classification is an important technical problem in developing the radiographic testing system. This paper proposes a novel weld defect classification method based on information fusion technology, Dempster-Shafer evidence theory. First, to characterize weld defects and improve the accuracy of their classification, 11 weld defect features were defined based on the sub-pixel level edges of radiographic images, four of which are presented for the first time in this paper. Second, we applied information fusion technology to combine different features for weld defect classification, including a mass function defined based on the weld defect feature information and the quartile-method-based calculation of standard weld defect class which is to solve a sample problem involving a limited number of training samples. A steam turbine weld defect classification case study is also presented herein to illustrate our technique. The results show that the proposed method can increase the correct classification rate with limited training samples and address the uncertainties associated with weld defect classification.

General tensor discriminant analysis and gabor features for gait recognition.

PubMed

Tao, Dacheng; Li, Xuelong; Wu, Xindong; Maybank, Stephen J

2007-10-01

The traditional image representations are not suited to conventional classification methods, such as the linear discriminant analysis (LDA), because of the under sample problem (USP): the dimensionality of the feature space is much higher than the number of training samples. Motivated by the successes of the two dimensional LDA (2DLDA) for face recognition, we develop a general tensor discriminant analysis (GTDA) as a preprocessing step for LDA. The benefits of GTDA compared with existing preprocessing methods, e.g., principal component analysis (PCA) and 2DLDA, include 1) the USP is reduced in subsequent classification by, for example, LDA; 2) the discriminative information in the training tensors is preserved; and 3) GTDA provides stable recognition rates because the alternating projection optimization algorithm to obtain a solution of GTDA converges, while that of 2DLDA does not. We use human gait recognition to validate the proposed GTDA. The averaged gait images are utilized for gait representation. Given the popularity of Gabor function based image decompositions for image understanding and object recognition, we develop three different Gabor function based image representations: 1) the GaborD representation is the sum of Gabor filter responses over directions, 2) GaborS is the sum of Gabor filter responses over scales, and 3) GaborSD is the sum of Gabor filter responses over scales and directions. The GaborD, GaborS and GaborSD representations are applied to the problem of recognizing people from their averaged gait images.A large number of experiments were carried out to evaluate the effectiveness (recognition rate) of gait recognition based on first obtaining a Gabor, GaborD, GaborS or GaborSD image representation, then using GDTA to extract features and finally using LDA for classification. The proposed methods achieved good performance for gait recognition based on image sequences from the USF HumanID Database. Experimental comparisons are made with nine state of the art classification methods in gait recognition.

Supervised target detection in hyperspectral images using one-class Fukunaga-Koontz Transform

NASA Astrophysics Data System (ADS)

Binol, Hamidullah; Bal, Abdullah

2016-05-01

A novel hyperspectral target detection technique based on Fukunaga-Koontz transform (FKT) is presented. FKT offers significant properties for feature selection and ordering. However, it can only be used to solve multi-pattern classification problems. Target detection may be considered as a two-class classification problem, i.e., target versus background clutter. Nevertheless, background clutter typically contains different types of materials. That's why; target detection techniques are different than classification methods by way of modeling clutter. To avoid the modeling of the background clutter, we have improved one-class FKT (OC-FKT) for target detection. The statistical properties of target training samples are used to define tunnel-like boundary of the target class. Non-target samples are then created synthetically as to be outside of the boundary. Thus, only limited target samples become adequate for training of FKT. The hyperspectral image experiments confirm that the proposed OC-FKT technique provides an effective means for target detection.

Spectral-Spatial Shared Linear Regression for Hyperspectral Image Classification.

PubMed

Haoliang Yuan; Yuan Yan Tang

2017-04-01

Classification of the pixels in hyperspectral image (HSI) is an important task and has been popularly applied in many practical applications. Its major challenge is the high-dimensional small-sized problem. To deal with this problem, lots of subspace learning (SL) methods are developed to reduce the dimension of the pixels while preserving the important discriminant information. Motivated by ridge linear regression (RLR) framework for SL, we propose a spectral-spatial shared linear regression method (SSSLR) for extracting the feature representation. Comparing with RLR, our proposed SSSLR has the following two advantages. First, we utilize a convex set to explore the spatial structure for computing the linear projection matrix. Second, we utilize a shared structure learning model, which is formed by original data space and a hidden feature space, to learn a more discriminant linear projection matrix for classification. To optimize our proposed method, an efficient iterative algorithm is proposed. Experimental results on two popular HSI data sets, i.e., Indian Pines and Salinas demonstrate that our proposed methods outperform many SL methods.

An anomaly detection approach for the identification of DME patients using spectral domain optical coherence tomography images.

PubMed

Sidibé, Désiré; Sankar, Shrinivasan; Lemaître, Guillaume; Rastgoo, Mojdeh; Massich, Joan; Cheung, Carol Y; Tan, Gavin S W; Milea, Dan; Lamoureux, Ecosse; Wong, Tien Y; Mériaudeau, Fabrice

2017-02-01

This paper proposes a method for automatic classification of spectral domain OCT data for the identification of patients with retinal diseases such as Diabetic Macular Edema (DME). We address this issue as an anomaly detection problem and propose a method that not only allows the classification of the OCT volume, but also allows the identification of the individual diseased B-scans inside the volume. Our approach is based on modeling the appearance of normal OCT images with a Gaussian Mixture Model (GMM) and detecting abnormal OCT images as outliers. The classification of an OCT volume is based on the number of detected outliers. Experimental results with two different datasets show that the proposed method achieves a sensitivity and a specificity of 80% and 93% on the first dataset, and 100% and 80% on the second one. Moreover, the experiments show that the proposed method achieves better classification performance than other recently published works. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning.

PubMed

Shin, Hoo-Chang; Roth, Holger R; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel; Summers, Ronald M

2016-05-01

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.

Classification of burn wounds using support vector machines

NASA Astrophysics Data System (ADS)

Acha, Begona; Serrano, Carmen; Palencia, Sergio; Murillo, Juan Jose

2004-05-01

The purpose of this work is to improve a previous method developed by the authors for the classification of burn wounds into their depths. The inputs of the system are color and texture information, as these are the characteristics observed by physicians in order to give a diagnosis. Our previous work consisted in segmenting the burn wound from the rest of the image and classifying the burn into its depth. In this paper we focus on the classification problem only. We already proposed to use a Fuzzy-ARTMAP neural network (NN). However, we may take advantage of new powerful classification tools such as Support Vector Machines (SVM). We apply the five-folded cross validation scheme to divide the database into training and validating sets. Then, we apply a feature selection method for each classifier, which will give us the set of features that yields the smallest classification error for each classifier. Features used to classify are first-order statistical parameters extracted from the L*, u* and v* color components of the image. The feature selection algorithms used are the Sequential Forward Selection (SFS) and the Sequential Backward Selection (SBS) methods. As data of the problem faced here are not linearly separable, the SVM was trained using some different kernels. The validating process shows that the SVM method, when using a Gaussian kernel of variance 1, outperforms classification results obtained with the rest of the classifiers, yielding an error classification rate of 0.7% whereas the Fuzzy-ARTMAP NN attained 1.6 %.

Machine Learning Approach to Automated Quality Identification of Human Induced Pluripotent Stem Cell Colony Images.

PubMed

Joutsijoki, Henry; Haponen, Markus; Rasku, Jyrki; Aalto-Setälä, Katriina; Juhola, Martti

2016-01-01

The focus of this research is on automated identification of the quality of human induced pluripotent stem cell (iPSC) colony images. iPS cell technology is a contemporary method by which the patient's cells are reprogrammed back to stem cells and are differentiated to any cell type wanted. iPS cell technology will be used in future to patient specific drug screening, disease modeling, and tissue repairing, for instance. However, there are technical challenges before iPS cell technology can be used in practice and one of them is quality control of growing iPSC colonies which is currently done manually but is unfeasible solution in large-scale cultures. The monitoring problem returns to image analysis and classification problem. In this paper, we tackle this problem using machine learning methods such as multiclass Support Vector Machines and several baseline methods together with Scaled Invariant Feature Transformation based features. We perform over 80 test arrangements and do a thorough parameter value search. The best accuracy (62.4%) for classification was obtained by using a k-NN classifier showing improved accuracy compared to earlier studies.

Building Change Detection from Bi-Temporal Dense-Matching Point Clouds and Aerial Images.

PubMed

Pang, Shiyan; Hu, Xiangyun; Cai, Zhongliang; Gong, Jinqi; Zhang, Mi

2018-03-24

In this work, a novel building change detection method from bi-temporal dense-matching point clouds and aerial images is proposed to address two major problems, namely, the robust acquisition of the changed objects above ground and the automatic classification of changed objects into buildings or non-buildings. For the acquisition of changed objects above ground, the change detection problem is converted into a binary classification, in which the changed area above ground is regarded as the foreground and the other area as the background. For the gridded points of each period, the graph cuts algorithm is adopted to classify the points into foreground and background, followed by the region-growing algorithm to form candidate changed building objects. A novel structural feature that was extracted from aerial images is constructed to classify the candidate changed building objects into buildings and non-buildings. The changed building objects are further classified as "newly built", "taller", "demolished", and "lower" by combining the classification and the digital surface models of two periods. Finally, three typical areas from a large dataset are used to validate the proposed method. Numerous experiments demonstrate the effectiveness of the proposed algorithm.

An efficient abnormal cervical cell detection system based on multi-instance extreme learning machine

NASA Astrophysics Data System (ADS)

Zhao, Lili; Yin, Jianping; Yuan, Lihuan; Liu, Qiang; Li, Kuan; Qiu, Minghui

2017-07-01

Automatic detection of abnormal cells from cervical smear images is extremely demanded in annual diagnosis of women's cervical cancer. For this medical cell recognition problem, there are three different feature sections, namely cytology morphology, nuclear chromatin pathology and region intensity. The challenges of this problem come from feature combination s and classification accurately and efficiently. Thus, we propose an efficient abnormal cervical cell detection system based on multi-instance extreme learning machine (MI-ELM) to deal with above two questions in one unified framework. MI-ELM is one of the most promising supervised learning classifiers which can deal with several feature sections and realistic classification problems analytically. Experiment results over Herlev dataset demonstrate that the proposed method outperforms three traditional methods for two-class classification in terms of well accuracy and less time.

Ice/water Classification of Sentinel-1 Images

NASA Astrophysics Data System (ADS)

Korosov, Anton; Zakhvatkina, Natalia; Muckenhuber, Stefan

2015-04-01

Sea Ice monitoring and classification relies heavily on synthetic aperture radar (SAR) imagery. These sensors record data either only at horizontal polarization (RADARSAT-1) or vertically polarized (ERS-1 and ERS-2) or at dual polarization (Radarsat-2, Sentinel-1). Many algorithms have been developed to discriminate sea ice types and open water using single polarization images. Ice type classification, however, is still ambiguous in some cases. Sea ice classification in single polarization SAR images has been attempted using various methods since the beginning of the ERS programme. The robust classification using only SAR images that can provide useful results under varying sea ice types and open water tend to be not generally applicable in operational regime. The new generation SAR satellites have capability to deliver images in several polarizations. This gives improved possibility to develop sea ice classification algorithms. In this study we use data from Sentinel-1 at dual-polarization, i.e. HH (horizontally transmitted and horizontally received) and HV (horizontally transmitted, vertically received). This mode assembles wide SAR image from several narrower SAR beams, resulting to an image of 500 x 500 km with 50 m resolution. A non-linear scheme for classification of Sentinel-1 data has been developed. The processing allows to identify three classes: ice, calm water and rough water at 1 km spatial resolution. The raw sigma0 data in HH and HV polarization are first corrected for thermal and random noise by extracting the background thermal noise level and smoothing the image with several filters. At the next step texture characteristics are computed in a moving window using a Gray Level Co-occurence Matrix (GLCM). A neural network is applied at the last step for processing array of the most informative texture characteristics and ice/water classification. The main results are: * the most informative texture characteristics to be used for sea ice classification were revealed; * the best set of parameters including the window size, number of levels of quantization of sigma0 values and co-occurence distance was found; * a support vector machine (SVM) was trained on results of visual classification of 30 Sentinel-1 images. Despite the general high accuracy of the neural network (95% of true positive classification) problems with classification of young newly formed ice and rough water arise due to the similar average backscatter and texture. Other methods of smoothing and computation of texture characteristics (e.g. computation of GLCM from a variable size window) is assessed. The developed scheme will be utilized in NRT processing of Sentinel-1 data at NERSC within the MyOcean2 project.

A Directed Acyclic Graph-Large Margin Distribution Machine Model for Music Symbol Classification

PubMed Central

Wen, Cuihong; Zhang, Jing; Rebelo, Ana; Cheng, Fanyong

2016-01-01

Optical Music Recognition (OMR) has received increasing attention in recent years. In this paper, we propose a classifier based on a new method named Directed Acyclic Graph-Large margin Distribution Machine (DAG-LDM). The DAG-LDM is an improvement of the Large margin Distribution Machine (LDM), which is a binary classifier that optimizes the margin distribution by maximizing the margin mean and minimizing the margin variance simultaneously. We modify the LDM to the DAG-LDM to solve the multi-class music symbol classification problem. Tests are conducted on more than 10000 music symbol images, obtained from handwritten and printed images of music scores. The proposed method provides superior classification capability and achieves much higher classification accuracy than the state-of-the-art algorithms such as Support Vector Machines (SVMs) and Neural Networks (NNs). PMID:26985826

A Directed Acyclic Graph-Large Margin Distribution Machine Model for Music Symbol Classification.

PubMed

Wen, Cuihong; Zhang, Jing; Rebelo, Ana; Cheng, Fanyong

2016-01-01

Optical Music Recognition (OMR) has received increasing attention in recent years. In this paper, we propose a classifier based on a new method named Directed Acyclic Graph-Large margin Distribution Machine (DAG-LDM). The DAG-LDM is an improvement of the Large margin Distribution Machine (LDM), which is a binary classifier that optimizes the margin distribution by maximizing the margin mean and minimizing the margin variance simultaneously. We modify the LDM to the DAG-LDM to solve the multi-class music symbol classification problem. Tests are conducted on more than 10000 music symbol images, obtained from handwritten and printed images of music scores. The proposed method provides superior classification capability and achieves much higher classification accuracy than the state-of-the-art algorithms such as Support Vector Machines (SVMs) and Neural Networks (NNs).

Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Cao, Xiangyong; Zhou, Feng; Xu, Lin; Meng, Deyu; Xu, Zongben; Paisley, John

2018-05-01

This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent (SGD) and update the class labels of all pixel vectors using an alpha-expansion min-cut-based algorithm. Compared with other state-of-the-art methods, the proposed classification method achieves better performance on one synthetic dataset and two benchmark HSI datasets in a number of experimental settings.

A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.

PubMed

Pang, Shuchao; Yu, Zhezhou; Orgun, Mehmet A

2017-03-01

Highly accurate classification of biomedical images is an essential task in the clinical diagnosis of numerous medical diseases identified from those images. Traditional image classification methods combined with hand-crafted image feature descriptors and various classifiers are not able to effectively improve the accuracy rate and meet the high requirements of classification of biomedical images. The same also holds true for artificial neural network models directly trained with limited biomedical images used as training data or directly used as a black box to extract the deep features based on another distant dataset. In this study, we propose a highly reliable and accurate end-to-end classifier for all kinds of biomedical images via deep learning and transfer learning. We first apply domain transferred deep convolutional neural network for building a deep model; and then develop an overall deep learning architecture based on the raw pixels of original biomedical images using supervised training. In our model, we do not need the manual design of the feature space, seek an effective feature vector classifier or segment specific detection object and image patches, which are the main technological difficulties in the adoption of traditional image classification methods. Moreover, we do not need to be concerned with whether there are large training sets of annotated biomedical images, affordable parallel computing resources featuring GPUs or long times to wait for training a perfect deep model, which are the main problems to train deep neural networks for biomedical image classification as observed in recent works. With the utilization of a simple data augmentation method and fast convergence speed, our algorithm can achieve the best accuracy rate and outstanding classification ability for biomedical images. We have evaluated our classifier on several well-known public biomedical datasets and compared it with several state-of-the-art approaches. We propose a robust automated end-to-end classifier for biomedical images based on a domain transferred deep convolutional neural network model that shows a highly reliable and accurate performance which has been confirmed on several public biomedical image datasets. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

A signature dissimilarity measure for trabecular bone texture in knee radiographs

DOE Office of Scientific and Technical Information (OSTI.GOV)

Woloszynski, T.; Podsiadlo, P.; Stachowiak, G. W.

Purpose: The purpose of this study is to develop a dissimilarity measure for the classification of trabecular bone (TB) texture in knee radiographs. Problems associated with the traditional extraction and selection of texture features and with the invariance to imaging conditions such as image size, anisotropy, noise, blur, exposure, magnification, and projection angle were addressed. Methods: In the method developed, called a signature dissimilarity measure (SDM), a sum of earth mover's distances calculated for roughness and orientation signatures is used to quantify dissimilarities between textures. Scale-space theory was used to ensure scale and rotation invariance. The effects of image size,more » anisotropy, noise, and blur on the SDM developed were studied using computer generated fractal texture images. The invariance of the measure to image exposure, magnification, and projection angle was studied using x-ray images of human tibia head. For the studies, Mann-Whitney tests with significance level of 0.01 were used. A comparison study between the performances of a SDM based classification system and other two systems in the classification of Brodatz textures and the detection of knee osteoarthritis (OA) were conducted. The other systems are based on weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM) and local binary patterns (LBP). Results: Results obtained indicate that the SDM developed is invariant to image exposure (2.5-30 mA s), magnification (x1.00-x1.35), noise associated with film graininess and quantum mottle (<25%), blur generated by a sharp film screen, and image size (>64x64 pixels). However, the measure is sensitive to changes in projection angle (>5 deg.), image anisotropy (>30 deg.), and blur generated by a regular film screen. For the classification of Brodatz textures, the SDM based system produced comparable results to the LBP system. For the detection of knee OA, the SDM based system achieved 78.8% classification accuracy and outperformed the WND-CHARM system (64.2%). Conclusions: The SDM is well suited for the classification of TB texture images in knee OA detection and may be useful for the texture classification of medical images in general.« less

A stereo remote sensing feature selection method based on artificial bee colony algorithm

NASA Astrophysics Data System (ADS)

Yan, Yiming; Liu, Pigang; Zhang, Ye; Su, Nan; Tian, Shu; Gao, Fengjiao; Shen, Yi

2014-05-01

To improve the efficiency of stereo information for remote sensing classification, a stereo remote sensing feature selection method is proposed in this paper presents, which is based on artificial bee colony algorithm. Remote sensing stereo information could be described by digital surface model (DSM) and optical image, which contain information of the three-dimensional structure and optical characteristics, respectively. Firstly, three-dimensional structure characteristic could be analyzed by 3D-Zernike descriptors (3DZD). However, different parameters of 3DZD could descript different complexity of three-dimensional structure, and it needs to be better optimized selected for various objects on the ground. Secondly, features for representing optical characteristic also need to be optimized. If not properly handled, when a stereo feature vector composed of 3DZD and image features, that would be a lot of redundant information, and the redundant information may not improve the classification accuracy, even cause adverse effects. To reduce information redundancy while maintaining or improving the classification accuracy, an optimized frame for this stereo feature selection problem is created, and artificial bee colony algorithm is introduced for solving this optimization problem. Experimental results show that the proposed method can effectively improve the computational efficiency, improve the classification accuracy.

Imaging techniques in digital forensic investigation: a study using neural networks

NASA Astrophysics Data System (ADS)

Williams, Godfried

2006-09-01

Imaging techniques have been applied to a number of applications, such as translation and classification problems in medicine and defence. This paper examines the application of imaging techniques in digital forensics investigation using neural networks. A review of applications of digital image processing is presented, whiles a Pedagogical analysis of computer forensics is also highlighted. A data set describing selected images in different forms are used in the simulation and experimentation.

Applying machine learning classification techniques to automate sky object cataloguing

NASA Astrophysics Data System (ADS)

Fayyad, Usama M.; Doyle, Richard J.; Weir, W. Nick; Djorgovski, Stanislav

1993-08-01

We describe the application of an Artificial Intelligence machine learning techniques to the development of an automated tool for the reduction of a large scientific data set. The 2nd Mt. Palomar Northern Sky Survey is nearly completed. This survey provides comprehensive coverage of the northern celestial hemisphere in the form of photographic plates. The plates are being transformed into digitized images whose quality will probably not be surpassed in the next ten to twenty years. The images are expected to contain on the order of 107 galaxies and 108 stars. Astronomers wish to determine which of these sky objects belong to various classes of galaxies and stars. Unfortunately, the size of this data set precludes analysis in an exclusively manual fashion. Our approach is to develop a software system which integrates the functions of independently developed techniques for image processing and data classification. Digitized sky images are passed through image processing routines to identify sky objects and to extract a set of features for each object. These routines are used to help select a useful set of attributes for classifying sky objects. Then GID3 (Generalized ID3) and O-B Tree, two inductive learning techniques, learns classification decision trees from examples. These classifiers will then be applied to new data. These developmnent process is highly interactive, with astronomer input playing a vital role. Astronomers refine the feature set used to construct sky object descriptions, and evaluate the performance of the automated classification technique on new data. This paper gives an overview of the machine learning techniques with an emphasis on their general applicability, describes the details of our specific application, and reports the initial encouraging results. The results indicate that our machine learning approach is well-suited to the problem. The primary benefit of the approach is increased data reduction throughput. Another benefit is consistency of classification. The classification rules which are the product of the inductive learning techniques will form an objective, examinable basis for classifying sky objects. A final, not to be underestimated benefit is that astronomers will be freed from the tedium of an intensely visual task to pursue more challenging analysis and interpretation problems based on automatically catalogued data.

Comparison of Unsupervised Vegetation Classification Methods from Vhr Images after Shadows Removal by Innovative Algorithms

NASA Astrophysics Data System (ADS)

Movia, A.; Beinat, A.; Crosilla, F.

2015-04-01

The recognition of vegetation by the analysis of very high resolution (VHR) aerial images provides meaningful information about environmental features; nevertheless, VHR images frequently contain shadows that generate significant problems for the classification of the image components and for the extraction of the needed information. The aim of this research is to classify, from VHR aerial images, vegetation involved in the balance process of the environmental biochemical cycle, and to discriminate it with respect to urban and agricultural features. Three classification algorithms have been experimented in order to better recognize vegetation, and compared to NDVI index; unfortunately all these methods are conditioned by the presence of shadows on the images. Literature presents several algorithms to detect and remove shadows in the scene: most of them are based on the RGB to HSI transformations. In this work some of them have been implemented and compared with one based on RGB bands. Successively, in order to remove shadows and restore brightness on the images, some innovative algorithms, based on Procrustes theory, have been implemented and applied. Among these, we evaluate the capability of the so called "not-centered oblique Procrustes" and "anisotropic Procrustes" methods to efficiently restore brightness with respect to a linear correlation correction based on the Cholesky decomposition. Some experimental results obtained by different classification methods after shadows removal carried out with the innovative algorithms are presented and discussed.

Model selection for anomaly detection

NASA Astrophysics Data System (ADS)

Burnaev, E.; Erofeev, P.; Smolyakov, D.

2015-12-01

Anomaly detection based on one-class classification algorithms is broadly used in many applied domains like image processing (e.g. detection of whether a patient is "cancerous" or "healthy" from mammography image), network intrusion detection, etc. Performance of an anomaly detection algorithm crucially depends on a kernel, used to measure similarity in a feature space. The standard approaches (e.g. cross-validation) for kernel selection, used in two-class classification problems, can not be used directly due to the specific nature of a data (absence of a second, abnormal, class data). In this paper we generalize several kernel selection methods from binary-class case to the case of one-class classification and perform extensive comparison of these approaches using both synthetic and real-world data.

Classifying Acute Ischemic Stroke Onset Time using Deep Imaging Features

PubMed Central

Ho, King Chung; Speier, William; El-Saden, Suzie; Arnold, Corey W.

2017-01-01

Models have been developed to predict stroke outcomes (e.g., mortality) in attempt to provide better guidance for stroke treatment. However, there is little work in developing classification models for the problem of unknown time-since-stroke (TSS), which determines a patient’s treatment eligibility based on a clinical defined cutoff time point (i.e., <4.5hrs). In this paper, we construct and compare machine learning methods to classify TSS<4.5hrs using magnetic resonance (MR) imaging features. We also propose a deep learning model to extract hidden representations from the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional imaging features. Finally, we discuss a strategy to visualize the learned features from the proposed deep learning model. The cross-validation results show that our best classifier achieved an area under the curve of 0.68, which improves significantly over current clinical methods (0.58), demonstrating the potential benefit of using advanced machine learning methods in TSS classification. PMID:29854156

Model-based object classification using unification grammars and abstract representations

NASA Astrophysics Data System (ADS)

Liburdy, Kathleen A.; Schalkoff, Robert J.

1993-04-01

The design and implementation of a high level computer vision system which performs object classification is described. General object labelling and functional analysis require models of classes which display a wide range of geometric variations. A large representational gap exists between abstract criteria such as `graspable' and current geometric image descriptions. The vision system developed and described in this work addresses this problem and implements solutions based on a fusion of semantics, unification, and formal language theory. Object models are represented using unification grammars, which provide a framework for the integration of structure and semantics. A methodology for the derivation of symbolic image descriptions capable of interacting with the grammar-based models is described and implemented. A unification-based parser developed for this system achieves object classification by determining if the symbolic image description can be unified with the abstract criteria of an object model. Future research directions are indicated.

Detection of colorectal masses in CT colonography: application of deep residual networks for differentiating masses from normal colon anatomy

NASA Astrophysics Data System (ADS)

Näppi, Janne J.; Hironaka, Toru; Yoshida, Hiroyuki

2018-02-01

Even though the clinical consequences of a missed colorectal cancer far outweigh those of a missed polyp, there has been little work on computer-aided detection (CADe) for colorectal masses in CT colonography (CTC). One of the problems is that it is not clear how to manually design mathematical image-based features that could be used to differentiate effectively between masses and certain types of normal colon anatomy such as ileocecal valves (ICVs). Deep learning has demonstrated ability to automatically determine effective discriminating features in many image-based problems. Recently, residual networks (ResNets) were developed to address the practical problems of constructing deep network architectures for optimizing the performance of deep learning. In this pilot study, we compared the classification performance of a conventional 2D-convolutional ResNet (2D-ResNet) with that of a volumetric 3D-convolutional ResNet (3D-ResNet) in differentiating masses from normal colon anatomy in CTC. For the development and evaluation of the ResNets, 695 volumetric images of biopsy-proven colorectal masses, ICVs, haustral folds, and rectal tubes were sampled from 196 clinical CTC cases and divided randomly into independent training, validation, and test datasets. The training set was expanded by use of volumetric data augmentation. Our preliminary results on the 140 test samples indicate that it is feasible to train a deep volumetric 3D-ResNet for performing effective image-based discriminations in CTC. The 3D-ResNet slightly outperformed the 2D-ResNet in the discrimination of masses and normal colon anatomy, but the statistical difference between their very high classification accuracies was not significant. The highest classification accuracy was obtained by combining the mass-likelihood estimates of the 2D- and 3D-ResNets, which enabled correct classification of all of the masses.

Real-Time Blob-Wise Sugar Beets VS Weeds Classification for Monitoring Fields Using Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Milioto, A.; Lottes, P.; Stachniss, C.

2017-08-01

UAVs are becoming an important tool for field monitoring and precision farming. A prerequisite for observing and analyzing fields is the ability to identify crops and weeds from image data. In this paper, we address the problem of detecting the sugar beet plants and weeds in the field based solely on image data. We propose a system that combines vegetation detection and deep learning to obtain a high-quality classification of the vegetation in the field into value crops and weeds. We implemented and thoroughly evaluated our system on image data collected from different sugar beet fields and illustrate that our approach allows for accurately identifying the weeds on the field.

Scene Semantic Segmentation from Indoor Rgb-D Images Using Encode-Decoder Fully Convolutional Networks

NASA Astrophysics Data System (ADS)

Wang, Z.; Li, T.; Pan, L.; Kang, Z.

2017-09-01

With increasing attention for the indoor environment and the development of low-cost RGB-D sensors, indoor RGB-D images are easily acquired. However, scene semantic segmentation is still an open area, which restricts indoor applications. The depth information can help to distinguish the regions which are difficult to be segmented out from the RGB images with similar color or texture in the indoor scenes. How to utilize the depth information is the key problem of semantic segmentation for RGB-D images. In this paper, we propose an Encode-Decoder Fully Convolutional Networks for RGB-D image classification. We use Multiple Kernel Maximum Mean Discrepancy (MK-MMD) as a distance measure to find common and special features of RGB and D images in the network to enhance performance of classification automatically. To explore better methods of applying MMD, we designed two strategies; the first calculates MMD for each feature map, and the other calculates MMD for whole batch features. Based on the result of classification, we use the full connect CRFs for the semantic segmentation. The experimental results show that our method can achieve a good performance on indoor RGB-D image semantic segmentation.

Automated image processing method for the diagnosis and classification of malaria on thin blood smears.

PubMed

Ross, Nicholas E; Pritchard, Charles J; Rubin, David M; Dusé, Adriano G

2006-05-01

Malaria is a serious global health problem, and rapid, accurate diagnosis is required to control the disease. An image processing algorithm to automate the diagnosis of malaria on thin blood smears is developed. The image classification system is designed to positively identify malaria parasites present in thin blood smears, and differentiate the species of malaria. Images are acquired using a charge-coupled device camera connected to a light microscope. Morphological and novel threshold selection techniques are used to identify erythrocytes (red blood cells) and possible parasites present on microscopic slides. Image features based on colour, texture and the geometry of the cells and parasites are generated, as well as features that make use of a priori knowledge of the classification problem and mimic features used by human technicians. A two-stage tree classifier using backpropogation feedforward neural networks distinguishes between true and false positives, and then diagnoses the species (Plasmodium falciparum, P. vivax, P. ovale or P. malariae) of the infection. Malaria samples obtained from the Department of Clinical Microbiology and Infectious Diseases at the University of the Witwatersrand Medical School are used for training and testing of the system. Infected erythrocytes are positively identified with a sensitivity of 85% and a positive predictive value (PPV) of 81%, which makes the method highly sensitive at diagnosing a complete sample provided many views are analysed. Species were correctly determined for 11 out of 15 samples.

Convex formulation of multiple instance learning from positive and unlabeled bags.

PubMed

Bao, Han; Sakai, Tomoya; Sato, Issei; Sugiyama, Masashi

2018-05-24

Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available. MIL has a variety of applications such as content-based image retrieval, text categorization, and medical diagnosis. Most of the previous work for MIL assume that training bags are fully labeled. However, it is often difficult to obtain an enough number of labeled bags in practical situations, while many unlabeled bags are available. A learning framework called PU classification (positive and unlabeled classification) can address this problem. In this paper, we propose a convex PU classification method to solve an MIL problem. We experimentally show that the proposed method achieves better performance with significantly lower computation costs than an existing method for PU-MIL. Copyright © 2018 Elsevier Ltd. All rights reserved.

Land cover/use classification of Cairns, Queensland, Australia: A remote sensing study involving the conjunctive use of the airborne imaging spectrometer, the large format camera and the thematic mapper simulator

NASA Technical Reports Server (NTRS)

Heric, Matthew; Cox, William; Gordon, Daniel K.

1987-01-01

In an attempt to improve the land cover/use classification accuracy obtainable from remotely sensed multispectral imagery, Airborne Imaging Spectrometer-1 (AIS-1) images were analyzed in conjunction with Thematic Mapper Simulator (NS001) Large Format Camera color infrared photography and black and white aerial photography. Specific portions of the combined data set were registered and used for classification. Following this procedure, the resulting derived data was tested using an overall accuracy assessment method. Precise photogrammetric 2D-3D-2D geometric modeling techniques is not the basis for this study. Instead, the discussion exposes resultant spectral findings from the image-to-image registrations. Problems associated with the AIS-1 TMS integration are considered, and useful applications of the imagery combination are presented. More advanced methodologies for imagery integration are needed if multisystem data sets are to be utilized fully. Nevertheless, research, described herein, provides a formulation for future Earth Observation Station related multisensor studies.

Three-Category Classification of Magnetic Resonance Hearing Loss Images Based on Deep Autoencoder.

PubMed

Jia, Wenjuan; Yang, Ming; Wang, Shui-Hua

2017-09-11

Hearing loss, a partial or total inability to hear, is known as hearing impairment. Untreated hearing loss can have a bad effect on normal social communication, and it can cause psychological problems in patients. Therefore, we design a three-category classification system to detect the specific category of hearing loss, which is beneficial to be treated in time for patients. Before the training and test stages, we use the technology of data augmentation to produce a balanced dataset. Then we use deep autoencoder neural network to classify the magnetic resonance brain images. In the stage of deep autoencoder, we use stacked sparse autoencoder to generate visual features, and softmax layer to classify the different brain images into three categories of hearing loss. Our method can obtain good experimental results. The overall accuracy of our method is 99.5%, and the time consuming is 0.078 s per brain image. Our proposed method based on stacked sparse autoencoder works well in classification of hearing loss images. The overall accuracy of our method is 4% higher than the best of state-of-the-art approaches.

Texture classification using autoregressive filtering

NASA Technical Reports Server (NTRS)

Lawton, W. M.; Lee, M.

1984-01-01

A general theory of image texture models is proposed and its applicability to the problem of scene segmentation using texture classification is discussed. An algorithm, based on half-plane autoregressive filtering, which optimally utilizes second order statistics to discriminate between texture classes represented by arbitrary wide sense stationary random fields is described. Empirical results of applying this algorithm to natural and sysnthesized scenes are presented and future research is outlined.

Medical X-ray Image Hierarchical Classification Using a Merging and Splitting Scheme in Feature Space.

PubMed

Fesharaki, Nooshin Jafari; Pourghassem, Hossein

2013-07-01

Due to the daily mass production and the widespread variation of medical X-ray images, it is necessary to classify these for searching and retrieving proposes, especially for content-based medical image retrieval systems. In this paper, a medical X-ray image hierarchical classification structure based on a novel merging and splitting scheme and using shape and texture features is proposed. In the first level of the proposed structure, to improve the classification performance, similar classes with regard to shape contents are grouped based on merging measures and shape features into the general overlapped classes. In the next levels of this structure, the overlapped classes split in smaller classes based on the classification performance of combination of shape and texture features or texture features only. Ultimately, in the last levels, this procedure is also continued forming all the classes, separately. Moreover, to optimize the feature vector in the proposed structure, we use orthogonal forward selection algorithm according to Mahalanobis class separability measure as a feature selection and reduction algorithm. In other words, according to the complexity and inter-class distance of each class, a sub-space of the feature space is selected in each level and then a supervised merging and splitting scheme is applied to form the hierarchical classification. The proposed structure is evaluated on a database consisting of 2158 medical X-ray images of 18 classes (IMAGECLEF 2005 database) and accuracy rate of 93.6% in the last level of the hierarchical structure for an 18-class classification problem is obtained.

Adaptive skin detection based on online training

NASA Astrophysics Data System (ADS)

Zhang, Ming; Tang, Liang; Zhou, Jie; Rong, Gang

2007-11-01

Skin is a widely used cue for porn image classification. Most conventional methods are off-line training schemes. They usually use a fixed boundary to segment skin regions in the images and are effective only in restricted conditions: e.g. good lightness and unique human race. This paper presents an adaptive online training scheme for skin detection which can handle these tough cases. In our approach, skin detection is considered as a classification problem on Gaussian mixture model. For each image, human face is detected and the face color is used to establish a primary estimation of skin color distribution. Then an adaptive online training algorithm is used to find the real boundary between skin color and background color in current image. Experimental results on 450 images showed that the proposed method is more robust in general situations than the conventional ones.

Fast Image Texture Classification Using Decision Trees

NASA Technical Reports Server (NTRS)

Thompson, David R.

2011-01-01

Texture analysis would permit improved autonomous, onboard science data interpretation for adaptive navigation, sampling, and downlink decisions. These analyses would assist with terrain analysis and instrument placement in both macroscopic and microscopic image data products. Unfortunately, most state-of-the-art texture analysis demands computationally expensive convolutions of filters involving many floating-point operations. This makes them infeasible for radiation- hardened computers and spaceflight hardware. A new method approximates traditional texture classification of each image pixel with a fast decision-tree classifier. The classifier uses image features derived from simple filtering operations involving integer arithmetic. The texture analysis method is therefore amenable to implementation on FPGA (field-programmable gate array) hardware. Image features based on the "integral image" transform produce descriptive and efficient texture descriptors. Training the decision tree on a set of training data yields a classification scheme that produces reasonable approximations of optimal "texton" analysis at a fraction of the computational cost. A decision-tree learning algorithm employing the traditional k-means criterion of inter-cluster variance is used to learn tree structure from training data. The result is an efficient and accurate summary of surface morphology in images. This work is an evolutionary advance that unites several previous algorithms (k-means clustering, integral images, decision trees) and applies them to a new problem domain (morphology analysis for autonomous science during remote exploration). Advantages include order-of-magnitude improvements in runtime, feasibility for FPGA hardware, and significant improvements in texture classification accuracy.

Convolutional neural network-based classification system design with compressed wireless sensor network images.

PubMed

Ahn, Jungmo; Park, JaeYeon; Park, Donghwan; Paek, Jeongyeup; Ko, JeongGil

2018-01-01

With the introduction of various advanced deep learning algorithms, initiatives for image classification systems have transitioned over from traditional machine learning algorithms (e.g., SVM) to Convolutional Neural Networks (CNNs) using deep learning software tools. A prerequisite in applying CNN to real world applications is a system that collects meaningful and useful data. For such purposes, Wireless Image Sensor Networks (WISNs), that are capable of monitoring natural environment phenomena using tiny and low-power cameras on resource-limited embedded devices, can be considered as an effective means of data collection. However, with limited battery resources, sending high-resolution raw images to the backend server is a burdensome task that has direct impact on network lifetime. To address this problem, we propose an energy-efficient pre- and post- processing mechanism using image resizing and color quantization that can significantly reduce the amount of data transferred while maintaining the classification accuracy in the CNN at the backend server. We show that, if well designed, an image in its highly compressed form can be well-classified with a CNN model trained in advance using adequately compressed data. Our evaluation using a real image dataset shows that an embedded device can reduce the amount of transmitted data by ∼71% while maintaining a classification accuracy of ∼98%. Under the same conditions, this process naturally reduces energy consumption by ∼71% compared to a WISN that sends the original uncompressed images.

On the detection of pornographic digital images

NASA Astrophysics Data System (ADS)

Schettini, Raimondo; Brambilla, Carla; Cusano, Claudio; Ciocca, Gianluigi

2003-06-01

The paper addresses the problem of distinguishing between pornographic and non-pornographic photographs, for the design of semantic filters for the web. Both, decision forests of trees built according to CART (Classification And Regression Trees) methodology and Support Vectors Machines (SVM), have been used to perform the classification. The photographs are described by a set of low-level features, features that can be automatically computed simply on gray-level and color representation of the image. The database used in our experiments contained 1500 photographs, 750 of which labeled as pornographic on the basis of the independent judgement of several viewers.

Single image super-resolution based on approximated Heaviside functions and iterative refinement

PubMed Central

Wang, Xin-Yu; Huang, Ting-Zhu; Deng, Liang-Jian

2018-01-01

One method of solving the single-image super-resolution problem is to use Heaviside functions. This has been done previously by making a binary classification of image components as “smooth” and “non-smooth”, describing these with approximated Heaviside functions (AHFs), and iteration including l1 regularization. We now introduce a new method in which the binary classification of image components is extended to different degrees of smoothness and non-smoothness, these components being represented by various classes of AHFs. Taking into account the sparsity of the non-smooth components, their coefficients are l1 regularized. In addition, to pick up more image details, the new method uses an iterative refinement for the residuals between the original low-resolution input and the downsampled resulting image. Experimental results showed that the new method is superior to the original AHF method and to four other published methods. PMID:29329298

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

PubMed Central

Hoo-Chang, Shin; Roth, Holger R.; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel

2016-01-01

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets (i.e. ImageNet) and the revival of deep convolutional neural networks (CNN). CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models (supervised) pre-trained from natural image dataset to medical image tasks (although domain transfer between two medical image datasets is also possible). In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computeraided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks. PMID:26886976

Impervious surface mapping with Quickbird imagery

PubMed Central

Lu, Dengsheng; Hetrick, Scott; Moran, Emilio

2010-01-01

This research selects two study areas with different urban developments, sizes, and spatial patterns to explore the suitable methods for mapping impervious surface distribution using Quickbird imagery. The selected methods include per-pixel based supervised classification, segmentation-based classification, and a hybrid method. A comparative analysis of the results indicates that per-pixel based supervised classification produces a large number of “salt-and-pepper” pixels, and segmentation based methods can significantly reduce this problem. However, neither method can effectively solve the spectral confusion of impervious surfaces with water/wetland and bare soils and the impacts of shadows. In order to accurately map impervious surface distribution from Quickbird images, manual editing is necessary and may be the only way to extract impervious surfaces from the confused land covers and the shadow problem. This research indicates that the hybrid method consisting of thresholding techniques, unsupervised classification and limited manual editing provides the best performance. PMID:21643434

Segmentation, modeling and classification of the compact objects in a pile

NASA Technical Reports Server (NTRS)

Gupta, Alok; Funka-Lea, Gareth; Wohn, Kwangyoen

1990-01-01

The problem of interpreting dense range images obtained from the scene of a heap of man-made objects is discussed. A range image interpretation system consisting of segmentation, modeling, verification, and classification procedures is described. First, the range image is segmented into regions and reasoning is done about the physical support of these regions. Second, for each region several possible three-dimensional interpretations are made based on various scenarios of the objects physical support. Finally each interpretation is tested against the data for its consistency. The superquadric model is selected as the three-dimensional shape descriptor, plus tapering deformations along the major axis. Experimental results obtained from some complex range images of mail pieces are reported to demonstrate the soundness and the robustness of our approach.

Authentication of bee pollen grains in bright-field microscopy by combining one-class classification techniques and image processing.

PubMed

Chica, Manuel

2012-11-01

A novel method for authenticating pollen grains in bright-field microscopic images is presented in this work. The usage of this new method is clear in many application fields such as bee-keeping sector, where laboratory experts need to identify fraudulent bee pollen samples against local known pollen types. Our system is based on image processing and one-class classification to reject unknown pollen grain objects. The latter classification technique allows us to tackle the major difficulty of the problem, the existence of many possible fraudulent pollen types, and the impossibility of modeling all of them. Different one-class classification paradigms are compared to study the most suitable technique for solving the problem. In addition, feature selection algorithms are applied to reduce the complexity and increase the accuracy of the models. For each local pollen type, a one-class classifier is trained and aggregated into a multiclassifier model. This multiclassification scheme combines the output of all the one-class classifiers in a unique final response. The proposed method is validated by authenticating pollen grains belonging to different Spanish bee pollen types. The overall accuracy of the system on classifying fraudulent microscopic pollen grain objects is 92.3%. The system is able to rapidly reject pollen grains, which belong to nonlocal pollen types, reducing the laboratory work and effort. The number of possible applications of this authentication method in the microscopy research field is unlimited. Copyright © 2012 Wiley Periodicals, Inc.

Joint Feature Selection and Classification for Multilabel Learning.

PubMed

Huang, Jun; Li, Guorong; Huang, Qingming; Wu, Xindong

2018-03-01

Multilabel learning deals with examples having multiple class labels simultaneously. It has been applied to a variety of applications, such as text categorization and image annotation. A large number of algorithms have been proposed for multilabel learning, most of which concentrate on multilabel classification problems and only a few of them are feature selection algorithms. Current multilabel classification models are mainly built on a single data representation composed of all the features which are shared by all the class labels. Since each class label might be decided by some specific features of its own, and the problems of classification and feature selection are often addressed independently, in this paper, we propose a novel method which can perform joint feature selection and classification for multilabel learning, named JFSC. Different from many existing methods, JFSC learns both shared features and label-specific features by considering pairwise label correlations, and builds the multilabel classifier on the learned low-dimensional data representations simultaneously. A comparative study with state-of-the-art approaches manifests a competitive performance of our proposed method both in classification and feature selection for multilabel learning.

Drawing a baseline in aesthetic quality assessment

NASA Astrophysics Data System (ADS)

Rubio, Fernando; Flores, M. Julia; Puerta, Jose M.

2018-04-01

Aesthetic classification of images is an inherently subjective task. There does not exist a validated collection of images/photographs labeled as having good or bad quality from experts. Nowadays, the closest approximation to that is to use databases of photos where a group of users rate each image. Hence, there is not a unique good/bad label but a rating distribution given by users voting. Due to this peculiarity, it is not possible to state the problem of binary aesthetic supervised classification in such a direct mode as other Computer Vision tasks. Recent literature follows an approach where researchers utilize the average rates from the users for each image, and they establish an arbitrary threshold to determine their class or label. In this way, images above the threshold are considered of good quality, while images below the threshold are seen as bad quality. This paper analyzes current literature, and it reviews those attributes able to represent an image, differentiating into three families: specific, general and deep features. Among those which have been proved more competitive, we have selected a representative subset, being our main goal to establish a clear experimental framework. Finally, once features were selected, we have used them for the full AVA dataset. We have to remark that to perform validation we report not only accuracy values, which is not that informative in this case, but also, metrics able to evaluate classification power within imbalanced datasets. We have conducted a series of experiments so that distinct well-known classifiers are learned from data. Like that, this paper provides what we could consider valuable and valid baseline results for the given problem.

Fuzzy C-means classification for corrosion evolution of steel images

NASA Astrophysics Data System (ADS)

Trujillo, Maite; Sadki, Mustapha

2004-05-01

An unavoidable problem of metal structures is their exposure to rust degradation during their operational life. Thus, the surfaces need to be assessed in order to avoid potential catastrophes. There is considerable interest in the use of patch repair strategies which minimize the project costs. However, to operate such strategies with confidence in the long useful life of the repair, it is essential that the condition of the existing coatings and the steel substrate can be accurately quantified and classified. This paper describes the application of fuzzy set theory for steel surfaces classification according to the steel rust time. We propose a semi-automatic technique to obtain image clustering using the Fuzzy C-means (FCM) algorithm and we analyze two kinds of data to study the classification performance. Firstly, we investigate the use of raw images" pixels without any pre-processing methods and neighborhood pixels. Secondly, we apply Gaussian noise to the images with different standard deviation to study the FCM method tolerance to Gaussian noise. The noisy images simulate the possible perturbations of the images due to the weather or rust deposits in the steel surfaces during typical on-site acquisition procedures

Improved Vote Aggregation Techniques for the Geo-Wiki Cropland Capture Crowdsourcing Game

NASA Astrophysics Data System (ADS)

Baklanov, Artem; Fritz, Steffen; Khachay, Michael; Nurmukhametov, Oleg; Salk, Carl; See, Linda; Shchepashchenko, Dmitry

2016-04-01

Crowdsourcing is a new approach for solving data processing problems for which conventional methods appear to be inaccurate, expensive, or time-consuming. Nowadays, the development of new crowdsourcing techniques is mostly motivated by so called Big Data problems, including problems of assessment and clustering for large datasets obtained in aerospace imaging, remote sensing, and even in social network analysis. By involving volunteers from all over the world, the Geo-Wiki project tackles problems of environmental monitoring with applications to flood resilience, biomass data analysis and classification of land cover. For example, the Cropland Capture Game, which is a gamified version of Geo-Wiki, was developed to aid in the mapping of cultivated land, and was used to gather 4.5 million image classifications from the Earth's surface. More recently, the Picture Pile game, which is a more generalized version of Cropland Capture, aims to identify tree loss over time from pairs of very high resolution satellite images. Despite recent progress in image analysis, the solution to these problems is hard to automate since human experts still outperform the majority of machine learning algorithms and artificial systems in this field on certain image recognition tasks. The replacement of rare and expensive experts by a team of distributed volunteers seems to be promising, but this approach leads to challenging questions such as: how can individual opinions be aggregated optimally, how can confidence bounds be obtained, and how can the unreliability of volunteers be dealt with? In this paper, on the basis of several known machine learning techniques, we propose a technical approach to improve the overall performance of the majority voting decision rule used in the Cropland Capture Game. The proposed approach increases the estimated consistency with expert opinion from 77% to 86%.

Segmentation of radiologic images with self-organizing maps: the segmentation problem transformed into a classification task

NASA Astrophysics Data System (ADS)

Pelikan, Erich; Vogelsang, Frank; Tolxdorff, Thomas

1996-04-01

The texture-based segmentation of x-ray images of focal bone lesions using topological maps is introduced. Texture characteristics are described by image-point correlation of feature images to feature vectors. For the segmentation, the topological map is labeled using an improved labeling strategy. Results of the technique are demonstrated on original and synthetic x-ray images and quantified with the aid of quality measures. In addition, a classifier-specific contribution analysis is applied for assessing the feature space.

Matrix frequency analysis and its applications to language classification of textual data for English and Hebrew

NASA Astrophysics Data System (ADS)

Uchill, Joseph H.; Assadi, Amir H.

2003-01-01

The advent of the internet has opened a host of new and exciting questions in the science and mathematics of information organization and data mining. In particular, a highly ambitious promise of the internet is to bring the bulk of human knowledge to everyone with access to a computer network, providing a democratic medium for sharing and communicating knowledge regardless of the language of the communication. The development of sharing and communication of knowledge via transfer of digital files is the first crucial achievement in this direction. Nonetheless, available solutions to numerous ancillary problems remain far from satisfactory. Among such outstanding problems are the first few fundamental questions that have been responsible for the emergence and rapid growth of the new field of Knowledge Engineering, namely, classification of forms of data, their effective organization, and extraction of knowledge from massive distributed data sets, and the design of fast effective search engines. The precision of machine learning algorithms in classification and recognition of image data (e.g. those scanned from books and other printed documents) are still far from human performance and speed in similar tasks. Discriminating the many forms of ASCII data from each other is not as difficult in view of the emerging universal standards for file-format. Nonetheless, most of the past and relatively recent human knowledge is yet to be transformed and saved in such machine readable formats. In particular, an outstanding problem in knowledge engineering is the problem of organization and management--with precision comparable to human performance--of knowledge in the form of images of documents that broadly belong to either text, image or a blend of both. It was shown in that the effectiveness of OCR was intertwined with the success of language and font recognition.

Case-based statistical learning applied to SPECT image classification

NASA Astrophysics Data System (ADS)

Górriz, Juan M.; Ramírez, Javier; Illán, I. A.; Martínez-Murcia, Francisco J.; Segovia, Fermín.; Salas-Gonzalez, Diego; Ortiz, A.

2017-03-01

Statistical learning and decision theory play a key role in many areas of science and engineering. Some examples include time series regression and prediction, optical character recognition, signal detection in communications or biomedical applications for diagnosis and prognosis. This paper deals with the topic of learning from biomedical image data in the classification problem. In a typical scenario we have a training set that is employed to fit a prediction model or learner and a testing set on which the learner is applied to in order to predict the outcome for new unseen patterns. Both processes are usually completely separated to avoid over-fitting and due to the fact that, in practice, the unseen new objects (testing set) have unknown outcomes. However, the outcome yields one of a discrete set of values, i.e. the binary diagnosis problem. Thus, assumptions on these outcome values could be established to obtain the most likely prediction model at the training stage, that could improve the overall classification accuracy on the testing set, or keep its performance at least at the level of the selected statistical classifier. In this sense, a novel case-based learning (c-learning) procedure is proposed which combines hypothesis testing from a discrete set of expected outcomes and a cross-validated classification stage.

Decision Tree Repository and Rule Set Based Mingjiang River Estuarine Wetlands Classifaction

NASA Astrophysics Data System (ADS)

Zhang, W.; Li, X.; Xiao, W.

2018-05-01

The increasing urbanization and industrialization have led to wetland losses in estuarine area of Mingjiang River over past three decades. There has been increasing attention given to produce wetland inventories using remote sensing and GIS technology. Due to inconsistency training site and training sample, traditionally pixel-based image classification methods can't achieve a comparable result within different organizations. Meanwhile, object-oriented image classification technique shows grate potential to solve this problem and Landsat moderate resolution remote sensing images are widely used to fulfill this requirement. Firstly, the standardized atmospheric correct, spectrally high fidelity texture feature enhancement was conducted before implementing the object-oriented wetland classification method in eCognition. Secondly, we performed the multi-scale segmentation procedure, taking the scale, hue, shape, compactness and smoothness of the image into account to get the appropriate parameters, using the top and down region merge algorithm from single pixel level, the optimal texture segmentation scale for different types of features is confirmed. Then, the segmented object is used as the classification unit to calculate the spectral information such as Mean value, Maximum value, Minimum value, Brightness value and the Normalized value. The Area, length, Tightness and the Shape rule of the image object Spatial features and texture features such as Mean, Variance and Entropy of image objects are used as classification features of training samples. Based on the reference images and the sampling points of on-the-spot investigation, typical training samples are selected uniformly and randomly for each type of ground objects. The spectral, texture and spatial characteristics of each type of feature in each feature layer corresponding to the range of values are used to create the decision tree repository. Finally, with the help of high resolution reference images, the random sampling method is used to conduct the field investigation, achieve an overall accuracy of 90.31 %, and the Kappa coefficient is 0.88. The classification method based on decision tree threshold values and rule set developed by the repository, outperforms the results obtained from the traditional methodology. Our decision tree repository and rule set based object-oriented classification technique was an effective method for producing comparable and consistency wetlands data set.

Assessment of Sampling Approaches for Remote Sensing Image Classification in the Iranian Playa Margins

NASA Astrophysics Data System (ADS)

Kazem Alavipanah, Seyed

There are some problems in soil salinity studies based upon remotely sensed data: 1-spectral world is full of ambiguity and therefore soil reflectance can not be attributed to a single soil property such as salinity, 2) soil surface conditions as a function of time and space is a complex phenomena, 3) vegetation with a dynamic biological nature may create some problems in the study of soil salinity. Due to these problems the first question which may arise is how to overcome or minimise these problems. In this study we hypothesised that different sources of data, well established sampling plan and optimum approach could be useful. In order to choose representative training sites in the Iranian playa margins, to define the spectral and informational classes and to overcome some problems encountered in the variation within the field, the following attempts were made: 1) Principal Component Analysis (PCA) in order: a) to determine the most important variables, b) to understand the Landsat satellite images and the most informative components, 2) the photomorphic unit (PMU) consideration and interpretation; 3) study of salt accumulation and salt distribution in the soil profile, 4) use of several forms of field data, such as geologic, geomorphologic and soil information; 6) confirmation of field data and land cover types with farmers and the members of the team. The results led us to find at suitable approaches with a high and acceptable image classification accuracy and image interpretation. KEY WORDS; Photo Morphic Unit, Pprincipal Ccomponent Analysis, Soil Salinity, Field Work, Remote Sensing

Autonomous target recognition using remotely sensed surface vibration measurements

NASA Astrophysics Data System (ADS)

Geurts, James; Ruck, Dennis W.; Rogers, Steven K.; Oxley, Mark E.; Barr, Dallas N.

1993-09-01

The remotely measured surface vibration signatures of tactical military ground vehicles are investigated for use in target classification and identification friend or foe (IFF) systems. The use of remote surface vibration sensing by a laser radar reduces the effects of partial occlusion, concealment, and camouflage experienced by automatic target recognition systems using traditional imagery in a tactical battlefield environment. Linear Predictive Coding (LPC) efficiently represents the vibration signatures and nearest neighbor classifiers exploit the LPC feature set using a variety of distortion metrics. Nearest neighbor classifiers achieve an 88 percent classification rate in an eight class problem, representing a classification performance increase of thirty percent from previous efforts. A novel confidence figure of merit is implemented to attain a 100 percent classification rate with less than 60 percent rejection. The high classification rates are achieved on a target set which would pose significant problems to traditional image-based recognition systems. The targets are presented to the sensor in a variety of aspects and engine speeds at a range of 1 kilometer. The classification rates achieved demonstrate the benefits of using remote vibration measurement in a ground IFF system. The signature modeling and classification system can also be used to identify rotary and fixed-wing targets.

A feasibility study of treatment verification using EPID cine images for hypofractionated lung radiotherapy

NASA Astrophysics Data System (ADS)

Tang, Xiaoli; Lin, Tong; Jiang, Steve

2009-09-01

We propose a novel approach for potential online treatment verification using cine EPID (electronic portal imaging device) images for hypofractionated lung radiotherapy based on a machine learning algorithm. Hypofractionated radiotherapy requires high precision. It is essential to effectively monitor the target to ensure that the tumor is within the beam aperture. We modeled the treatment verification problem as a two-class classification problem and applied an artificial neural network (ANN) to classify the cine EPID images acquired during the treatment into corresponding classes—with the tumor inside or outside of the beam aperture. Training samples were generated for the ANN using digitally reconstructed radiographs (DRRs) with artificially added shifts in the tumor location—to simulate cine EPID images with different tumor locations. Principal component analysis (PCA) was used to reduce the dimensionality of the training samples and cine EPID images acquired during the treatment. The proposed treatment verification algorithm was tested on five hypofractionated lung patients in a retrospective fashion. On average, our proposed algorithm achieved a 98.0% classification accuracy, a 97.6% recall rate and a 99.7% precision rate. This work was first presented at the Seventh International Conference on Machine Learning and Applications, San Diego, CA, USA, 11-13 December 2008.

Information extraction and transmission techniques for spaceborne synthetic aperture radar images

NASA Technical Reports Server (NTRS)

Frost, V. S.; Yurovsky, L.; Watson, E.; Townsend, K.; Gardner, S.; Boberg, D.; Watson, J.; Minden, G. J.; Shanmugan, K. S.

1984-01-01

Information extraction and transmission techniques for synthetic aperture radar (SAR) imagery were investigated. Four interrelated problems were addressed. An optimal tonal SAR image classification algorithm was developed and evaluated. A data compression technique was developed for SAR imagery which is simple and provides a 5:1 compression with acceptable image quality. An optimal textural edge detector was developed. Several SAR image enhancement algorithms have been proposed. The effectiveness of each algorithm was compared quantitatively.

Efficient HIK SVM learning for image classification.

PubMed

Wu, Jianxin

2012-10-01

Histograms are used in almost every aspect of image processing and computer vision, from visual descriptors to image representations. Histogram intersection kernel (HIK) and support vector machine (SVM) classifiers are shown to be very effective in dealing with histograms. This paper presents contributions concerning HIK SVM for image classification. First, we propose intersection coordinate descent (ICD), a deterministic and scalable HIK SVM solver. ICD is much faster than, and has similar accuracies to, general purpose SVM solvers and other fast HIK SVM training methods. We also extend ICD to the efficient training of a broader family of kernels. Second, we show an important empirical observation that ICD is not sensitive to the C parameter in SVM, and we provide some theoretical analyses to explain this observation. ICD achieves high accuracies in many problems, using its default parameters. This is an attractive property for practitioners, because many image processing tasks are too large to choose SVM parameters using cross-validation.

Optical recognition of statistical patterns

NASA Astrophysics Data System (ADS)

Lee, S. H.

1981-12-01

Optical implementation of the Fukunaga-Koontz transform (FKT) and the Least-Squares Linear Mapping Technique (LSLMT) is described. The FKT is a linear transformation which performs image feature extraction for a two-class image classification problem. The LSLMT performs a transform from large dimensional feature space to small dimensional decision space for separating multiple image classes by maximizing the interclass differences while minimizing the intraclass variations. The FKT and the LSLMT were optically implemented by utilizing a coded phase optical processor. The transform was used for classifying birds and fish. After the F-K basis functions were calculated, those most useful for classification were incorporated into a computer generated hologram. The output of the optical processor, consisting of the squared magnitude of the F-K coefficients, was detected by a T.V. camera, digitized, and fed into a micro-computer for classification. A simple linear classifier based on only two F-K coefficients was able to separate the images into two classes, indicating that the F-K transform had chosen good features. Two advantages of optically implementing the FKT and LSLMT are parallel and real time processing.

Optical recognition of statistical patterns

NASA Technical Reports Server (NTRS)

Lee, S. H.

1981-01-01

Optical implementation of the Fukunaga-Koontz transform (FKT) and the Least-Squares Linear Mapping Technique (LSLMT) is described. The FKT is a linear transformation which performs image feature extraction for a two-class image classification problem. The LSLMT performs a transform from large dimensional feature space to small dimensional decision space for separating multiple image classes by maximizing the interclass differences while minimizing the intraclass variations. The FKT and the LSLMT were optically implemented by utilizing a coded phase optical processor. The transform was used for classifying birds and fish. After the F-K basis functions were calculated, those most useful for classification were incorporated into a computer generated hologram. The output of the optical processor, consisting of the squared magnitude of the F-K coefficients, was detected by a T.V. camera, digitized, and fed into a micro-computer for classification. A simple linear classifier based on only two F-K coefficients was able to separate the images into two classes, indicating that the F-K transform had chosen good features. Two advantages of optically implementing the FKT and LSLMT are parallel and real time processing.

Assessing paedophilia based on the haemodynamic brain response to face images.

PubMed

Ponseti, Jorge; Granert, Oliver; Van Eimeren, Thilo; Jansen, Olav; Wolff, Stephan; Beier, Klaus; Deuschl, Günther; Huchzermeier, Christian; Stirn, Aglaja; Bosinski, Hartmut; Roman Siebner, Hartwig

2016-01-01

Objective assessment of sexual preferences may be of relevance in the treatment and prognosis of child sexual offenders. Previous research has indicated that this can be achieved by pattern classification of brain responses to sexual child and adult images. Our recent research showed that human face processing is tuned to sexual age preferences. This observation prompted us to test whether paedophilia can be inferred based on the haemodynamic brain responses to adult and child faces. Twenty-four men sexually attracted to prepubescent boys or girls (paedophiles) and 32 men sexually attracted to men or women (teleiophiles) were exposed to images of child and adult, male and female faces during a functional magnetic resonance imaging (fMRI) session. A cross-validated, automatic pattern classification algorithm of brain responses to facial stimuli yielded four misclassified participants (three false positives), corresponding to a specificity of 91% and a sensitivity of 95%. These results indicate that the functional response to facial stimuli can be reliably used for fMRI-based classification of paedophilia, bypassing the problem of showing child sexual stimuli to paedophiles.

Infrared variation reduction by simultaneous background suppression and target contrast enhancement for deep convolutional neural network-based automatic target recognition

NASA Astrophysics Data System (ADS)

Kim, Sungho

2017-06-01

Automatic target recognition (ATR) is a traditionally challenging problem in military applications because of the wide range of infrared (IR) image variations and the limited number of training images. IR variations are caused by various three-dimensional target poses, noncooperative weather conditions (fog and rain), and difficult target acquisition environments. Recently, deep convolutional neural network-based approaches for RGB images (RGB-CNN) showed breakthrough performance in computer vision problems, such as object detection and classification. The direct use of RGB-CNN to the IR ATR problem fails to work because of the IR database problems (limited database size and IR image variations). An IR variation-reduced deep CNN (IVR-CNN) to cope with the problems is presented. The problem of limited IR database size is solved by a commercial thermal simulator (OKTAL-SE). The second problem of IR variations is mitigated by the proposed shifted ramp function-based intensity transformation. This can suppress the background and enhance the target contrast simultaneously. The experimental results on the synthesized IR images generated by the thermal simulator (OKTAL-SE) validated the feasibility of IVR-CNN for military ATR applications.

Multi-temporal and multi-source remote sensing image classification by nonlinear relative normalization

NASA Astrophysics Data System (ADS)

Tuia, Devis; Marcos, Diego; Camps-Valls, Gustau

2016-10-01

Remote sensing image classification exploiting multiple sensors is a very challenging problem: data from different modalities are affected by spectral distortions and mis-alignments of all kinds, and this hampers re-using models built for one image to be used successfully in other scenes. In order to adapt and transfer models across image acquisitions, one must be able to cope with datasets that are not co-registered, acquired under different illumination and atmospheric conditions, by different sensors, and with scarce ground references. Traditionally, methods based on histogram matching have been used. However, they fail when densities have very different shapes or when there is no corresponding band to be matched between the images. An alternative builds upon manifold alignment. Manifold alignment performs a multidimensional relative normalization of the data prior to product generation that can cope with data of different dimensionality (e.g. different number of bands) and possibly unpaired examples. Aligning data distributions is an appealing strategy, since it allows to provide data spaces that are more similar to each other, regardless of the subsequent use of the transformed data. In this paper, we study a methodology that aligns data from different domains in a nonlinear way through kernelization. We introduce the Kernel Manifold Alignment (KEMA) method, which provides a flexible and discriminative projection map, exploits only a few labeled samples (or semantic ties) in each domain, and reduces to solving a generalized eigenvalue problem. We successfully test KEMA in multi-temporal and multi-source very high resolution classification tasks, as well as on the task of making a model invariant to shadowing for hyperspectral imaging.

Bin Ratio-Based Histogram Distances and Their Application to Image Classification.

PubMed

Hu, Weiming; Xie, Nianhua; Hu, Ruiguang; Ling, Haibin; Chen, Qiang; Yan, Shuicheng; Maybank, Stephen

2014-12-01

Large variations in image background may cause partial matching and normalization problems for histogram-based representations, i.e., the histograms of the same category may have bins which are significantly different, and normalization may produce large changes in the differences between corresponding bins. In this paper, we deal with this problem by using the ratios between bin values of histograms, rather than bin values' differences which are used in the traditional histogram distances. We propose a bin ratio-based histogram distance (BRD), which is an intra-cross-bin distance, in contrast with previous bin-to-bin distances and cross-bin distances. The BRD is robust to partial matching and histogram normalization, and captures correlations between bins with only a linear computational complexity. We combine the BRD with the ℓ1 histogram distance and the χ(2) histogram distance to generate the ℓ1 BRD and the χ(2) BRD, respectively. These combinations exploit and benefit from the robustness of the BRD under partial matching and the robustness of the ℓ1 and χ(2) distances to small noise. We propose a method for assessing the robustness of histogram distances to partial matching. The BRDs and logistic regression-based histogram fusion are applied to image classification. The experimental results on synthetic data sets show the robustness of the BRDs to partial matching, and the experiments on seven benchmark data sets demonstrate promising results of the BRDs for image classification.

Large Margin Multi-Modal Multi-Task Feature Extraction for Image Classification.

PubMed

Yong Luo; Yonggang Wen; Dacheng Tao; Jie Gui; Chao Xu

2016-01-01

The features used in many image analysis-based applications are frequently of very high dimension. Feature extraction offers several advantages in high-dimensional cases, and many recent studies have used multi-task feature extraction approaches, which often outperform single-task feature extraction approaches. However, most of these methods are limited in that they only consider data represented by a single type of feature, even though features usually represent images from multiple modalities. We, therefore, propose a novel large margin multi-modal multi-task feature extraction (LM3FE) framework for handling multi-modal features for image classification. In particular, LM3FE simultaneously learns the feature extraction matrix for each modality and the modality combination coefficients. In this way, LM3FE not only handles correlated and noisy features, but also utilizes the complementarity of different modalities to further help reduce feature redundancy in each modality. The large margin principle employed also helps to extract strongly predictive features, so that they are more suitable for prediction (e.g., classification). An alternating algorithm is developed for problem optimization, and each subproblem can be efficiently solved. Experiments on two challenging real-world image data sets demonstrate the effectiveness and superiority of the proposed method.

FISH Finder: a high-throughput tool for analyzing FISH images

PubMed Central

Shirley, James W.; Ty, Sereyvathana; Takebayashi, Shin-ichiro; Liu, Xiuwen; Gilbert, David M.

2011-01-01

Motivation: Fluorescence in situ hybridization (FISH) is used to study the organization and the positioning of specific DNA sequences within the cell nucleus. Analyzing the data from FISH images is a tedious process that invokes an element of subjectivity. Automated FISH image analysis offers savings in time as well as gaining the benefit of objective data analysis. While several FISH image analysis software tools have been developed, they often use a threshold-based segmentation algorithm for nucleus segmentation. As fluorescence signal intensities can vary significantly from experiment to experiment, from cell to cell, and within a cell, threshold-based segmentation is inflexible and often insufficient for automatic image analysis, leading to additional manual segmentation and potential subjective bias. To overcome these problems, we developed a graphical software tool called FISH Finder to automatically analyze FISH images that vary significantly. By posing the nucleus segmentation as a classification problem, compound Bayesian classifier is employed so that contextual information is utilized, resulting in reliable classification and boundary extraction. This makes it possible to analyze FISH images efficiently and objectively without adjustment of input parameters. Additionally, FISH Finder was designed to analyze the distances between differentially stained FISH probes. Availability: FISH Finder is a standalone MATLAB application and platform independent software. The program is freely available from: http://code.google.com/p/fishfinder/downloads/list Contact: gilbert@bio.fsu.edu PMID:21310746

DOE Office of Scientific and Technical Information (OSTI.GOV)

Tokola, Ryan A; Mikkilineni, Aravind K; Boehnen, Chris Bensing

Despite being increasingly easy to acquire, 3D data is rarely used for face-based biometrics applications beyond identification. Recent work in image-based demographic biometrics has enjoyed much success, but these approaches suffer from the well-known limitations of 2D representations, particularly variations in illumination, texture, and pose, as well as a fundamental inability to describe 3D shape. This paper shows that simple 3D shape features in a face-based coordinate system are capable of representing many biometric attributes without problem-specific models or specialized domain knowledge. The same feature vector achieves impressive results for problems as diverse as age estimation, gender classification, and racemore » classification.« less

Machine processing of remotely sensed data; Proceedings of the Conference, Purdue University, West Lafayette, Ind., October 16-18, 1973

NASA Technical Reports Server (NTRS)

1973-01-01

Topics discussed include the management and processing of earth resources information, special-purpose processors for the machine processing of remotely sensed data, digital image registration by a mathematical programming technique, the use of remote-sensor data in land classification (in particular, the use of ERTS-1 multispectral scanning data), the use of remote-sensor data in geometrical transformations and mapping, earth resource measurement with the aid of ERTS-1 multispectral scanning data, the use of remote-sensor data in the classification of turbidity levels in coastal zones and in the identification of ecological anomalies, the problem of feature selection and the classification of objects in multispectral images, the estimation of proportions of certain categories of objects, and a number of special systems and techniques. Individual items are announced in this issue.

A necessary condition for applying MUSIC algorithm in limited-view inverse scattering problem

NASA Astrophysics Data System (ADS)

Park, Taehoon; Park, Won-Kwang

2015-09-01

Throughout various results of numerical simulations, it is well-known that MUltiple SIgnal Classification (MUSIC) algorithm can be applied in the limited-view inverse scattering problems. However, the application is somehow heuristic. In this contribution, we identify a necessary condition of MUSIC for imaging of collection of small, perfectly conducting cracks. This is based on the fact that MUSIC imaging functional can be represented as an infinite series of Bessel function of integer order of the first kind. Numerical experiments from noisy synthetic data supports our investigation.

Minimum Bayes risk image correlation

NASA Technical Reports Server (NTRS)

Minter, T. C., Jr.

1980-01-01

In this paper, the problem of designing a matched filter for image correlation will be treated as a statistical pattern recognition problem. It is shown that, by minimizing a suitable criterion, a matched filter can be estimated which approximates the optimum Bayes discriminant function in a least-squares sense. It is well known that the use of the Bayes discriminant function in target classification minimizes the Bayes risk, which in turn directly minimizes the probability of a false fix. A fast Fourier implementation of the minimum Bayes risk correlation procedure is described.

Computer-aided diagnostic approach of dermoscopy images acquiring relevant features

NASA Astrophysics Data System (ADS)

Castillejos-Fernández, H.; Franco-Arcega, A.; López-Ortega, O.

2016-09-01

In skin cancer detection, automated analysis of borders, colors, and structures of a lesion relies upon an accurate segmentation process and it is an important first step in any Computer-Aided Diagnosis (CAD) system. However, irregular and disperse lesion borders, low contrast, artifacts in images and variety of colors within the interest region make the problem difficult. In this paper, we propose an efficient approach of automatic classification which considers specific lesion features. First, for the selection of lesion skin we employ the segmentation algorithm W-FCM.1 Then, in the feature extraction stage we consider several aspects: the area of the lesion, which is calculated by correlating axes and we calculate the specific the value of asymmetry in both axes. For color analysis we employ an ensemble of clusterers including K-Means, Fuzzy K-Means and Kohonep maps, all of which estimate the presence of one or more colors defined in ABCD rule and the values for each of the segmented colors. Another aspect to consider is the type of structures that appear in the lesion Those are defined by using the ell-known GLCM method. During the classification stage we compare several methods in order to define if the lesion is benign or malignant. An important contribution of the current approach in segmentation-classification problem resides in the use of information from all color channels together, as well as the measure of each color in the lesion and the axes correlation. The segmentation and classification measures have been performed using sensibility, specificity, accuracy and AUC metric over a set of dermoscopy images from ISDIS data set

Multi-class texture analysis in colorectal cancer histology

NASA Astrophysics Data System (ADS)

Kather, Jakob Nikolas; Weis, Cleo-Aron; Bianconi, Francesco; Melchers, Susanne M.; Schad, Lothar R.; Gaiser, Timo; Marx, Alexander; Zöllner, Frank Gerrit

2016-06-01

Automatic recognition of different tissue types in histological images is an essential part in the digital pathology toolbox. Texture analysis is commonly used to address this problem; mainly in the context of estimating the tumour/stroma ratio on histological samples. However, although histological images typically contain more than two tissue types, only few studies have addressed the multi-class problem. For colorectal cancer, one of the most prevalent tumour types, there are in fact no published results on multiclass texture separation. In this paper we present a new dataset of 5,000 histological images of human colorectal cancer including eight different types of tissue. We used this set to assess the classification performance of a wide range of texture descriptors and classifiers. As a result, we found an optimal classification strategy that markedly outperformed traditional methods, improving the state of the art for tumour-stroma separation from 96.9% to 98.6% accuracy and setting a new standard for multiclass tissue separation (87.4% accuracy for eight classes). We make our dataset of histological images publicly available under a Creative Commons license and encourage other researchers to use it as a benchmark for their studies.

Integrating Human and Machine Intelligence in Galaxy Morphology Classification Tasks

NASA Astrophysics Data System (ADS)

Beck, Melanie Renee

The large flood of data flowing from observatories presents significant challenges to astronomy and cosmology--challenges that will only be magnified by projects currently under development. Growth in both volume and velocity of astrophysics data is accelerating: whereas the Sloan Digital Sky Survey (SDSS) has produced 60 terabytes of data in the last decade, the upcoming Large Synoptic Survey Telescope (LSST) plans to register 30 terabytes per night starting in the year 2020. Additionally, the Euclid Mission will acquire imaging for 5 x 107 resolvable galaxies. The field of galaxy evolution faces a particularly challenging future as complete understanding often cannot be reached without analysis of detailed morphological galaxy features. Historically, morphological analysis has relied on visual classification by astronomers, accessing the human brains capacity for advanced pattern recognition. However, this accurate but inefficient method falters when confronted with many thousands (or millions) of images. In the SDSS era, efforts to automate morphological classifications of galaxies (e.g., Conselice et al., 2000; Lotz et al., 2004) are reasonably successful and can distinguish between elliptical and disk-dominated galaxies with accuracies of 80%. While this is statistically very useful, a key problem with these methods is that they often cannot say which 80% of their samples are accurate. Furthermore, when confronted with the more complex task of identifying key substructure within galaxies, automated classification algorithms begin to fail. The Galaxy Zoo project uses a highly innovative approach to solving the scalability problem of visual classification. Displaying images of SDSS galaxies to volunteers via a simple and engaging web interface, www.galaxyzoo.org asks people to classify images by eye. Within the first year hundreds of thousands of members of the general public had classified each of the 1 million SDSS galaxies an average of 40 times. Galaxy Zoo thus solved both the visual classification problem of time efficiency and improved accuracy by producing a distribution of independent classifications for each galaxy. While crowd-sourced galaxy classifications have proven their worth, challenges remain before establishing this method as a critical and standard component of the data processing pipelines for the next generation of surveys. In particular, though innovative, crowd-sourcing techniques do not have the capacity to handle the data volume and rates expected in the next generation of surveys. These algorithms will be delegated to handle the majority of the classification tasks, freeing citizen scientists to contribute their efforts on subtler and more complex assignments. This thesis presents a solution through an integration of visual and automated classifications, preserving the best features of both human and machine. We demonstrate the effectiveness of such a system through a re-analysis of visual galaxy morphology classifications collected during the Galaxy Zoo 2 (GZ2) project. We reprocess the top-level question of the GZ2 decision tree with a Bayesian classification aggregation algorithm dubbed SWAP, originally developed for the Space Warps gravitational lens project. Through a simple binary classification scheme we increase the classification rate nearly 5-fold classifying 226,124 galaxies in 92 days of GZ2 project time while reproducing labels derived from GZ2 classification data with 95.7% accuracy. We next combine this with a Random Forest machine learning algorithm that learns on a suite of non-parametric morphology indicators widely used for automated morphologies. We develop a decision engine that delegates tasks between human and machine and demonstrate that the combined system provides a factor of 11.4 increase in the classification rate, classifying 210,803 galaxies in just 32 days of GZ2 project time with 93.1% accuracy. As the Random Forest algorithm requires a minimal amount of computational cost, this result has important implications for galaxy morphology identification tasks in the era of Euclid and other large-scale surveys.

A combined reconstruction-classification method for diffuse optical tomography.

PubMed

Hiltunen, P; Prince, S J D; Arridge, S

2009-11-07

We present a combined classification and reconstruction algorithm for diffuse optical tomography (DOT). DOT is a nonlinear ill-posed inverse problem. Therefore, some regularization is needed. We present a mixture of Gaussians prior, which regularizes the DOT reconstruction step. During each iteration, the parameters of a mixture model are estimated. These associate each reconstructed pixel with one of several classes based on the current estimate of the optical parameters. This classification is exploited to form a new prior distribution to regularize the reconstruction step and update the optical parameters. The algorithm can be described as an iteration between an optimization scheme with zeroth-order variable mean and variance Tikhonov regularization and an expectation-maximization scheme for estimation of the model parameters. We describe the algorithm in a general Bayesian framework. Results from simulated test cases and phantom measurements show that the algorithm enhances the contrast of the reconstructed images with good spatial accuracy. The probabilistic classifications of each image contain only a few misclassified pixels.

Pathological brain detection based on wavelet entropy and Hu moment invariants.

PubMed

Zhang, Yudong; Wang, Shuihua; Sun, Ping; Phillips, Preetha

2015-01-01

With the aim of developing an accurate pathological brain detection system, we proposed a novel automatic computer-aided diagnosis (CAD) to detect pathological brains from normal brains obtained by magnetic resonance imaging (MRI) scanning. The problem still remained a challenge for technicians and clinicians, since MR imaging generated an exceptionally large information dataset. A new two-step approach was proposed in this study. We used wavelet entropy (WE) and Hu moment invariants (HMI) for feature extraction, and the generalized eigenvalue proximal support vector machine (GEPSVM) for classification. To further enhance classification accuracy, the popular radial basis function (RBF) kernel was employed. The 10 runs of k-fold stratified cross validation result showed that the proposed "WE + HMI + GEPSVM + RBF" method was superior to existing methods w.r.t. classification accuracy. It obtained the average classification accuracies of 100%, 100%, and 99.45% over Dataset-66, Dataset-160, and Dataset-255, respectively. The proposed method is effective and can be applied to realistic use.

Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods

PubMed Central

Burlina, Philippe; Billings, Seth; Joshi, Neil

2017-01-01

Objective To evaluate the use of ultrasound coupled with machine learning (ML) and deep learning (DL) techniques for automated or semi-automated classification of myositis. Methods Eighty subjects comprised of 19 with inclusion body myositis (IBM), 14 with polymyositis (PM), 14 with dermatomyositis (DM), and 33 normal (N) subjects were included in this study, where 3214 muscle ultrasound images of 7 muscles (observed bilaterally) were acquired. We considered three problems of classification including (A) normal vs. affected (DM, PM, IBM); (B) normal vs. IBM patients; and (C) IBM vs. other types of myositis (DM or PM). We studied the use of an automated DL method using deep convolutional neural networks (DL-DCNNs) for diagnostic classification and compared it with a semi-automated conventional ML method based on random forests (ML-RF) and “engineered” features. We used the known clinical diagnosis as the gold standard for evaluating performance of muscle classification. Results The performance of the DL-DCNN method resulted in accuracies ± standard deviation of 76.2% ± 3.1% for problem (A), 86.6% ± 2.4% for (B) and 74.8% ± 3.9% for (C), while the ML-RF method led to accuracies of 72.3% ± 3.3% for problem (A), 84.3% ± 2.3% for (B) and 68.9% ± 2.5% for (C). Conclusions This study demonstrates the application of machine learning methods for automatically or semi-automatically classifying inflammatory muscle disease using muscle ultrasound. Compared to the conventional random forest machine learning method used here, which has the drawback of requiring manual delineation of muscle/fat boundaries, DCNN-based classification by and large improved the accuracies in all classification problems while providing a fully automated approach to classification. PMID:28854220

Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods.

PubMed

Burlina, Philippe; Billings, Seth; Joshi, Neil; Albayda, Jemima

2017-01-01

To evaluate the use of ultrasound coupled with machine learning (ML) and deep learning (DL) techniques for automated or semi-automated classification of myositis. Eighty subjects comprised of 19 with inclusion body myositis (IBM), 14 with polymyositis (PM), 14 with dermatomyositis (DM), and 33 normal (N) subjects were included in this study, where 3214 muscle ultrasound images of 7 muscles (observed bilaterally) were acquired. We considered three problems of classification including (A) normal vs. affected (DM, PM, IBM); (B) normal vs. IBM patients; and (C) IBM vs. other types of myositis (DM or PM). We studied the use of an automated DL method using deep convolutional neural networks (DL-DCNNs) for diagnostic classification and compared it with a semi-automated conventional ML method based on random forests (ML-RF) and "engineered" features. We used the known clinical diagnosis as the gold standard for evaluating performance of muscle classification. The performance of the DL-DCNN method resulted in accuracies ± standard deviation of 76.2% ± 3.1% for problem (A), 86.6% ± 2.4% for (B) and 74.8% ± 3.9% for (C), while the ML-RF method led to accuracies of 72.3% ± 3.3% for problem (A), 84.3% ± 2.3% for (B) and 68.9% ± 2.5% for (C). This study demonstrates the application of machine learning methods for automatically or semi-automatically classifying inflammatory muscle disease using muscle ultrasound. Compared to the conventional random forest machine learning method used here, which has the drawback of requiring manual delineation of muscle/fat boundaries, DCNN-based classification by and large improved the accuracies in all classification problems while providing a fully automated approach to classification.

Binary image classification

NASA Technical Reports Server (NTRS)

Morris, Carl N.

1987-01-01

Motivated by the LANDSAT problem of estimating the probability of crop or geological types based on multi-channel satellite imagery data, Morris and Kostal (1983), Hill, Hinkley, Kostal, and Morris (1984), and Morris, Hinkley, and Johnston (1985) developed an empirical Bayes approach to this problem. Here, researchers return to those developments, making certain improvements and extensions, but restricting attention to the binary case of only two attributes.

Design of partially supervised classifiers for multispectral image data

NASA Technical Reports Server (NTRS)

Jeon, Byeungwoo; Landgrebe, David

1993-01-01

A partially supervised classification problem is addressed, especially when the class definition and corresponding training samples are provided a priori only for just one particular class. In practical applications of pattern classification techniques, a frequently observed characteristic is the heavy, often nearly impossible requirements on representative prior statistical class characteristics of all classes in a given data set. Considering the effort in both time and man-power required to have a well-defined, exhaustive list of classes with a corresponding representative set of training samples, this 'partially' supervised capability would be very desirable, assuming adequate classifier performance can be obtained. Two different classification algorithms are developed to achieve simplicity in classifier design by reducing the requirement of prior statistical information without sacrificing significant classifying capability. The first one is based on optimal significance testing, where the optimal acceptance probability is estimated directly from the data set. In the second approach, the partially supervised classification is considered as a problem of unsupervised clustering with initially one known cluster or class. A weighted unsupervised clustering procedure is developed to automatically define other classes and estimate their class statistics. The operational simplicity thus realized should make these partially supervised classification schemes very viable tools in pattern classification.

Tongue Images Classification Based on Constrained High Dispersal Network.

PubMed

Meng, Dan; Cao, Guitao; Duan, Ye; Zhu, Minghua; Tu, Liping; Xu, Dong; Xu, Jiatuo

2017-01-01

Computer aided tongue diagnosis has a great potential to play important roles in traditional Chinese medicine (TCM). However, the majority of the existing tongue image analyses and classification methods are based on the low-level features, which may not provide a holistic view of the tongue. Inspired by deep convolutional neural network (CNN), we propose a novel feature extraction framework called constrained high dispersal neural networks (CHDNet) to extract unbiased features and reduce human labor for tongue diagnosis in TCM. Previous CNN models have mostly focused on learning convolutional filters and adapting weights between them, but these models have two major issues: redundancy and insufficient capability in handling unbalanced sample distribution. We introduce high dispersal and local response normalization operation to address the issue of redundancy. We also add multiscale feature analysis to avoid the problem of sensitivity to deformation. Our proposed CHDNet learns high-level features and provides more classification information during training time, which may result in higher accuracy when predicting testing samples. We tested the proposed method on a set of 267 gastritis patients and a control group of 48 healthy volunteers. Test results show that CHDNet is a promising method in tongue image classification for the TCM study.

Defect detection and classification of galvanized stamping parts based on fully convolution neural network

NASA Astrophysics Data System (ADS)

Xiao, Zhitao; Leng, Yanyi; Geng, Lei; Xi, Jiangtao

2018-04-01

In this paper, a new convolution neural network method is proposed for the inspection and classification of galvanized stamping parts. Firstly, all workpieces are divided into normal and defective by image processing, and then the defective workpieces extracted from the region of interest (ROI) area are input to the trained fully convolutional networks (FCN). The network utilizes an end-to-end and pixel-to-pixel training convolution network that is currently the most advanced technology in semantic segmentation, predicts result of each pixel. Secondly, we mark the different pixel values of the workpiece, defect and background for the training image, and use the pixel value and the number of pixels to realize the recognition of the defects of the output picture. Finally, the defect area's threshold depended on the needs of the project is set to achieve the specific classification of the workpiece. The experiment results show that the proposed method can successfully achieve defect detection and classification of galvanized stamping parts under ordinary camera and illumination conditions, and its accuracy can reach 99.6%. Moreover, it overcomes the problem of complex image preprocessing and difficult feature extraction and performs better adaptability.

Image segmentation using hidden Markov Gauss mixture models.

PubMed

Pyun, Kyungsuk; Lim, Johan; Won, Chee Sun; Gray, Robert M

2007-07-01

Image segmentation is an important tool in image processing and can serve as an efficient front end to sophisticated algorithms and thereby simplify subsequent processing. We develop a multiclass image segmentation method using hidden Markov Gauss mixture models (HMGMMs) and provide examples of segmentation of aerial images and textures. HMGMMs incorporate supervised learning, fitting the observation probability distribution given each class by a Gauss mixture estimated using vector quantization with a minimum discrimination information (MDI) distortion. We formulate the image segmentation problem using a maximum a posteriori criteria and find the hidden states that maximize the posterior density given the observation. We estimate both the hidden Markov parameter and hidden states using a stochastic expectation-maximization algorithm. Our results demonstrate that HMGMM provides better classification in terms of Bayes risk and spatial homogeneity of the classified objects than do several popular methods, including classification and regression trees, learning vector quantization, causal hidden Markov models (HMMs), and multiresolution HMMs. The computational load of HMGMM is similar to that of the causal HMM.

Super-Resolution of Plant Disease Images for the Acceleration of Image-based Phenotyping and Vigor Diagnosis in Agriculture.

PubMed

Yamamoto, Kyosuke; Togami, Takashi; Yamaguchi, Norio

2017-11-06

Unmanned aerial vehicles (UAVs or drones) are a very promising branch of technology, and they have been utilized in agriculture-in cooperation with image processing technologies-for phenotyping and vigor diagnosis. One of the problems in the utilization of UAVs for agricultural purposes is the limitation in flight time. It is necessary to fly at a high altitude to capture the maximum number of plants in the limited time available, but this reduces the spatial resolution of the captured images. In this study, we applied a super-resolution method to the low-resolution images of tomato diseases to recover detailed appearances, such as lesions on plant organs. We also conducted disease classification using high-resolution, low-resolution, and super-resolution images to evaluate the effectiveness of super-resolution methods in disease classification. Our results indicated that the super-resolution method outperformed conventional image scaling methods in spatial resolution enhancement of tomato disease images. The results of disease classification showed that the accuracy attained was also better by a large margin with super-resolution images than with low-resolution images. These results indicated that our approach not only recovered the information lost in low-resolution images, but also exerted a beneficial influence on further image analysis. The proposed approach will accelerate image-based phenotyping and vigor diagnosis in the field, because it not only saves time to capture images of a crop in a cultivation field but also secures the accuracy of these images for further analysis.

Super-Resolution of Plant Disease Images for the Acceleration of Image-based Phenotyping and Vigor Diagnosis in Agriculture

PubMed Central

Togami, Takashi; Yamaguchi, Norio

2017-01-01

Unmanned aerial vehicles (UAVs or drones) are a very promising branch of technology, and they have been utilized in agriculture—in cooperation with image processing technologies—for phenotyping and vigor diagnosis. One of the problems in the utilization of UAVs for agricultural purposes is the limitation in flight time. It is necessary to fly at a high altitude to capture the maximum number of plants in the limited time available, but this reduces the spatial resolution of the captured images. In this study, we applied a super-resolution method to the low-resolution images of tomato diseases to recover detailed appearances, such as lesions on plant organs. We also conducted disease classification using high-resolution, low-resolution, and super-resolution images to evaluate the effectiveness of super-resolution methods in disease classification. Our results indicated that the super-resolution method outperformed conventional image scaling methods in spatial resolution enhancement of tomato disease images. The results of disease classification showed that the accuracy attained was also better by a large margin with super-resolution images than with low-resolution images. These results indicated that our approach not only recovered the information lost in low-resolution images, but also exerted a beneficial influence on further image analysis. The proposed approach will accelerate image-based phenotyping and vigor diagnosis in the field, because it not only saves time to capture images of a crop in a cultivation field but also secures the accuracy of these images for further analysis. PMID:29113104

A Multi-modal, Discriminative and Spatially Invariant CNN for RGB-D Object Labeling.

PubMed

Asif, Umar; Bennamoun, Mohammed; Sohel, Ferdous

2017-08-30

While deep convolutional neural networks have shown a remarkable success in image classification, the problems of inter-class similarities, intra-class variances, the effective combination of multimodal data, and the spatial variability in images of objects remain to be major challenges. To address these problems, this paper proposes a novel framework to learn a discriminative and spatially invariant classification model for object and indoor scene recognition using multimodal RGB-D imagery. This is achieved through three postulates: 1) spatial invariance - this is achieved by combining a spatial transformer network with a deep convolutional neural network to learn features which are invariant to spatial translations, rotations, and scale changes, 2) high discriminative capability - this is achieved by introducing Fisher encoding within the CNN architecture to learn features which have small inter-class similarities and large intra-class compactness, and 3) multimodal hierarchical fusion - this is achieved through the regularization of semantic segmentation to a multi-modal CNN architecture, where class probabilities are estimated at different hierarchical levels (i.e., imageand pixel-levels), and fused into a Conditional Random Field (CRF)- based inference hypothesis, the optimization of which produces consistent class labels in RGB-D images. Extensive experimental evaluations on RGB-D object and scene datasets, and live video streams (acquired from Kinect) show that our framework produces superior object and scene classification results compared to the state-of-the-art methods.

Covert photo classification by fusing image features and visual attributes.

PubMed

Lang, Haitao; Ling, Haibin

2015-10-01

In this paper, we study a novel problem of classifying covert photos, whose acquisition processes are intentionally concealed from the subjects being photographed. Covert photos are often privacy invasive and, if distributed over Internet, can cause serious consequences. Automatic identification of such photos, therefore, serves as an important initial step toward further privacy protection operations. The problem is, however, very challenging due to the large semantic similarity between covert and noncovert photos, the enormous diversity in the photographing process and environment of cover photos, and the difficulty to collect an effective data set for the study. Attacking these challenges, we make three consecutive contributions. First, we collect a large data set containing 2500 covert photos, each of them is verified rigorously and carefully. Second, we conduct a user study on how humans distinguish covert photos from noncovert ones. The user study not only provides an important evaluation baseline, but also suggests fusing heterogeneous information for an automatic solution. Our third contribution is a covert photo classification algorithm that fuses various image features and visual attributes in the multiple kernel learning framework. We evaluate the proposed approach on the collected data set in comparison with other modern image classifiers. The results show that our approach achieves an average classification rate (1-EER) of 0.8940, which significantly outperforms other competitors as well as human's performance.

Prostate segmentation by sparse representation based classification

PubMed Central

Gao, Yaozong; Liao, Shu; Shen, Dinggang

2012-01-01

Purpose: The segmentation of prostate in CT images is of essential importance to external beam radiotherapy, which is one of the major treatments for prostate cancer nowadays. During the radiotherapy, the prostate is radiated by high-energy x rays from different directions. In order to maximize the dose to the cancer and minimize the dose to the surrounding healthy tissues (e.g., bladder and rectum), the prostate in the new treatment image needs to be accurately localized. Therefore, the effectiveness and efficiency of external beam radiotherapy highly depend on the accurate localization of the prostate. However, due to the low contrast of the prostate with its surrounding tissues (e.g., bladder), the unpredicted prostate motion, and the large appearance variations across different treatment days, it is challenging to segment the prostate in CT images. In this paper, the authors present a novel classification based segmentation method to address these problems. Methods: To segment the prostate, the proposed method first uses sparse representation based classification (SRC) to enhance the prostate in CT images by pixel-wise classification, in order to overcome the limitation of poor contrast of the prostate images. Then, based on the classification results, previous segmented prostates of the same patient are used as patient-specific atlases to align onto the current treatment image and the majority voting strategy is finally adopted to segment the prostate. In order to address the limitations of the traditional SRC in pixel-wise classification, especially for the purpose of segmentation, the authors extend SRC from the following four aspects: (1) A discriminant subdictionary learning method is proposed to learn a discriminant and compact representation of training samples for each class so that the discriminant power of SRC can be increased and also SRC can be applied to the large-scale pixel-wise classification. (2) The L1 regularized sparse coding is replaced by the elastic net in order to obtain a smooth and clear prostate boundary in the classification result. (3) Residue-based linear regression is incorporated to improve the classification performance and to extend SRC from hard classification to soft classification. (4) Iterative SRC is proposed by using context information to iteratively refine the classification results. Results: The proposed method has been comprehensively evaluated on a dataset consisting of 330 CT images from 24 patients. The effectiveness of the extended SRC has been validated by comparing it with the traditional SRC based on the proposed four extensions. The experimental results show that our extended SRC can obtain not only more accurate classification results but also smoother and clearer prostate boundary than the traditional SRC. Besides, the comparison with other five state-of-the-art prostate segmentation methods indicates that our method can achieve better performance than other methods under comparison. Conclusions: The authors have proposed a novel prostate segmentation method based on the sparse representation based classification, which can achieve considerably accurate segmentation results in CT prostate segmentation. PMID:23039673

Prostate segmentation by sparse representation based classification.

PubMed

Gao, Yaozong; Liao, Shu; Shen, Dinggang

2012-10-01

The segmentation of prostate in CT images is of essential importance to external beam radiotherapy, which is one of the major treatments for prostate cancer nowadays. During the radiotherapy, the prostate is radiated by high-energy x rays from different directions. In order to maximize the dose to the cancer and minimize the dose to the surrounding healthy tissues (e.g., bladder and rectum), the prostate in the new treatment image needs to be accurately localized. Therefore, the effectiveness and efficiency of external beam radiotherapy highly depend on the accurate localization of the prostate. However, due to the low contrast of the prostate with its surrounding tissues (e.g., bladder), the unpredicted prostate motion, and the large appearance variations across different treatment days, it is challenging to segment the prostate in CT images. In this paper, the authors present a novel classification based segmentation method to address these problems. To segment the prostate, the proposed method first uses sparse representation based classification (SRC) to enhance the prostate in CT images by pixel-wise classification, in order to overcome the limitation of poor contrast of the prostate images. Then, based on the classification results, previous segmented prostates of the same patient are used as patient-specific atlases to align onto the current treatment image and the majority voting strategy is finally adopted to segment the prostate. In order to address the limitations of the traditional SRC in pixel-wise classification, especially for the purpose of segmentation, the authors extend SRC from the following four aspects: (1) A discriminant subdictionary learning method is proposed to learn a discriminant and compact representation of training samples for each class so that the discriminant power of SRC can be increased and also SRC can be applied to the large-scale pixel-wise classification. (2) The L1 regularized sparse coding is replaced by the elastic net in order to obtain a smooth and clear prostate boundary in the classification result. (3) Residue-based linear regression is incorporated to improve the classification performance and to extend SRC from hard classification to soft classification. (4) Iterative SRC is proposed by using context information to iteratively refine the classification results. The proposed method has been comprehensively evaluated on a dataset consisting of 330 CT images from 24 patients. The effectiveness of the extended SRC has been validated by comparing it with the traditional SRC based on the proposed four extensions. The experimental results show that our extended SRC can obtain not only more accurate classification results but also smoother and clearer prostate boundary than the traditional SRC. Besides, the comparison with other five state-of-the-art prostate segmentation methods indicates that our method can achieve better performance than other methods under comparison. The authors have proposed a novel prostate segmentation method based on the sparse representation based classification, which can achieve considerably accurate segmentation results in CT prostate segmentation.

Filtering Based Adaptive Visual Odometry Sensor Framework Robust to Blurred Images

PubMed Central

Zhao, Haiying; Liu, Yong; Xie, Xiaojia; Liao, Yiyi; Liu, Xixi

2016-01-01

Visual odometry (VO) estimation from blurred image is a challenging problem in practical robot applications, and the blurred images will severely reduce the estimation accuracy of the VO. In this paper, we address the problem of visual odometry estimation from blurred images, and present an adaptive visual odometry estimation framework robust to blurred images. Our approach employs an objective measure of images, named small image gradient distribution (SIGD), to evaluate the blurring degree of the image, then an adaptive blurred image classification algorithm is proposed to recognize the blurred images, finally we propose an anti-blurred key-frame selection algorithm to enable the VO robust to blurred images. We also carried out varied comparable experiments to evaluate the performance of the VO algorithms with our anti-blur framework under varied blurred images, and the experimental results show that our approach can achieve superior performance comparing to the state-of-the-art methods under the condition with blurred images while not increasing too much computation cost to the original VO algorithms. PMID:27399704

Breast tissue classification in digital tomosynthesis images based on global gradient minimization and texture features

NASA Astrophysics Data System (ADS)

Qin, Xulei; Lu, Guolan; Sechopoulos, Ioannis; Fei, Baowei

2014-03-01

Digital breast tomosynthesis (DBT) is a pseudo-three-dimensional x-ray imaging modality proposed to decrease the effect of tissue superposition present in mammography, potentially resulting in an increase in clinical performance for the detection and diagnosis of breast cancer. Tissue classification in DBT images can be useful in risk assessment, computer-aided detection and radiation dosimetry, among other aspects. However, classifying breast tissue in DBT is a challenging problem because DBT images include complicated structures, image noise, and out-of-plane artifacts due to limited angular tomographic sampling. In this project, we propose an automatic method to classify fatty and glandular tissue in DBT images. First, the DBT images are pre-processed to enhance the tissue structures and to decrease image noise and artifacts. Second, a global smooth filter based on L0 gradient minimization is applied to eliminate detailed structures and enhance large-scale ones. Third, the similar structure regions are extracted and labeled by fuzzy C-means (FCM) classification. At the same time, the texture features are also calculated. Finally, each region is classified into different tissue types based on both intensity and texture features. The proposed method is validated using five patient DBT images using manual segmentation as the gold standard. The Dice scores and the confusion matrix are utilized to evaluate the classified results. The evaluation results demonstrated the feasibility of the proposed method for classifying breast glandular and fat tissue on DBT images.

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning

PubMed Central

Wang, Shuihua; Yang, Ming; Du, Sidan; Yang, Jiquan; Liu, Bin; Gorriz, Juan M.; Ramírez, Javier; Yuan, Ti-Fei; Zhang, Yudong

2016-01-01

Highlights We develop computer-aided diagnosis system for unilateral hearing loss detection in structural magnetic resonance imaging.Wavelet entropy is introduced to extract image global features from brain images. Directed acyclic graph is employed to endow support vector machine an ability to handle multi-class problems.The developed computer-aided diagnosis system achieves an overall accuracy of 95.1% for this three-class problem of differentiating left-sided and right-sided hearing loss from healthy controls. Aim: Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way. Materials: We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC). Method: We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM). Results: The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier. Conclusions: This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss. PMID:27807415

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning.

PubMed

Wang, Shuihua; Yang, Ming; Du, Sidan; Yang, Jiquan; Liu, Bin; Gorriz, Juan M; Ramírez, Javier; Yuan, Ti-Fei; Zhang, Yudong

2016-01-01

Highlights We develop computer-aided diagnosis system for unilateral hearing loss detection in structural magnetic resonance imaging.Wavelet entropy is introduced to extract image global features from brain images. Directed acyclic graph is employed to endow support vector machine an ability to handle multi-class problems.The developed computer-aided diagnosis system achieves an overall accuracy of 95.1% for this three-class problem of differentiating left-sided and right-sided hearing loss from healthy controls. Aim: Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way. Materials: We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC). Method: We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM). Results: The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier. Conclusions: This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss.

Texture Descriptors Ensembles Enable Image-Based Classification of Maturation of Human Stem Cell-Derived Retinal Pigmented Epithelium

PubMed Central

Caetano dos Santos, Florentino Luciano; Skottman, Heli; Juuti-Uusitalo, Kati; Hyttinen, Jari

2016-01-01

Aims A fast, non-invasive and observer-independent method to analyze the homogeneity and maturity of human pluripotent stem cell (hPSC) derived retinal pigment epithelial (RPE) cells is warranted to assess the suitability of hPSC-RPE cells for implantation or in vitro use. The aim of this work was to develop and validate methods to create ensembles of state-of-the-art texture descriptors and to provide a robust classification tool to separate three different maturation stages of RPE cells by using phase contrast microscopy images. The same methods were also validated on a wide variety of biological image classification problems, such as histological or virus image classification. Methods For image classification we used different texture descriptors, descriptor ensembles and preprocessing techniques. Also, three new methods were tested. The first approach was an ensemble of preprocessing methods, to create an additional set of images. The second was the region-based approach, where saliency detection and wavelet decomposition divide each image in two different regions, from which features were extracted through different descriptors. The third method was an ensemble of Binarized Statistical Image Features, based on different sizes and thresholds. A Support Vector Machine (SVM) was trained for each descriptor histogram and the set of SVMs combined by sum rule. The accuracy of the computer vision tool was verified in classifying the hPSC-RPE cell maturation level. Dataset and Results The RPE dataset contains 1862 subwindows from 195 phase contrast images. The final descriptor ensemble outperformed the most recent stand-alone texture descriptors, obtaining, for the RPE dataset, an area under ROC curve (AUC) of 86.49% with the 10-fold cross validation and 91.98% with the leave-one-image-out protocol. The generality of the three proposed approaches was ascertained with 10 more biological image datasets, obtaining an average AUC greater than 97%. Conclusions Here we showed that the developed ensembles of texture descriptors are able to classify the RPE cell maturation stage. Moreover, we proved that preprocessing and region-based decomposition improves many descriptors’ accuracy in biological dataset classification. Finally, we built the first public dataset of stem cell-derived RPE cells, which is publicly available to the scientific community for classification studies. The proposed tool is available at https://www.dei.unipd.it/node/2357 and the RPE dataset at http://www.biomeditech.fi/data/RPE_dataset/. Both are available at https://figshare.com/s/d6fb591f1beb4f8efa6f. PMID:26895509

Gold-standard for computer-assisted morphological sperm analysis.

PubMed

Chang, Violeta; Garcia, Alejandra; Hitschfeld, Nancy; Härtel, Steffen

2017-04-01

Published algorithms for classification of human sperm heads are based on relatively small image databases that are not open to the public, and thus no direct comparison is available for competing methods. We describe a gold-standard for morphological sperm analysis (SCIAN-MorphoSpermGS), a dataset of sperm head images with expert-classification labels in one of the following classes: normal, tapered, pyriform, small or amorphous. This gold-standard is for evaluating and comparing known techniques and future improvements to present approaches for classification of human sperm heads for semen analysis. Although this paper does not provide a computational tool for morphological sperm analysis, we present a set of experiments for comparing sperm head description and classification common techniques. This classification base-line is aimed to be used as a reference for future improvements to present approaches for human sperm head classification. The gold-standard provides a label for each sperm head, which is achieved by majority voting among experts. The classification base-line compares four supervised learning methods (1- Nearest Neighbor, naive Bayes, decision trees and Support Vector Machine (SVM)) and three shape-based descriptors (Hu moments, Zernike moments and Fourier descriptors), reporting the accuracy and the true positive rate for each experiment. We used Fleiss' Kappa Coefficient to evaluate the inter-expert agreement and Fisher's exact test for inter-expert variability and statistical significant differences between descriptors and learning techniques. Our results confirm the high degree of inter-expert variability in the morphological sperm analysis. Regarding the classification base line, we show that none of the standard descriptors or classification approaches is best suitable for tackling the problem of sperm head classification. We discovered that the correct classification rate was highly variable when trying to discriminate among non-normal sperm heads. By using the Fourier descriptor and SVM, we achieved the best mean correct classification: only 49%. We conclude that the SCIAN-MorphoSpermGS will provide a standard tool for evaluation of characterization and classification approaches for human sperm heads. Indeed, there is a clear need for a specific shape-based descriptor for human sperm heads and a specific classification approach to tackle the problem of high variability within subcategories of abnormal sperm cells. Copyright © 2017 Elsevier Ltd. All rights reserved.

Influence of Texture and Colour in Breast TMA Classification

PubMed Central

Fernández-Carrobles, M. Milagro; Bueno, Gloria; Déniz, Oscar; Salido, Jesús; García-Rojo, Marcial; González-López, Lucía

2015-01-01

Breast cancer diagnosis is still done by observation of biopsies under the microscope. The development of automated methods for breast TMA classification would reduce diagnostic time. This paper is a step towards the solution for this problem and shows a complete study of breast TMA classification based on colour models and texture descriptors. The TMA images were divided into four classes: i) benign stromal tissue with cellularity, ii) adipose tissue, iii) benign and benign anomalous structures, and iv) ductal and lobular carcinomas. A relevant set of features was obtained on eight different colour models from first and second order Haralick statistical descriptors obtained from the intensity image, Fourier, Wavelets, Multiresolution Gabor, M-LBP and textons descriptors. Furthermore, four types of classification experiments were performed using six different classifiers: (1) classification per colour model individually, (2) classification by combination of colour models, (3) classification by combination of colour models and descriptors, and (4) classification by combination of colour models and descriptors with a previous feature set reduction. The best result shows an average of 99.05% accuracy and 98.34% positive predictive value. These results have been obtained by means of a bagging tree classifier with combination of six colour models and the use of 1719 non-correlated (correlation threshold of 97%) textural features based on Statistical, M-LBP, Gabor and Spatial textons descriptors. PMID:26513238

Boosting bonsai trees for handwritten/printed text discrimination

NASA Astrophysics Data System (ADS)

Ricquebourg, Yann; Raymond, Christian; Poirriez, Baptiste; Lemaitre, Aurélie; Coüasnon, Bertrand

2013-12-01

Boosting over decision-stumps proved its efficiency in Natural Language Processing essentially with symbolic features, and its good properties (fast, few and not critical parameters, not sensitive to over-fitting) could be of great interest in the numeric world of pixel images. In this article we investigated the use of boosting over small decision trees, in image classification processing, for the discrimination of handwritten/printed text. Then, we conducted experiments to compare it to usual SVM-based classification revealing convincing results with very close performance, but with faster predictions and behaving far less as a black-box. Those promising results tend to make use of this classifier in more complex recognition tasks like multiclass problems.

Designing a training tool for imaging mental models

NASA Technical Reports Server (NTRS)

Dede, Christopher J.; Jayaram, Geetha

1990-01-01

The training process can be conceptualized as the student acquiring an evolutionary sequence of classification-problem solving mental models. For example a physician learns (1) classification systems for patient symptoms, diagnostic procedures, diseases, and therapeutic interventions and (2) interrelationships among these classifications (e.g., how to use diagnostic procedures to collect data about a patient's symptoms in order to identify the disease so that therapeutic measures can be taken. This project developed functional specifications for a computer-based tool, Mental Link, that allows the evaluative imaging of such mental models. The fundamental design approach underlying this representational medium is traversal of virtual cognition space. Typically intangible cognitive entities and links among them are visible as a three-dimensional web that represents a knowledge structure. The tool has a high degree of flexibility and customizability to allow extension to other types of uses, such a front-end to an intelligent tutoring system, knowledge base, hypermedia system, or semantic network.

Directional Multi-scale Modeling of High-Resolution Computed Tomography (HRCT) Lung Images for Diffuse Lung Disease Classification

NASA Astrophysics Data System (ADS)

Vo, Kiet T.; Sowmya, Arcot

A directional multi-scale modeling scheme based on wavelet and contourlet transforms is employed to describe HRCT lung image textures for classifying four diffuse lung disease patterns: normal, emphysema, ground glass opacity (GGO) and honey-combing. Generalized Gaussian density parameters are used to represent the detail sub-band features obtained by wavelet and contourlet transforms. In addition, support vector machines (SVMs) with excellent performance in a variety of pattern classification problems are used as classifier. The method is tested on a collection of 89 slices from 38 patients, each slice of size 512x512, 16 bits/pixel in DICOM format. The dataset contains 70,000 ROIs of those slices marked by experienced radiologists. We employ this technique at different wavelet and contourlet transform scales for diffuse lung disease classification. The technique presented here has best overall sensitivity 93.40% and specificity 98.40%.

A semi-automated image analysis procedure for in situ plankton imaging systems.

PubMed

Bi, Hongsheng; Guo, Zhenhua; Benfield, Mark C; Fan, Chunlei; Ford, Michael; Shahrestani, Suzan; Sieracki, Jeffery M

2015-01-01

Plankton imaging systems are capable of providing fine-scale observations that enhance our understanding of key physical and biological processes. However, processing the large volumes of data collected by imaging systems remains a major obstacle for their employment, and existing approaches are designed either for images acquired under laboratory controlled conditions or within clear waters. In the present study, we developed a semi-automated approach to analyze plankton taxa from images acquired by the ZOOplankton VISualization (ZOOVIS) system within turbid estuarine waters, in Chesapeake Bay. When compared to images under laboratory controlled conditions or clear waters, images from highly turbid waters are often of relatively low quality and more variable, due to the large amount of objects and nonlinear illumination within each image. We first customized a segmentation procedure to locate objects within each image and extracted them for classification. A maximally stable extremal regions algorithm was applied to segment large gelatinous zooplankton and an adaptive threshold approach was developed to segment small organisms, such as copepods. Unlike the existing approaches for images acquired from laboratory, controlled conditions or clear waters, the target objects are often the majority class, and the classification can be treated as a multi-class classification problem. We customized a two-level hierarchical classification procedure using support vector machines to classify the target objects (< 5%), and remove the non-target objects (> 95%). First, histograms of oriented gradients feature descriptors were constructed for the segmented objects. In the first step all non-target and target objects were classified into different groups: arrow-like, copepod-like, and gelatinous zooplankton. Each object was passed to a group-specific classifier to remove most non-target objects. After the object was classified, an expert or non-expert then manually removed the non-target objects that could not be removed by the procedure. The procedure was tested on 89,419 images collected in Chesapeake Bay, and results were consistent with visual counts with >80% accuracy for all three groups.

A Semi-Automated Image Analysis Procedure for In Situ Plankton Imaging Systems

PubMed Central

Bi, Hongsheng; Guo, Zhenhua; Benfield, Mark C.; Fan, Chunlei; Ford, Michael; Shahrestani, Suzan; Sieracki, Jeffery M.

2015-01-01

Plankton imaging systems are capable of providing fine-scale observations that enhance our understanding of key physical and biological processes. However, processing the large volumes of data collected by imaging systems remains a major obstacle for their employment, and existing approaches are designed either for images acquired under laboratory controlled conditions or within clear waters. In the present study, we developed a semi-automated approach to analyze plankton taxa from images acquired by the ZOOplankton VISualization (ZOOVIS) system within turbid estuarine waters, in Chesapeake Bay. When compared to images under laboratory controlled conditions or clear waters, images from highly turbid waters are often of relatively low quality and more variable, due to the large amount of objects and nonlinear illumination within each image. We first customized a segmentation procedure to locate objects within each image and extracted them for classification. A maximally stable extremal regions algorithm was applied to segment large gelatinous zooplankton and an adaptive threshold approach was developed to segment small organisms, such as copepods. Unlike the existing approaches for images acquired from laboratory, controlled conditions or clear waters, the target objects are often the majority class, and the classification can be treated as a multi-class classification problem. We customized a two-level hierarchical classification procedure using support vector machines to classify the target objects (< 5%), and remove the non-target objects (> 95%). First, histograms of oriented gradients feature descriptors were constructed for the segmented objects. In the first step all non-target and target objects were classified into different groups: arrow-like, copepod-like, and gelatinous zooplankton. Each object was passed to a group-specific classifier to remove most non-target objects. After the object was classified, an expert or non-expert then manually removed the non-target objects that could not be removed by the procedure. The procedure was tested on 89,419 images collected in Chesapeake Bay, and results were consistent with visual counts with >80% accuracy for all three groups. PMID:26010260

The application of remote sensing image sea ice monitoring method in Bohai Bay based on C4.5 decision tree algorithm

NASA Astrophysics Data System (ADS)

Ye, Wei; Song, Wei

2018-02-01

In The Paper, the remote sensing monitoring of sea ice problem was turned into a classification problem in data mining. Based on the statistic of the related band data of HJ1B remote sensing images, the main bands of HJ1B images related with the reflectance of seawater and sea ice were found. On the basis, the decision tree rules for sea ice monitoring were constructed by the related bands found above, and then the rules were applied to Liaodong Bay area seriously covered by sea ice for sea ice monitoring. The result proved that the method is effective.

Less is More: Bigger Data from Compressive Measurements

DOE Office of Scientific and Technical Information (OSTI.GOV)

Stevens, Andrew; Browning, Nigel D.

Compressive sensing approaches are beginning to take hold in (scanning) transmission electron microscopy (S/TEM) [1,2,3]. Compressive sensing is a mathematical theory about acquiring signals in a compressed form (measurements) and the probability of recovering the original signal by solving an inverse problem [4]. The inverse problem is underdetermined (more unknowns than measurements), so it is not obvious that recovery is possible. Compression is achieved by taking inner products of the signal with measurement weight vectors. Both Gaussian random weights and Bernoulli (0,1) random weights form a large class of measurement vectors for which recovery is possible. The measurements can alsomore » be designed through an optimization process. The key insight for electron microscopists is that compressive sensing can be used to increase acquisition speed and reduce dose. Building on work initially developed for optical cameras, this new paradigm will allow electron microscopists to solve more problems in the engineering and life sciences. We will be collecting orders of magnitude more data than previously possible. The reason that we will have more data is because we will have increased temporal/spatial/spectral sampling rates, and we will be able ability to interrogate larger classes of samples that were previously too beam sensitive to survive the experiment. For example consider an in-situ experiment that takes 1 minute. With traditional sensing, we might collect 5 images per second for a total of 300 images. With compressive sensing, each of those 300 images can be expanded into 10 more images, making the collection rate 50 images per second, and the decompressed data a total of 3000 images [3]. But, what are the implications, in terms of data, for this new methodology? Acquisition of compressed data will require downstream reconstruction to be useful. The reconstructed data will be much larger than traditional data, we will need space to store the reconstructions during analysis, and the computational demands for analysis will be higher. Moreover, there will be time costs associated with reconstruction. Deep learning [5] is an approach to address these problems. Deep learning is a hierarchical approach to find useful (for a particular task) representations of data. Each layer of the hierarchy is intended to represent higher levels of abstraction. For example, a deep model of faces might have sinusoids, edges and gradients in the first layer; eyes, noses, and mouths in the second layer, and faces in the third layer. There has been significant effort recently in deep learning algorithms for tasks beyond image classification such as compressive reconstruction [6] and image segmentation [7]. A drawback of deep learning, however, is that training the model requires large datasets and dedicated computational resources (to reduce training time to a few days). A second issue is that deep learning is not user-friendly and the meaning behind the results is usually not interpretable. We have shown it is possible to reduce the data set size while maintaining model quality [8] and developed interpretable models for image classification [9], but the demands are still significant. The key to addressing these problems is to NOT reconstruct the data. Instead, we should design computational sensors that give answers to specific problems. A simple version of this idea is compressive classification [10], where the goal is to classify signal type from a small number of compressed measurements. Classification is a much simpler problem than reconstruction, so 1) much fewer measurements will be necessary, and 2) these measurements will probably not be useful for reconstruction. Other simple examples of computational sensing include determining object volume or the number of objects present in the field of view [11].« less

Classification of cancerous cells based on the one-class problem approach

NASA Astrophysics Data System (ADS)

Murshed, Nabeel A.; Bortolozzi, Flavio; Sabourin, Robert

1996-03-01

One of the most important factors in reducing the effect of cancerous diseases is the early diagnosis, which requires a good and a robust method. With the advancement of computer technologies and digital image processing, the development of a computer-based system has become feasible. In this paper, we introduce a new approach for the detection of cancerous cells. This approach is based on the one-class problem approach, through which the classification system need only be trained with patterns of cancerous cells. This reduces the burden of the training task by about 50%. Based on this approach, a computer-based classification system is developed, based on the Fuzzy ARTMAP neural networks. Experimental results were performed using a set of 542 patterns taken from a sample of breast cancer. Results of the experiment show 98% correct identification of cancerous cells and 95% correct identification of non-cancerous cells.

Hyperspectral face recognition with spatiospectral information fusion and PLS regression.

PubMed

Uzair, Muhammad; Mahmood, Arif; Mian, Ajmal

2015-03-01

Hyperspectral imaging offers new opportunities for face recognition via improved discrimination along the spectral dimension. However, it poses new challenges, including low signal-to-noise ratio, interband misalignment, and high data dimensionality. Due to these challenges, the literature on hyperspectral face recognition is not only sparse but is limited to ad hoc dimensionality reduction techniques and lacks comprehensive evaluation. We propose a hyperspectral face recognition algorithm using a spatiospectral covariance for band fusion and partial least square regression for classification. Moreover, we extend 13 existing face recognition techniques, for the first time, to perform hyperspectral face recognition.We formulate hyperspectral face recognition as an image-set classification problem and evaluate the performance of seven state-of-the-art image-set classification techniques. We also test six state-of-the-art grayscale and RGB (color) face recognition algorithms after applying fusion techniques on hyperspectral images. Comparison with the 13 extended and five existing hyperspectral face recognition techniques on three standard data sets show that the proposed algorithm outperforms all by a significant margin. Finally, we perform band selection experiments to find the most discriminative bands in the visible and near infrared response spectrum.

Computer assisted optical biopsy for colorectal polyps

NASA Astrophysics Data System (ADS)

Navarro-Avila, Fernando J.; Saint-Hill-Febles, Yadira; Renner, Janis; Klare, Peter; von Delius, Stefan; Navab, Nassir; Mateus, Diana

2017-03-01

We propose a method for computer-assisted optical biopsy for colorectal polyps, with the final goal of assisting the medical expert during the colonoscopy. In particular, we target the problem of automatic classification of polyp images in two classes: adenomatous vs non-adenoma. Our approach is based on recent advancements in convolutional neural networks (CNN) for image representation. In the paper, we describe and compare four different methodologies to address the binary classification task: a baseline with classical features and a Random Forest classifier, two methods based on features obtained from a pre-trained network, and finally, the end-to-end training of a CNN. With the pre-trained network, we show the feasibility of transferring a feature extraction mechanism trained on millions of natural images, to the task of classifying adenomatous polyps. We then demonstrate further performance improvements when training the CNN for our specific classification task. In our study, 776 polyp images were acquired and histologically analyzed after polyp resection. We report a performance increase of the CNN-based approaches with respect to both, the conventional engineered features and to a state-of-the-art method based on videos and 3D shape features.

Inverse imaging of the breast with a material classification technique.

PubMed

Manry, C W; Broschat, S L

1998-03-01

In recent publications [Chew et al., IEEE Trans. Blomed. Eng. BME-9, 218-225 (1990); Borup et al., Ultrason. Imaging 14, 69-85 (1992)] the inverse imaging problem has been solved by means of a two-step iterative method. In this paper, a third step is introduced for ultrasound imaging of the breast. In this step, which is based on statistical pattern recognition, classification of tissue types and a priori knowledge of the anatomy of the breast are integrated into the iterative method. Use of this material classification technique results in more rapid convergence to the inverse solution--approximately 40% fewer iterations are required--as well as greater accuracy. In addition, tumors are detected early in the reconstruction process. Results for reconstructions of a simple two-dimensional model of the human breast are presented. These reconstructions are extremely accurate when system noise and variations in tissue parameters are not too great. However, for the algorithm used, degradation of the reconstructions and divergence from the correct solution occur when system noise and variations in parameters exceed threshold values. Even in this case, however, tumors are still identified within a few iterations.

An unsupervised technique for optimal feature selection in attribute profiles for spectral-spatial classification of hyperspectral images

NASA Astrophysics Data System (ADS)

Bhardwaj, Kaushal; Patra, Swarnajyoti

2018-04-01

Inclusion of spatial information along with spectral features play a significant role in classification of remote sensing images. Attribute profiles have already proved their ability to represent spatial information. In order to incorporate proper spatial information, multiple attributes are required and for each attribute large profiles need to be constructed by varying the filter parameter values within a wide range. Thus, the constructed profiles that represent spectral-spatial information of an hyperspectral image have huge dimension which leads to Hughes phenomenon and increases computational burden. To mitigate these problems, this work presents an unsupervised feature selection technique that selects a subset of filtered image from the constructed high dimensional multi-attribute profile which are sufficiently informative to discriminate well among classes. In this regard the proposed technique exploits genetic algorithms (GAs). The fitness function of GAs are defined in an unsupervised way with the help of mutual information. The effectiveness of the proposed technique is assessed using one-against-all support vector machine classifier. The experiments conducted on three hyperspectral data sets show the robustness of the proposed method in terms of computation time and classification accuracy.

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images.

PubMed

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-06-12

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the "navigation via classification" task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.

Gender classification in low-resolution surveillance video: in-depth comparison of random forests and SVMs

NASA Astrophysics Data System (ADS)

Geelen, Christopher D.; Wijnhoven, Rob G. J.; Dubbelman, Gijs; de With, Peter H. N.

2015-03-01

This research considers gender classification in surveillance environments, typically involving low-resolution images and a large amount of viewpoint variations and occlusions. Gender classification is inherently difficult due to the large intra-class variation and interclass correlation. We have developed a gender classification system, which is successfully evaluated on two novel datasets, which realistically consider the above conditions, typical for surveillance. The system reaches a mean accuracy of up to 90% and approaches our human baseline of 92.6%, proving a high-quality gender classification system. We also present an in-depth discussion of the fundamental differences between SVM and RF classifiers. We conclude that balancing the degree of randomization in any classifier is required for the highest classification accuracy. For our problem, an RF-SVM hybrid classifier exploiting the combination of HSV and LBP features results in the highest classification accuracy of 89.9 0.2%, while classification computation time is negligible compared to the detection time of pedestrians.

Computational Imaging in Demanding Conditions

DTIC Science & Technology

2015-11-18

spatiotemporal domain where such blur is not present.  Detailed Accomplishments:  ● Removing  Atmospheric   Turbulence  via Space-Invariant  Deconvolution:  ○ To...given image sequence distorted by  atmospheric   turbulence . This approach  reduces the space and time-varying deblurring problem to a shift invariant...SUBJECT TERMS Image processing, Computational imaging, turbulence , blur, enhancement 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18

Applying local binary patterns in image clustering problems

NASA Astrophysics Data System (ADS)

Skorokhod, Nikolai N.; Elizarov, Alexey I.

2017-11-01

Due to the fact that the cloudiness plays a critical role in the Earth radiative balance, the study of the distribution of different types of clouds and their movements is relevant. The main sources of such information are artificial satellites that provide data in the form of images. The most commonly used method of solving tasks of processing and classification of images of clouds is based on the description of texture features. The use of a set of local binary patterns is proposed to describe the texture image.

Shadow detection and removal in RGB VHR images for land use unsupervised classification

NASA Astrophysics Data System (ADS)

Movia, A.; Beinat, A.; Crosilla, F.

2016-09-01

Nowadays, high resolution aerial images are widely available thanks to the diffusion of advanced technologies such as UAVs (Unmanned Aerial Vehicles) and new satellite missions. Although these developments offer new opportunities for accurate land use analysis and change detection, cloud and terrain shadows actually limit benefits and possibilities of modern sensors. Focusing on the problem of shadow detection and removal in VHR color images, the paper proposes new solutions and analyses how they can enhance common unsupervised classification procedures for identifying land use classes related to the CO2 absorption. To this aim, an improved fully automatic procedure has been developed for detecting image shadows using exclusively RGB color information, and avoiding user interaction. Results show a significant accuracy enhancement with respect to similar methods using RGB based indexes. Furthermore, novel solutions derived from Procrustes analysis have been applied to remove shadows and restore brightness in the images. In particular, two methods implementing the so called "anisotropic Procrustes" and the "not-centered oblique Procrustes" algorithms have been developed and compared with the linear correlation correction method based on the Cholesky decomposition. To assess how shadow removal can enhance unsupervised classifications, results obtained with classical methods such as k-means, maximum likelihood, and self-organizing maps, have been compared to each other and with a supervised clustering procedure.

Application of LANDSAT data to monitor land reclamation progress in Belmont County, Ohio

NASA Technical Reports Server (NTRS)

Bloemer, H. H. L.; Brumfield, J. O.; Campbell, W. J.; Witt, R. G.; Bly, B. G.

1981-01-01

Strip and contour mining techniques are reviewed as well as some studies conducted to determine the applicability of LANDSAT and associated digital image processing techniques to the surficial problems associated with mining operations. A nontraditional unsupervised classification approach to multispectral data is considered which renders increased classification separability in land cover analysis of surface mined areas. The approach also reduces the dimensionality of the data and requires only minimal analytical skills in digital data processing.

Patient-specific semi-supervised learning for postoperative brain tumor segmentation.

PubMed

Meier, Raphael; Bauer, Stefan; Slotboom, Johannes; Wiest, Roland; Reyes, Mauricio

2014-01-01

In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor segmentation has been rarely approached so far. We present a fully-automatic segmentation method using multimodal magnetic resonance image data and patient-specific semi-supervised learning. The idea behind our semi-supervised approach is to effectively fuse information from both pre- and postoperative image data of the same patient to improve segmentation of the postoperative image. We pose image segmentation as a classification problem and solve it by adopting a semi-supervised decision forest. The method is evaluated on a cohort of 10 high-grade glioma patients, with segmentation performance and computation time comparable or superior to a state-of-the-art brain tumor segmentation method. Moreover, our results confirm that the inclusion of preoperative MR images lead to a better performance regarding postoperative brain tumor segmentation.

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce.

PubMed

Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan

2016-01-01

A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.

Localized thin-section CT with radiomics feature extraction and machine learning to classify early-detected pulmonary nodules from lung cancer screening

NASA Astrophysics Data System (ADS)

Tu, Shu-Ju; Wang, Chih-Wei; Pan, Kuang-Tse; Wu, Yi-Cheng; Wu, Chen-Te

2018-03-01

Lung cancer screening aims to detect small pulmonary nodules and decrease the mortality rate of those affected. However, studies from large-scale clinical trials of lung cancer screening have shown that the false-positive rate is high and positive predictive value is low. To address these problems, a technical approach is greatly needed for accurate malignancy differentiation among these early-detected nodules. We studied the clinical feasibility of an additional protocol of localized thin-section CT for further assessment on recalled patients from lung cancer screening tests. Our approach of localized thin-section CT was integrated with radiomics features extraction and machine learning classification which was supervised by pathological diagnosis. Localized thin-section CT images of 122 nodules were retrospectively reviewed and 374 radiomics features were extracted. In this study, 48 nodules were benign and 74 malignant. There were nine patients with multiple nodules and four with synchronous multiple malignant nodules. Different machine learning classifiers with a stratified ten-fold cross-validation were used and repeated 100 times to evaluate classification accuracy. Of the image features extracted from the thin-section CT images, 238 (64%) were useful in differentiating between benign and malignant nodules. These useful features include CT density (p  =  0.002 518), sigma (p  =  0.002 781), uniformity (p  =  0.032 41), and entropy (p  =  0.006 685). The highest classification accuracy was 79% by the logistic classifier. The performance metrics of this logistic classification model was 0.80 for the positive predictive value, 0.36 for the false-positive rate, and 0.80 for the area under the receiver operating characteristic curve. Our approach of direct risk classification supervised by the pathological diagnosis with localized thin-section CT and radiomics feature extraction may support clinical physicians in determining truly malignant nodules and therefore reduce problems in lung cancer screening.

Localized thin-section CT with radiomics feature extraction and machine learning to classify early-detected pulmonary nodules from lung cancer screening.

PubMed

Tu, Shu-Ju; Wang, Chih-Wei; Pan, Kuang-Tse; Wu, Yi-Cheng; Wu, Chen-Te

2018-03-14

Lung cancer screening aims to detect small pulmonary nodules and decrease the mortality rate of those affected. However, studies from large-scale clinical trials of lung cancer screening have shown that the false-positive rate is high and positive predictive value is low. To address these problems, a technical approach is greatly needed for accurate malignancy differentiation among these early-detected nodules. We studied the clinical feasibility of an additional protocol of localized thin-section CT for further assessment on recalled patients from lung cancer screening tests. Our approach of localized thin-section CT was integrated with radiomics features extraction and machine learning classification which was supervised by pathological diagnosis. Localized thin-section CT images of 122 nodules were retrospectively reviewed and 374 radiomics features were extracted. In this study, 48 nodules were benign and 74 malignant. There were nine patients with multiple nodules and four with synchronous multiple malignant nodules. Different machine learning classifiers with a stratified ten-fold cross-validation were used and repeated 100 times to evaluate classification accuracy. Of the image features extracted from the thin-section CT images, 238 (64%) were useful in differentiating between benign and malignant nodules. These useful features include CT density (p  =  0.002 518), sigma (p  =  0.002 781), uniformity (p  =  0.032 41), and entropy (p  =  0.006 685). The highest classification accuracy was 79% by the logistic classifier. The performance metrics of this logistic classification model was 0.80 for the positive predictive value, 0.36 for the false-positive rate, and 0.80 for the area under the receiver operating characteristic curve. Our approach of direct risk classification supervised by the pathological diagnosis with localized thin-section CT and radiomics feature extraction may support clinical physicians in determining truly malignant nodules and therefore reduce problems in lung cancer screening.

Fluorescent marker-based and marker-free discrimination between healthy and cancerous human tissues using hyper-spectral imaging

NASA Astrophysics Data System (ADS)

Arnold, Thomas; De Biasio, Martin; Leitner, Raimund

2015-06-01

Two problems are addressed in this paper (i) the fluorescent marker-based and the (ii) marker-free discrimination between healthy and cancerous human tissues. For both applications the performance of hyper-spectral methods are quantified. Fluorescent marker-based tissue classification uses a number of fluorescent markers to dye specific parts of a human cell. The challenge is that the emission spectra of the fluorescent dyes overlap considerably. They are, furthermore disturbed by the inherent auto-fluorescence of human tissue. This results in ambiguities and decreased image contrast causing difficulties for the treatment decision. The higher spectral resolution introduced by tunable-filter-based spectral imaging in combination with spectral unmixing techniques results in an improvement of the image contrast and therefore more reliable information for the physician to choose the treatment decision. Marker-free tissue classification is based solely on the subtle spectral features of human tissue without the use of artificial markers. The challenge in this case is that the spectral differences between healthy and cancerous tissues are subtle and embedded in intra- and inter-patient variations of these features. The contributions of this paper are (i) the evaluation of hyper-spectral imaging in combination with spectral unmixing techniques for fluorescence marker-based tissue classification, (ii) the evaluation of spectral imaging for marker-free intra surgery tissue classification. Within this paper, we consider real hyper-spectral fluorescence and endoscopy data sets to emphasize the practical capability of the proposed methods. It is shown that the combination of spectral imaging with multivariate statistical methods can improve the sensitivity and specificity of the detection and the staging of cancerous tissues compared to standard procedures.

(Un)Natural Disasters: The Electoral Cycle Outweighs the Hydrologic Cycle in Drought Declaration in Northeast Brazil

NASA Astrophysics Data System (ADS)

Camps-Valls, G.; Gomez-Chova, L.; Mateo, G.; Laparra, V.; Perez-Suay, A.; Munoz-Mari, J.

2016-12-01

Current Earth-observation (EO) applications for image classification have to deal with an unprecedented big amount of heterogeneous and complex data sources. Spatio-temporally explicit classification methods are a requirement in a variety of Earth system data processing applications. Upcoming missions such as the super-spectral Copernicus Sentinels EnMAP and FLEX will soon provide unprecedented data streams. Very high resolution (VHR) sensors like Worldview-3 also pose big challenges to data processing. The challenge is not only attached to optical sensors but also to infrared sounders and radar images which increased in spectral, spatial and temporal resolution. Besides, we should not forget the availability of the extremely large remote sensing data archives already collected by several past missions, such ENVISAT, Cosmo-SkyMED, Landsat, SPOT, or Seviri/MSG. These large-scale data problems require enhanced processing techniques that should be accurate, robust and fast. Standard parameter retrieval and classification algorithms cannot cope with this new scenario efficiently. In this work, we review the field of large scale kernel methods for both atmospheric parameter retrieval and cloud detection using infrared sounding IASI data and optical Seviri/MSG imagery. We propose novel Gaussian Processes (GPs) to train problems with millions of instances and high number of input features. Algorithms can cope with non-linearities efficiently, accommodate multi-output problems, and provide confidence intervals for the predictions. Several strategies to speed up algorithms are devised: random Fourier features and variational approaches for cloud classification using IASI data and Seviri/MSG, and engineered randomized kernel functions and emulation in temperature, moisture and ozone atmospheric profile retrieval from IASI as a proxy to the upcoming MTG-IRS sensor. Excellent compromise between accuracy and scalability are obtained in all applications.

Large Scale Gaussian Processes for Atmospheric Parameter Retrieval and Cloud Screening

NASA Astrophysics Data System (ADS)

Camps-Valls, G.; Gomez-Chova, L.; Mateo, G.; Laparra, V.; Perez-Suay, A.; Munoz-Mari, J.

2017-12-01

Current Earth-observation (EO) applications for image classification have to deal with an unprecedented big amount of heterogeneous and complex data sources. Spatio-temporally explicit classification methods are a requirement in a variety of Earth system data processing applications. Upcoming missions such as the super-spectral Copernicus Sentinels EnMAP and FLEX will soon provide unprecedented data streams. Very high resolution (VHR) sensors like Worldview-3 also pose big challenges to data processing. The challenge is not only attached to optical sensors but also to infrared sounders and radar images which increased in spectral, spatial and temporal resolution. Besides, we should not forget the availability of the extremely large remote sensing data archives already collected by several past missions, such ENVISAT, Cosmo-SkyMED, Landsat, SPOT, or Seviri/MSG. These large-scale data problems require enhanced processing techniques that should be accurate, robust and fast. Standard parameter retrieval and classification algorithms cannot cope with this new scenario efficiently. In this work, we review the field of large scale kernel methods for both atmospheric parameter retrieval and cloud detection using infrared sounding IASI data and optical Seviri/MSG imagery. We propose novel Gaussian Processes (GPs) to train problems with millions of instances and high number of input features. Algorithms can cope with non-linearities efficiently, accommodate multi-output problems, and provide confidence intervals for the predictions. Several strategies to speed up algorithms are devised: random Fourier features and variational approaches for cloud classification using IASI data and Seviri/MSG, and engineered randomized kernel functions and emulation in temperature, moisture and ozone atmospheric profile retrieval from IASI as a proxy to the upcoming MTG-IRS sensor. Excellent compromise between accuracy and scalability are obtained in all applications.

Integrated Imaging and Vision Techniques for Industrial Inspection: A Special Issue on Machine Vision and Applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Liu, Zheng; Ukida, H.; Ramuhalli, Pradeep

2010-06-05

Imaging- and vision-based techniques play an important role in industrial inspection. The sophistication of the techniques assures high- quality performance of the manufacturing process through precise positioning, online monitoring, and real-time classification. Advanced systems incorporating multiple imaging and/or vision modalities provide robust solutions to complex situations and problems in industrial applications. A diverse range of industries, including aerospace, automotive, electronics, pharmaceutical, biomedical, semiconductor, and food/beverage, etc., have benefited from recent advances in multi-modal imaging, data fusion, and computer vision technologies. Many of the open problems in this context are in the general area of image analysis methodologies (preferably in anmore » automated fashion). This editorial article introduces a special issue of this journal highlighting recent advances and demonstrating the successful applications of integrated imaging and vision technologies in industrial inspection.« less

Developing collaborative classifiers using an expert-based model

USGS Publications Warehouse

Mountrakis, G.; Watts, R.; Luo, L.; Wang, Jingyuan

2009-01-01

This paper presents a hierarchical, multi-stage adaptive strategy for image classification. We iteratively apply various classification methods (e.g., decision trees, neural networks), identify regions of parametric and geographic space where accuracy is low, and in these regions, test and apply alternate methods repeating the process until the entire image is classified. Currently, classifiers are evaluated through human input using an expert-based system; therefore, this paper acts as the proof of concept for collaborative classifiers. Because we decompose the problem into smaller, more manageable sub-tasks, our classification exhibits increased flexibility compared to existing methods since classification methods are tailored to the idiosyncrasies of specific regions. A major benefit of our approach is its scalability and collaborative support since selected low-accuracy classifiers can be easily replaced with others without affecting classification accuracy in high accuracy areas. At each stage, we develop spatially explicit accuracy metrics that provide straightforward assessment of results by non-experts and point to areas that need algorithmic improvement or ancillary data. Our approach is demonstrated in the task of detecting impervious surface areas, an important indicator for human-induced alterations to the environment, using a 2001 Landsat scene from Las Vegas, Nevada. ?? 2009 American Society for Photogrammetry and Remote Sensing.

Building Extraction Based on Openstreetmap Tags and Very High Spatial Resolution Image in Urban Area

NASA Astrophysics Data System (ADS)

Kang, L.; Wang, Q.; Yan, H. W.

2018-04-01

How to derive contour of buildings from VHR images is the essential problem for automatic building extraction in urban area. To solve this problem, OSM data is introduced to offer vector contour information of buildings which is hard to get from VHR images. First, we import OSM data into database. The line string data of OSM with tags of building, amenity, office etc. are selected and combined into completed contours; Second, the accuracy of contours of buildings is confirmed by comparing with the real buildings in Google Earth; Third, maximum likelihood classification is conducted with the confirmed building contours, and the result demonstrates that the proposed approach is effective and accurate. The approach offers a new way for automatic interpretation of VHR images.

Retinal Microaneurysms Detection Using Gradient Vector Analysis and Class Imbalance Classification.

PubMed

Dai, Baisheng; Wu, Xiangqian; Bu, Wei

2016-01-01

Retinal microaneurysms (MAs) are the earliest clinically observable lesions of diabetic retinopathy. Reliable automated MAs detection is thus critical for early diagnosis of diabetic retinopathy. This paper proposes a novel method for the automated MAs detection in color fundus images based on gradient vector analysis and class imbalance classification, which is composed of two stages, i.e. candidate MAs extraction and classification. In the first stage, a candidate MAs extraction algorithm is devised by analyzing the gradient field of the image, in which a multi-scale log condition number map is computed based on the gradient vectors for vessel removal, and then the candidate MAs are localized according to the second order directional derivatives computed in different directions. Due to the complexity of fundus image, besides a small number of true MAs, there are also a large amount of non-MAs in the extracted candidates. Classifying the true MAs and the non-MAs is an extremely class imbalanced classification problem. Therefore, in the second stage, several types of features including geometry, contrast, intensity, edge, texture, region descriptors and other features are extracted from the candidate MAs and a class imbalance classifier, i.e., RUSBoost, is trained for the MAs classification. With the Retinopathy Online Challenge (ROC) criterion, the proposed method achieves an average sensitivity of 0.433 at 1/8, 1/4, 1/2, 1, 2, 4 and 8 false positives per image on the ROC database, which is comparable with the state-of-the-art approaches, and 0.321 on the DiaRetDB1 V2.1 database, which outperforms the state-of-the-art approaches.

Manifold Embedding and Semantic Segmentation for Intraoperative Guidance With Hyperspectral Brain Imaging.

PubMed

Ravi, Daniele; Fabelo, Himar; Callic, Gustavo Marrero; Yang, Guang-Zhong

2017-09-01

Recent advances in hyperspectral imaging have made it a promising solution for intra-operative tissue characterization, with the advantages of being non-contact, non-ionizing, and non-invasive. Working with hyperspectral images in vivo, however, is not straightforward as the high dimensionality of the data makes real-time processing challenging. In this paper, a novel dimensionality reduction scheme and a new processing pipeline are introduced to obtain a detailed tumor classification map for intra-operative margin definition during brain surgery. However, existing approaches to dimensionality reduction based on manifold embedding can be time consuming and may not guarantee a consistent result, thus hindering final tissue classification. The proposed framework aims to overcome these problems through a process divided into two steps: dimensionality reduction based on an extension of the T-distributed stochastic neighbor approach is first performed and then a semantic segmentation technique is applied to the embedded results by using a Semantic Texton Forest for tissue classification. Detailed in vivo validation of the proposed method has been performed to demonstrate the potential clinical value of the system.

Texture classification using non-Euclidean Minkowski dilation

NASA Astrophysics Data System (ADS)

Florindo, Joao B.; Bruno, Odemir M.

2018-03-01

This study presents a new method to extract meaningful descriptors of gray-scale texture images using Minkowski morphological dilation based on the Lp metric. The proposed approach is motivated by the success previously achieved by Bouligand-Minkowski fractal descriptors on texture classification. In essence, such descriptors are directly derived from the morphological dilation of a three-dimensional representation of the gray-level pixels using the classical Euclidean metric. In this way, we generalize the dilation for different values of p in the Lp metric (Euclidean is a particular case when p = 2) and obtain the descriptors from the cumulated distribution of the distance transform computed over the texture image. The proposed method is compared to other state-of-the-art approaches (such as local binary patterns and textons for example) in the classification of two benchmark data sets (UIUC and Outex). The proposed descriptors outperformed all the other approaches in terms of rate of images correctly classified. The interesting results suggest the potential of these descriptors in this type of task, with a wide range of possible applications to real-world problems.

Classification of corn kernels contaminated with aflatoxins using fluorescence and reflectance hyperspectral image analysis

USDA-ARS?s Scientific Manuscript database

Aflatoxins are secondary metabolites produced by certain fungal species of the Aspergillus genus. Aflatoxin contamination remains a problem in agricultural products due to its toxic and carcinogenic properties. Conventional chemical methods for aflatoxin detection are time-consuming and destructive....

Classifying magnetic resonance image modalities with convolutional neural networks

NASA Astrophysics Data System (ADS)

Remedios, Samuel; Pham, Dzung L.; Butman, John A.; Roy, Snehashis

2018-02-01

Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)- based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs postcontrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy.

Active learning for solving the incomplete data problem in facial age classification by the furthest nearest-neighbor criterion.

PubMed

Wang, Jian-Gang; Sung, Eric; Yau, Wei-Yun

2011-07-01

Facial age classification is an approach to classify face images into one of several predefined age groups. One of the difficulties in applying learning techniques to the age classification problem is the large amount of labeled training data required. Acquiring such training data is very costly in terms of age progress, privacy, human time, and effort. Although unlabeled face images can be obtained easily, it would be expensive to manually label them on a large scale and getting the ground truth. The frugal selection of the unlabeled data for labeling to quickly reach high classification performance with minimal labeling efforts is a challenging problem. In this paper, we present an active learning approach based on an online incremental bilateral two-dimension linear discriminant analysis (IB2DLDA) which initially learns from a small pool of labeled data and then iteratively selects the most informative samples from the unlabeled set to increasingly improve the classifier. Specifically, we propose a novel data selection criterion called the furthest nearest-neighbor (FNN) that generalizes the margin-based uncertainty to the multiclass case and which is easy to compute, so that the proposed active learning algorithm can handle a large number of classes and large data sizes efficiently. Empirical experiments on FG-NET and Morph databases together with a large unlabeled data set for age categorization problems show that the proposed approach can achieve results comparable or even outperform a conventionally trained active classifier that requires much more labeling effort. Our IB2DLDA-FNN algorithm can achieve similar results much faster than random selection and with fewer samples for age categorization. It also can achieve comparable results with active SVM but is much faster than active SVM in terms of training because kernel methods are not needed. The results on the face recognition database and palmprint/palm vein database showed that our approach can handle problems with large number of classes. Our contributions in this paper are twofold. First, we proposed the IB2DLDA-FNN, the FNN being our novel idea, as a generic on-line or active learning paradigm. Second, we showed that it can be another viable tool for active learning of facial age range classification.

Steganography anomaly detection using simple one-class classification

NASA Astrophysics Data System (ADS)

Rodriguez, Benjamin M.; Peterson, Gilbert L.; Agaian, Sos S.

2007-04-01

There are several security issues tied to multimedia when implementing the various applications in the cellular phone and wireless industry. One primary concern is the potential ease of implementing a steganography system. Traditionally, the only mechanism to embed information into a media file has been with a desktop computer. However, as the cellular phone and wireless industry matures, it becomes much simpler for the same techniques to be performed using a cell phone. In this paper, two methods are compared that classify cell phone images as either an anomaly or clean, where a clean image is one in which no alterations have been made and an anomalous image is one in which information has been hidden within the image. An image in which information has been hidden is known as a stego image. The main concern in detecting steganographic content with machine learning using cell phone images is in training specific embedding procedures to determine if the method has been used to generate a stego image. This leads to a possible flaw in the system when the learned model of stego is faced with a new stego method which doesn't match the existing model. The proposed solution to this problem is to develop systems that detect steganography as anomalies, making the embedding method irrelevant in detection. Two applicable classification methods for solving the anomaly detection of steganographic content problem are single class support vector machines (SVM) and Parzen-window. Empirical comparison of the two approaches shows that Parzen-window outperforms the single class SVM most likely due to the fact that Parzen-window generalizes less.

Some new classification methods for hyperspectral remote sensing

NASA Astrophysics Data System (ADS)

Du, Pei-jun; Chen, Yun-hao; Jones, Simon; Ferwerda, Jelle G.; Chen, Zhi-jun; Zhang, Hua-peng; Tan, Kun; Yin, Zuo-xia

2006-10-01

Hyperspectral Remote Sensing (HRS) is one of the most significant recent achievements of Earth Observation Technology. Classification is the most commonly employed processing methodology. In this paper three new hyperspectral RS image classification methods are analyzed. These methods are: Object-oriented FIRS image classification, HRS image classification based on information fusion and HSRS image classification by Back Propagation Neural Network (BPNN). OMIS FIRS image is used as the example data. Object-oriented techniques have gained popularity for RS image classification in recent years. In such method, image segmentation is used to extract the regions from the pixel information based on homogeneity criteria at first, and spectral parameters like mean vector, texture, NDVI and spatial/shape parameters like aspect ratio, convexity, solidity, roundness and orientation for each region are calculated, finally classification of the image using the region feature vectors and also using suitable classifiers such as artificial neural network (ANN). It proves that object-oriented methods can improve classification accuracy since they utilize information and features both from the point and the neighborhood, and the processing unit is a polygon (in which all pixels are homogeneous and belong to the class). HRS image classification based on information fusion, divides all bands of the image into different groups initially, and extracts features from every group according to the properties of each group. Three levels of information fusion: data level fusion, feature level fusion and decision level fusion are used to HRS image classification. Artificial Neural Network (ANN) can perform well in RS image classification. In order to promote the advances of ANN used for HIRS image classification, Back Propagation Neural Network (BPNN), the most commonly used neural network, is used to HRS image classification.

Medical image classification using spatial adjacent histogram based on adaptive local binary patterns.

PubMed

Liu, Dong; Wang, Shengsheng; Huang, Dezhi; Deng, Gang; Zeng, Fantao; Chen, Huiling

2016-05-01

Medical image recognition is an important task in both computer vision and computational biology. In the field of medical image classification, representing an image based on local binary patterns (LBP) descriptor has become popular. However, most existing LBP-based methods encode the binary patterns in a fixed neighborhood radius and ignore the spatial relationships among local patterns. The ignoring of the spatial relationships in the LBP will cause a poor performance in the process of capturing discriminative features for complex samples, such as medical images obtained by microscope. To address this problem, in this paper we propose a novel method to improve local binary patterns by assigning an adaptive neighborhood radius for each pixel. Based on these adaptive local binary patterns, we further propose a spatial adjacent histogram strategy to encode the micro-structures for image representation. An extensive set of evaluations are performed on four medical datasets which show that the proposed method significantly improves standard LBP and compares favorably with several other prevailing approaches. Copyright © 2016 Elsevier Ltd. All rights reserved.

Distributed multimodal data fusion for large scale wireless sensor networks

NASA Astrophysics Data System (ADS)

Ertin, Emre

2006-05-01

Sensor network technology has enabled new surveillance systems where sensor nodes equipped with processing and communication capabilities can collaboratively detect, classify and track targets of interest over a large surveillance area. In this paper we study distributed fusion of multimodal sensor data for extracting target information from a large scale sensor network. Optimal tracking, classification, and reporting of threat events require joint consideration of multiple sensor modalities. Multiple sensor modalities improve tracking by reducing the uncertainty in the track estimates as well as resolving track-sensor data association problems. Our approach to solving the fusion problem with large number of multimodal sensors is construction of likelihood maps. The likelihood maps provide a summary data for the solution of the detection, tracking and classification problem. The likelihood map presents the sensory information in an easy format for the decision makers to interpret and is suitable with fusion of spatial prior information such as maps, imaging data from stand-off imaging sensors. We follow a statistical approach to combine sensor data at different levels of uncertainty and resolution. The likelihood map transforms each sensor data stream to a spatio-temporal likelihood map ideally suitable for fusion with imaging sensor outputs and prior geographic information about the scene. We also discuss distributed computation of the likelihood map using a gossip based algorithm and present simulation results.

Monocular precrash vehicle detection: features and classifiers.

PubMed

Sun, Zehang; Bebis, George; Miller, Ronald

2006-07-01

Robust and reliable vehicle detection from images acquired by a moving vehicle (i.e., on-road vehicle detection) is an important problem with applications to driver assistance systems and autonomous, self-guided vehicles. The focus of this work is on the issues of feature extraction and classification for rear-view vehicle detection. Specifically, by treating the problem of vehicle detection as a two-class classification problem, we have investigated several different feature extraction methods such as principal component analysis, wavelets, and Gabor filters. To evaluate the extracted features, we have experimented with two popular classifiers, neural networks and support vector machines (SVMs). Based on our evaluation results, we have developed an on-board real-time monocular vehicle detection system that is capable of acquiring grey-scale images, using Ford's proprietary low-light camera, achieving an average detection rate of 10 Hz. Our vehicle detection algorithm consists of two main steps: a multiscale driven hypothesis generation step and an appearance-based hypothesis verification step. During the hypothesis generation step, image locations where vehicles might be present are extracted. This step uses multiscale techniques not only to speed up detection, but also to improve system robustness. The appearance-based hypothesis verification step verifies the hypotheses using Gabor features and SVMs. The system has been tested in Ford's concept vehicle under different traffic conditions (e.g., structured highway, complex urban streets, and varying weather conditions), illustrating good performance.

Research on Remote Sensing Image Classification Based on Feature Level Fusion

NASA Astrophysics Data System (ADS)

Yuan, L.; Zhu, G.

2018-04-01

Remote sensing image classification, as an important direction of remote sensing image processing and application, has been widely studied. However, in the process of existing classification algorithms, there still exists the phenomenon of misclassification and missing points, which leads to the final classification accuracy is not high. In this paper, we selected Sentinel-1A and Landsat8 OLI images as data sources, and propose a classification method based on feature level fusion. Compare three kind of feature level fusion algorithms (i.e., Gram-Schmidt spectral sharpening, Principal Component Analysis transform and Brovey transform), and then select the best fused image for the classification experimental. In the classification process, we choose four kinds of image classification algorithms (i.e. Minimum distance, Mahalanobis distance, Support Vector Machine and ISODATA) to do contrast experiment. We use overall classification precision and Kappa coefficient as the classification accuracy evaluation criteria, and the four classification results of fused image are analysed. The experimental results show that the fusion effect of Gram-Schmidt spectral sharpening is better than other methods. In four kinds of classification algorithms, the fused image has the best applicability to Support Vector Machine classification, the overall classification precision is 94.01 % and the Kappa coefficients is 0.91. The fused image with Sentinel-1A and Landsat8 OLI is not only have more spatial information and spectral texture characteristics, but also enhances the distinguishing features of the images. The proposed method is beneficial to improve the accuracy and stability of remote sensing image classification.

Transfer learning for visual categorization: a survey.

PubMed

Shao, Ling; Zhu, Fan; Li, Xuelong

2015-05-01

Regular machine learning and data mining techniques study the training data for future inferences under a major assumption that the future data are within the same feature space or have the same distribution as the training data. However, due to the limited availability of human labeled training data, training data that stay in the same feature space or have the same distribution as the future data cannot be guaranteed to be sufficient enough to avoid the over-fitting problem. In real-world applications, apart from data in the target domain, related data in a different domain can also be included to expand the availability of our prior knowledge about the target future data. Transfer learning addresses such cross-domain learning problems by extracting useful information from data in a related domain and transferring them for being used in target tasks. In recent years, with transfer learning being applied to visual categorization, some typical problems, e.g., view divergence in action recognition tasks and concept drifting in image classification tasks, can be efficiently solved. In this paper, we survey state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition.

Fine-grained visual marine vessel classification for coastal surveillance and defense applications

NASA Astrophysics Data System (ADS)

Solmaz, Berkan; Gundogdu, Erhan; Karaman, Kaan; Yücesoy, Veysel; Koç, Aykut

2017-10-01

The need for capabilities of automated visual content analysis has substantially increased due to presence of large number of images captured by surveillance cameras. With a focus on development of practical methods for extracting effective visual data representations, deep neural network based representations have received great attention due to their success in visual categorization of generic images. For fine-grained image categorization, a closely related yet a more challenging research problem compared to generic image categorization due to high visual similarities within subgroups, diverse applications were developed such as classifying images of vehicles, birds, food and plants. Here, we propose the use of deep neural network based representations for categorizing and identifying marine vessels for defense and security applications. First, we gather a large number of marine vessel images via online sources grouping them into four coarse categories; naval, civil, commercial and service vessels. Next, we subgroup naval vessels into fine categories such as corvettes, frigates and submarines. For distinguishing images, we extract state-of-the-art deep visual representations and train support-vector-machines. Furthermore, we fine tune deep representations for marine vessel images. Experiments address two scenarios, classification and verification of naval marine vessels. Classification experiment aims coarse categorization, as well as learning models of fine categories. Verification experiment embroils identification of specific naval vessels by revealing if a pair of images belongs to identical marine vessels by the help of learnt deep representations. Obtaining promising performance, we believe these presented capabilities would be essential components of future coastal and on-board surveillance systems.

MO-DE-207A-02: A Feature-Preserving Image Reconstruction Method for Improved Pancreaticlesion Classification in Diagnostic CT Imaging

DOE Office of Scientific and Technical Information (OSTI.GOV)

Xu, J; Tsui, B; Noo, F

Purpose: To develop a feature-preserving model based image reconstruction (MBIR) method that improves performance in pancreatic lesion classification at equal or reduced radiation dose. Methods: A set of pancreatic lesion models was created with both benign and premalignant lesion types. These two classes of lesions are distinguished by their fine internal structures; their delineation is therefore crucial to the task of pancreatic lesion classification. To reduce image noise while preserving the features of the lesions, we developed a MBIR method with curvature-based regularization. The novel regularization encourages formation of smooth surfaces that model both the exterior shape and the internalmore » features of pancreatic lesions. Given that the curvature depends on the unknown image, image reconstruction or denoising becomes a non-convex optimization problem; to address this issue an iterative-reweighting scheme was used to calculate and update the curvature using the image from the previous iteration. Evaluation was carried out with insertion of the lesion models into the pancreas of a patient CT image. Results: Visual inspection was used to compare conventional TV regularization with our curvature-based regularization. Several penalty-strengths were considered for TV regularization, all of which resulted in erasing portions of the septation (thin partition) in a premalignant lesion. At matched noise variance (50% noise reduction in the patient stomach region), the connectivity of the septation was well preserved using the proposed curvature-based method. Conclusion: The curvature-based regularization is able to reduce image noise while simultaneously preserving the lesion features. This method could potentially improve task performance for pancreatic lesion classification at equal or reduced radiation dose. The result is of high significance for longitudinal surveillance studies of patients with pancreatic cysts, which may develop into pancreatic cancer. The Senior Author receives financial support from Siemens GmbH Healthcare.« less

A method for classification of multisource data using interval-valued probabilities and its application to HIRIS data

NASA Technical Reports Server (NTRS)

Kim, H.; Swain, P. H.

1991-01-01

A method of classifying multisource data in remote sensing is presented. The proposed method considers each data source as an information source providing a body of evidence, represents statistical evidence by interval-valued probabilities, and uses Dempster's rule to integrate information based on multiple data source. The method is applied to the problems of ground-cover classification of multispectral data combined with digital terrain data such as elevation, slope, and aspect. Then this method is applied to simulated 201-band High Resolution Imaging Spectrometer (HIRIS) data by dividing the dimensionally huge data source into smaller and more manageable pieces based on the global statistical correlation information. It produces higher classification accuracy than the Maximum Likelihood (ML) classification method when the Hughes phenomenon is apparent.

Application of LANDSAT data to wetland study and land use classification in west Tennessee

NASA Technical Reports Server (NTRS)

Jones, N. L.; Shahrokhi, F.

1977-01-01

The Obion-Forked Deer River Basin in northwest Tennessee is confronted with several acute land use problems which result in excessive erosion, sedimentation, pollution, and hydrologic runoff. LANDSAT data was applied to determine land use of selected watershed areas within the basin, with special emphasis on determining wetland boundaries. Densitometric analysis was performed to allow numerical classification of objects observed in the imagery on the basis of measurements of optical densities. Multispectral analysis of the LANDSAT imagery provided the capability of altering the color of the image presentation in order to enhance desired relationships. Manual mapping and classification techniques were performed in order to indicate a level of accuracy of the LANDSAT data as compared with high and low altitude photography for land use classification.

Preparation of 2D sequences of corneal images for 3D model building.

PubMed

Elbita, Abdulhakim; Qahwaji, Rami; Ipson, Stanley; Sharif, Mhd Saeed; Ghanchi, Faruque

2014-04-01

A confocal microscope provides a sequence of images, at incremental depths, of the various corneal layers and structures. From these, medical practioners can extract clinical information on the state of health of the patient's cornea. In this work we are addressing problems associated with capturing and processing these images including blurring, non-uniform illumination and noise, as well as the displacement of images laterally and in the anterior-posterior direction caused by subject movement. The latter may cause some of the captured images to be out of sequence in terms of depth. In this paper we introduce automated algorithms for classification, reordering, registration and segmentation to solve these problems. The successful implementation of these algorithms could open the door for another interesting development, which is the 3D modelling of these sequences. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Stages as models of scene geometry.

PubMed

Nedović, Vladimir; Smeulders, Arnold W M; Redert, André; Geusebroek, Jan-Mark

2010-09-01

Reconstruction of 3D scene geometry is an important element for scene understanding, autonomous vehicle and robot navigation, image retrieval, and 3D television. We propose accounting for the inherent structure of the visual world when trying to solve the scene reconstruction problem. Consequently, we identify geometric scene categorization as the first step toward robust and efficient depth estimation from single images. We introduce 15 typical 3D scene geometries called stages, each with a unique depth profile, which roughly correspond to a large majority of broadcast video frames. Stage information serves as a first approximation of global depth, narrowing down the search space in depth estimation and object localization. We propose different sets of low-level features for depth estimation, and perform stage classification on two diverse data sets of television broadcasts. Classification results demonstrate that stages can often be efficiently learned from low-dimensional image representations.

Classification of hyperspectral imagery using MapReduce on a NVIDIA graphics processing unit (Conference Presentation)

NASA Astrophysics Data System (ADS)

Ramirez, Andres; Rahnemoonfar, Maryam

2017-04-01

A hyperspectral image provides multidimensional figure rich in data consisting of hundreds of spectral dimensions. Analyzing the spectral and spatial information of such image with linear and non-linear algorithms will result in high computational time. In order to overcome this problem, this research presents a system using a MapReduce-Graphics Processing Unit (GPU) model that can help analyzing a hyperspectral image through the usage of parallel hardware and a parallel programming model, which will be simpler to handle compared to other low-level parallel programming models. Additionally, Hadoop was used as an open-source version of the MapReduce parallel programming model. This research compared classification accuracy results and timing results between the Hadoop and GPU system and tested it against the following test cases: the CPU and GPU test case, a CPU test case and a test case where no dimensional reduction was applied.

Morphological classification of odontogenic keratocysts using Bouligand-Minkowski fractal descriptors.

PubMed

Florindo, Joao B; Bruno, Odemir M; Landini, Gabriel

2017-02-01

The Odontogenic keratocyst (OKC) is a cystic lesion of the jaws, which has high growth and recurrence rates compared to other cysts of the jaws (for instance, radicular cyst, which is the most common jaw cyst type). For this reason OKCs are considered by some to be benign neoplasms. There exist two sub-types of OKCs (sporadic and syndromic) and the ability to discriminate between these sub-types, as well as other jaw cysts, is an important task in terms of disease diagnosis and prognosis. With the development of digital pathology, computational algorithms have become central to addressing this type of problem. Considering that only basic feature-based methods have been investigated in this problem before, we propose to use a different approach (the Bouligand-Minkowski descriptors) to assess the success rates achieved on the classification of a database of histological images of the epithelial lining of these cysts. This does not require the level of abstraction necessary to extract histologically-relevant features and therefore has the potential of being more robust than previous approaches. The descriptors were obtained by mapping pixel intensities into a three dimensional cloud of points in discrete space and applying morphological dilations with spheres of increasing radii. The descriptors were computed from the volume of the dilated set and submitted to a machine learning algorithm to classify the samples into diagnostic groups. This approach was capable of discriminating between OKCs and radicular cysts in 98% of images (100% of cases) and between the two sub-types of OKCs in 68% of images (71% of cases). These results improve over previously reported classification rates reported elsewhere and suggest that Bouligand-Minkowski descriptors are useful features to be used in histopathological images of these cysts. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network.

PubMed

Prasoon, Adhish; Petersen, Kersten; Igel, Christian; Lauze, François; Dam, Erik; Nielsen, Mads

2013-01-01

Segmentation of anatomical structures in medical images is often based on a voxel/pixel classification approach. Deep learning systems, such as convolutional neural networks (CNNs), can infer a hierarchical representation of images that fosters categorization. We propose a novel system for voxel classification integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D image, respectively. We applied our method to the segmentation of tibial cartilage in low field knee MRI scans and tested it on 114 unseen scans. Although our method uses only 2D features at a single scale, it performs better than a state-of-the-art method using 3D multi-scale features. In the latter approach, the features and the classifier have been carefully adapted to the problem at hand. That we were able to get better results by a deep learning architecture that autonomously learns the features from the images is the main insight of this study.

Classification of footwear outsole patterns using Fourier transform and local interest points.

PubMed

Richetelli, Nicole; Lee, Mackenzie C; Lasky, Carleen A; Gump, Madison E; Speir, Jacqueline A

2017-06-01

Successful classification of questioned footwear has tremendous evidentiary value; the result can minimize the potential suspect pool and link a suspect to a victim, a crime scene, or even multiple crime scenes to each other. With this in mind, several different automated and semi-automated classification models have been applied to the forensic footwear recognition problem, with superior performance commonly associated with two different approaches: correlation of image power (magnitude) or phase, and the use of local interest points transformed using the Scale Invariant Feature Transform (SIFT) and compared using Random Sample Consensus (RANSAC). Despite the distinction associated with each of these methods, all three have not been cross-compared using a single dataset, of limited quality (i.e., characteristic of crime scene-like imagery), and created using a wide combination of image inputs. To address this question, the research presented here examines the classification performance of the Fourier-Mellin transform (FMT), phase-only correlation (POC), and local interest points (transformed using SIFT and compared using RANSAC), as a function of inputs that include mixed media (blood and dust), transfer mechanisms (gel lifters), enhancement techniques (digital and chemical) and variations in print substrate (ceramic tiles, vinyl tiles and paper). Results indicate that POC outperforms both FMT and SIFT+RANSAC, regardless of image input (type, quality and totality), and that the difference in stochastic dominance detected for POC is significant across all image comparison scenarios evaluated in this study. Copyright © 2017 Elsevier B.V. All rights reserved.

A New Approach to Image Fusion Based on Cokriging

NASA Technical Reports Server (NTRS)

Memarsadeghi, Nargess; LeMoigne, Jacqueline; Mount, David M.; Morisette, Jeffrey T.

2005-01-01

We consider the image fusion problem involving remotely sensed data. We introduce cokriging as a method to perform fusion. We investigate the advantages of fusing Hyperion with ALI. The evaluation is performed by comparing the classification of the fused data with that of input images and by calculating well-chosen quantitative fusion quality metrics. We consider the Invasive Species Forecasting System (ISFS) project as our fusion application. The fusion of ALI with Hyperion data is studies using PCA and wavelet-based fusion. We then propose utilizing a geostatistical based interpolation method called cokriging as a new approach for image fusion.

Recognition and classification of oscillatory patterns of electric brain activity using artificial neural network approach

NASA Astrophysics Data System (ADS)

Pchelintseva, Svetlana V.; Runnova, Anastasia E.; Musatov, Vyacheslav Yu.; Hramov, Alexander E.

2017-03-01

In the paper we study the problem of recognition type of the observed object, depending on the generated pattern and the registered EEG data. EEG recorded at the time of displaying cube Necker characterizes appropriate state of brain activity. As an image we use bistable image Necker cube. Subject selects the type of cube and interpret it either as aleft cube or as the right cube. To solve the problem of recognition, we use artificial neural networks. In our paper to create a classifier we have considered a multilayer perceptron. We examine the structure of the artificial neural network and define cubes recognition accuracy.

Using spectral imaging for the analysis of abnormalities for colorectal cancer: When is it helpful?

PubMed

Awan, Ruqayya; Al-Maadeed, Somaya; Al-Saady, Rafif

2018-01-01

The spectral imaging technique has been shown to provide more discriminative information than the RGB images and has been proposed for a range of problems. There are many studies demonstrating its potential for the analysis of histopathology images for abnormality detection but there have been discrepancies among previous studies as well. Many multispectral based methods have been proposed for histopathology images but the significance of the use of whole multispectral cube versus a subset of bands or a single band is still arguable. We performed comprehensive analysis using individual bands and different subsets of bands to determine the effectiveness of spectral information for determining the anomaly in colorectal images. Our multispectral colorectal dataset consists of four classes, each represented by infra-red spectrum bands in addition to the visual spectrum bands. We performed our analysis of spectral imaging by stratifying the abnormalities using both spatial and spectral information. For our experiments, we used a combination of texture descriptors with an ensemble classification approach that performed best on our dataset. We applied our method to another dataset and got comparable results with those obtained using the state-of-the-art method and convolutional neural network based method. Moreover, we explored the relationship of the number of bands with the problem complexity and found that higher number of bands is required for a complex task to achieve improved performance. Our results demonstrate a synergy between infra-red and visual spectrum by improving the classification accuracy (by 6%) on incorporating the infra-red representation. We also highlight the importance of how the dataset should be divided into training and testing set for evaluating the histopathology image-based approaches, which has not been considered in previous studies on multispectral histopathology images.

Using spectral imaging for the analysis of abnormalities for colorectal cancer: When is it helpful?

PubMed Central

Al-Maadeed, Somaya; Al-Saady, Rafif

2018-01-01

The spectral imaging technique has been shown to provide more discriminative information than the RGB images and has been proposed for a range of problems. There are many studies demonstrating its potential for the analysis of histopathology images for abnormality detection but there have been discrepancies among previous studies as well. Many multispectral based methods have been proposed for histopathology images but the significance of the use of whole multispectral cube versus a subset of bands or a single band is still arguable. We performed comprehensive analysis using individual bands and different subsets of bands to determine the effectiveness of spectral information for determining the anomaly in colorectal images. Our multispectral colorectal dataset consists of four classes, each represented by infra-red spectrum bands in addition to the visual spectrum bands. We performed our analysis of spectral imaging by stratifying the abnormalities using both spatial and spectral information. For our experiments, we used a combination of texture descriptors with an ensemble classification approach that performed best on our dataset. We applied our method to another dataset and got comparable results with those obtained using the state-of-the-art method and convolutional neural network based method. Moreover, we explored the relationship of the number of bands with the problem complexity and found that higher number of bands is required for a complex task to achieve improved performance. Our results demonstrate a synergy between infra-red and visual spectrum by improving the classification accuracy (by 6%) on incorporating the infra-red representation. We also highlight the importance of how the dataset should be divided into training and testing set for evaluating the histopathology image-based approaches, which has not been considered in previous studies on multispectral histopathology images. PMID:29874262

Motor Oil Classification using Color Histograms and Pattern Recognition Techniques.

PubMed

Ahmadi, Shiva; Mani-Varnosfaderani, Ahmad; Habibi, Biuck

2018-04-20

Motor oil classification is important for quality control and the identification of oil adulteration. In thiswork, we propose a simple, rapid, inexpensive and nondestructive approach based on image analysis and pattern recognition techniques for the classification of nine different types of motor oils according to their corresponding color histograms. For this, we applied color histogram in different color spaces such as red green blue (RGB), grayscale, and hue saturation intensity (HSI) in order to extract features that can help with the classification procedure. These color histograms and their combinations were used as input for model development and then were statistically evaluated by using linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machine (SVM) techniques. Here, two common solutions for solving a multiclass classification problem were applied: (1) transformation to binary classification problem using a one-against-all (OAA) approach and (2) extension from binary classifiers to a single globally optimized multilabel classification model. In the OAA strategy, LDA, QDA, and SVM reached up to 97% in terms of accuracy, sensitivity, and specificity for both the training and test sets. In extension from binary case, despite good performances by the SVM classification model, QDA and LDA provided better results up to 92% for RGB-grayscale-HSI color histograms and up to 93% for the HSI color map, respectively. In order to reduce the numbers of independent variables for modeling, a principle component analysis algorithm was used. Our results suggest that the proposed method is promising for the identification and classification of different types of motor oils.

Multiple and Single Green Area Measurements and Classification Using Phantom Images in Comparison with Derived Experimental Law

NASA Astrophysics Data System (ADS)

Abu-Zaid, N. A. M.

2017-11-01

In many circumstances, it is difficult for humans to reach some areas, due to its topography, personal safety, or security regulations in the country. Governments and persons need to calculate those areas and classify the green parts for reclamation to benefit from it.To solve this problem, this research proposes to use a phantom air plane to capture a digital image for the targeted area, then use a segmentation algorithm to separate the green space and calculate it's area. It was necessary to deal with two problems. The first is the variable elevation at which an image was taken, which leads to a change in the physical area of each pixel. To overcome this problem a fourth degree polynomial was fit to some experimental data. The second problem was the existence of different unconnected pieces of green areas in a single image, but we might be interested only in one of them. To solve this problem, the probability of classifying the targeted area as green was increased, while the probability of other untargeted sections was decreased by the inclusion of parts of it as non-green. A practical law was also devised to measure the target area in the digital image for comparison purposes with practical measurements and the polynomial fit.

Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations.

PubMed

Fabelo, Himar; Ortega, Samuel; Ravi, Daniele; Kiran, B Ravi; Sosa, Coralia; Bulters, Diederik; Callicó, Gustavo M; Bulstrode, Harry; Szolna, Adam; Piñeiro, Juan F; Kabwama, Silvester; Madroñal, Daniel; Lazcano, Raquel; J-O'Shanahan, Aruma; Bisshopp, Sara; Hernández, María; Báez, Abelardo; Yang, Guang-Zhong; Stanciulescu, Bogdan; Salvador, Rubén; Juárez, Eduardo; Sarmiento, Roberto

2018-01-01

Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal brain by these tumors makes their accurate identification by the naked eye difficult. Since surgery is the common treatment for brain cancer, an accurate radical resection of the tumor leads to improved survival rates for patients. However, the identification of the tumor boundaries during surgery is challenging. Hyperspectral imaging is a non-contact, non-ionizing and non-invasive technique suitable for medical diagnosis. This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor. The algorithm proposed in this study to approach an efficient solution consists of a hybrid framework that combines both supervised and unsupervised machine learning methods. Firstly, a supervised pixel-wise classification using a Support Vector Machine classifier is performed. The generated classification map is spatially homogenized using a one-band representation of the HS cube, employing the Fixed Reference t-Stochastic Neighbors Embedding dimensional reduction algorithm, and performing a K-Nearest Neighbors filtering. The information generated by the supervised stage is combined with a segmentation map obtained via unsupervised clustering employing a Hierarchical K-Means algorithm. The fusion is performed using a majority voting approach that associates each cluster with a certain class. To evaluate the proposed approach, five hyperspectral images of surface of the brain affected by glioblastoma tumor in vivo from five different patients have been used. The final classification maps obtained have been analyzed and validated by specialists. These preliminary results are promising, obtaining an accurate delineation of the tumor area.

Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations

PubMed Central

Kabwama, Silvester; Madroñal, Daniel; Lazcano, Raquel; J-O’Shanahan, Aruma; Bisshopp, Sara; Hernández, María; Báez, Abelardo; Yang, Guang-Zhong; Stanciulescu, Bogdan; Salvador, Rubén; Juárez, Eduardo; Sarmiento, Roberto

2018-01-01

Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal brain by these tumors makes their accurate identification by the naked eye difficult. Since surgery is the common treatment for brain cancer, an accurate radical resection of the tumor leads to improved survival rates for patients. However, the identification of the tumor boundaries during surgery is challenging. Hyperspectral imaging is a non-contact, non-ionizing and non-invasive technique suitable for medical diagnosis. This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor. The algorithm proposed in this study to approach an efficient solution consists of a hybrid framework that combines both supervised and unsupervised machine learning methods. Firstly, a supervised pixel-wise classification using a Support Vector Machine classifier is performed. The generated classification map is spatially homogenized using a one-band representation of the HS cube, employing the Fixed Reference t-Stochastic Neighbors Embedding dimensional reduction algorithm, and performing a K-Nearest Neighbors filtering. The information generated by the supervised stage is combined with a segmentation map obtained via unsupervised clustering employing a Hierarchical K-Means algorithm. The fusion is performed using a majority voting approach that associates each cluster with a certain class. To evaluate the proposed approach, five hyperspectral images of surface of the brain affected by glioblastoma tumor in vivo from five different patients have been used. The final classification maps obtained have been analyzed and validated by specialists. These preliminary results are promising, obtaining an accurate delineation of the tumor area. PMID:29554126

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce

PubMed Central

Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan

2016-01-01

A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data. PMID:27304987

The brain MRI classification problem from wavelets perspective

NASA Astrophysics Data System (ADS)

Bendib, Mohamed M.; Merouani, Hayet F.; Diaba, Fatma

2015-02-01

Haar and Daubechies 4 (DB4) are the most used wavelets for brain MRI (Magnetic Resonance Imaging) classification. The former is simple and fast to compute while the latter is more complex and offers a better resolution. This paper explores the potential of both of them in performing Normal versus Pathological discrimination on the one hand, and Multiclassification on the other hand. The Whole Brain Atlas is used as a validation database, and the Random Forest (RF) algorithm is employed as a learning approach. The achieved results are discussed and statistically compared.

Learning to rank image tags with limited training examples.

PubMed

Songhe Feng; Zheyun Feng; Rong Jin

2015-04-01

With an increasing number of images that are available in social media, image annotation has emerged as an important research topic due to its application in image matching and retrieval. Most studies cast image annotation into a multilabel classification problem. The main shortcoming of this approach is that it requires a large number of training images with clean and complete annotations in order to learn a reliable model for tag prediction. We address this limitation by developing a novel approach that combines the strength of tag ranking with the power of matrix recovery. Instead of having to make a binary decision for each tag, our approach ranks tags in the descending order of their relevance to the given image, significantly simplifying the problem. In addition, the proposed method aggregates the prediction models for different tags into a matrix, and casts tag ranking into a matrix recovery problem. It introduces the matrix trace norm to explicitly control the model complexity, so that a reliable prediction model can be learned for tag ranking even when the tag space is large and the number of training images is limited. Experiments on multiple well-known image data sets demonstrate the effectiveness of the proposed framework for tag ranking compared with the state-of-the-art approaches for image annotation and tag ranking.

Status report: Data management program algorithm evaluation activity at Marshall Space Flight Center

NASA Technical Reports Server (NTRS)

Jayroe, R. R., Jr.

1977-01-01

An algorithm evaluation activity was initiated to study the problems associated with image processing by assessing the independent and interdependent effects of registration, compression, and classification techniques on LANDSAT data for several discipline applications. The objective of the activity was to make recommendations on selected applicable image processing algorithms in terms of accuracy, cost, and timeliness or to propose alternative ways of processing the data. As a means of accomplishing this objective, an Image Coding Panel was established. The conduct of the algorithm evaluation is described.

Method of radiometric quality assessment of NIR images acquired with a custom sensor mounted on an unmanned aerial vehicle

NASA Astrophysics Data System (ADS)

Wierzbicki, Damian; Fryskowska, Anna; Kedzierski, Michal; Wojtkowska, Michalina; Delis, Paulina

2018-01-01

Unmanned aerial vehicles are suited to various photogrammetry and remote sensing missions. Such platforms are equipped with various optoelectronic sensors imaging in the visible and infrared spectral ranges and also thermal sensors. Nowadays, near-infrared (NIR) images acquired from low altitudes are often used for producing orthophoto maps for precision agriculture among other things. One major problem results from the application of low-cost custom and compact NIR cameras with wide-angle lenses introducing vignetting. In numerous cases, such cameras acquire low radiometric quality images depending on the lighting conditions. The paper presents a method of radiometric quality assessment of low-altitude NIR imagery data from a custom sensor. The method utilizes statistical analysis of NIR images. The data used for the analyses were acquired from various altitudes in various weather and lighting conditions. An objective NIR imagery quality index was determined as a result of the research. The results obtained using this index enabled the classification of images into three categories: good, medium, and low radiometric quality. The classification makes it possible to determine the a priori error of the acquired images and assess whether a rerun of the photogrammetric flight is necessary.

High resolution through-the-wall radar image based on beamspace eigenstructure subspace methods

NASA Astrophysics Data System (ADS)

Yoon, Yeo-Sun; Amin, Moeness G.

2008-04-01

Through-the-wall imaging (TWI) is a challenging problem, even if the wall parameters and characteristics are known to the system operator. Proper target classification and correct imaging interpretation require the application of high resolution techniques using limited array size. In inverse synthetic aperture radar (ISAR), signal subspace methods such as Multiple Signal Classification (MUSIC) are used to obtain high resolution imaging. In this paper, we adopt signal subspace methods and apply them to the 2-D spectrum obtained from the delay-andsum beamforming image. This is in contrast to ISAR, where raw data, in frequency and angle, is directly used to form the estimate of the covariance matrix and array response vector. Using beams rather than raw data has two main advantages, namely, it improves the signal-to-noise ratio (SNR) and can correctly image typical indoor extended targets, such as tables and cabinets, as well as point targets. The paper presents both simulated and experimental results using synthesized and real data. It compares the performance of beam-space MUSIC and Capon beamformer. The experimental data is collected at the test facility in the Radar Imaging Laboratory, Villanova University.

Pattern recognition and image processing for environmental monitoring

NASA Astrophysics Data System (ADS)

Siddiqui, Khalid J.; Eastwood, DeLyle

1999-12-01

Pattern recognition (PR) and signal/image processing methods are among the most powerful tools currently available for noninvasively examining spectroscopic and other chemical data for environmental monitoring. Using spectral data, these systems have found a variety of applications employing analytical techniques for chemometrics such as gas chromatography, fluorescence spectroscopy, etc. An advantage of PR approaches is that they make no a prior assumption regarding the structure of the patterns. However, a majority of these systems rely on human judgment for parameter selection and classification. A PR problem is considered as a composite of four subproblems: pattern acquisition, feature extraction, feature selection, and pattern classification. One of the basic issues in PR approaches is to determine and measure the features useful for successful classification. Selection of features that contain the most discriminatory information is important because the cost of pattern classification is directly related to the number of features used in the decision rules. The state of the spectral techniques as applied to environmental monitoring is reviewed. A spectral pattern classification system combining the above components and automatic decision-theoretic approaches for classification is developed. It is shown how such a system can be used for analysis of large data sets, warehousing, and interpretation. In a preliminary test, the classifier was used to classify synchronous UV-vis fluorescence spectra of relatively similar petroleum oils with reasonable success.

Automated segmentation and feature extraction of product inspection items

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1997-03-01

X-ray film and linescan images of pistachio nuts on conveyor trays for product inspection are considered. The final objective is the categorization of pistachios into good, blemished and infested nuts. A crucial step before classification is the separation of touching products and the extraction of features essential for classification. This paper addresses new detection and segmentation algorithms to isolate touching or overlapping items. These algorithms employ a new filter, a new watershed algorithm, and morphological processing to produce nutmeat-only images. Tests on a large database of x-ray film and real-time x-ray linescan images of around 2900 small, medium and large nuts showed excellent segmentation results. A new technique to detect and segment dark regions in nutmeat images is also presented and tested on approximately 300 x-ray film and approximately 300 real-time linescan x-ray images with 95-97 percent detection and correct segmentation. New algorithms are described that determine nutmeat fill ratio and locate splits in nutmeat. The techniques formulated in this paper are of general use in many different product inspection and computer vision problems.

A hierarchical knowledge-based approach for retrieving similar medical images described with semantic annotations

PubMed Central

Kurtz, Camille; Beaulieu, Christopher F.; Napel, Sandy; Rubin, Daniel L.

2014-01-01

Computer-assisted image retrieval applications could assist radiologist interpretations by identifying similar images in large archives as a means to providing decision support. However, the semantic gap between low-level image features and their high level semantics may impair the system performances. Indeed, it can be challenging to comprehensively characterize the images using low-level imaging features to fully capture the visual appearance of diseases on images, and recently the use of semantic terms has been advocated to provide semantic descriptions of the visual contents of images. However, most of the existing image retrieval strategies do not consider the intrinsic properties of these terms during the comparison of the images beyond treating them as simple binary (presence/absence) features. We propose a new framework that includes semantic features in images and that enables retrieval of similar images in large databases based on their semantic relations. It is based on two main steps: (1) annotation of the images with semantic terms extracted from an ontology, and (2) evaluation of the similarity of image pairs by computing the similarity between the terms using the Hierarchical Semantic-Based Distance (HSBD) coupled to an ontological measure. The combination of these two steps provides a means of capturing the semantic correlations among the terms used to characterize the images that can be considered as a potential solution to deal with the semantic gap problem. We validate this approach in the context of the retrieval and the classification of 2D regions of interest (ROIs) extracted from computed tomographic (CT) images of the liver. Under this framework, retrieval accuracy of more than 0.96 was obtained on a 30-images dataset using the Normalized Discounted Cumulative Gain (NDCG) index that is a standard technique used to measure the effectiveness of information retrieval algorithms when a separate reference standard is available. Classification results of more than 95% were obtained on a 77-images dataset. For comparison purpose, the use of the Earth Mover's Distance (EMD), which is an alternative distance metric that considers all the existing relations among the terms, led to results retrieval accuracy of 0.95 and classification results of 93% with a higher computational cost. The results provided by the presented framework are competitive with the state-of-the-art and emphasize the usefulness of the proposed methodology for radiology image retrieval and classification. PMID:24632078

Automated connectionist-geostatistical classification as an approach to identify sea ice and land ice types, properties and provinces

NASA Astrophysics Data System (ADS)

Goetz-Weiss, L. R.; Herzfeld, U. C.; Trantow, T.; Hunke, E. C.; Maslanik, J. A.; Crocker, R. I.

2016-12-01

An important problem in model-data comparison is the identification of parameters that can be extracted from observational data as well as used in numerical models, which are typically based on idealized physical processes. Here, we present a suite of approaches to characterization and classification of sea ice and land ice types, properties and provinces based on several types of remote-sensing data. Applications will be given to not only illustrate the approach, but employ it in model evaluation and understanding of physical processes. (1) In a geostatistical characterization, spatial sea-ice properties in the Chukchi and Beaufort Sea and in Elsoon Lagoon are derived from analysis of RADARSAT and ERS-2 SAR data. (2) The analysis is taken further by utilizing multi-parameter feature vectors as inputs for unsupervised and supervised statistical classification, which facilitates classification of different sea-ice types. (3) Characteristic sea-ice parameters, as resultant from the classification, can then be applied in model evaluation, as demonstrated for the ridging scheme of the Los Alamos sea ice model, CICE, using high-resolution altimeter and image data collected from unmanned aircraft over Fram Strait during the Characterization of Arctic Sea Ice Experiment (CASIE). The characteristic parameters chosen in this application are directly related to deformation processes, which also underly the ridging scheme. (4) The method that is capable of the most complex classification tasks is the connectionist-geostatistical classification method. This approach has been developed to identify currently up to 18 different crevasse types in order to map progression of the surge through the complex Bering-Bagley Glacier System, Alaska, in 2011-2014. The analysis utilizes airborne altimeter data and video image data and satellite image data. Results of the crevasse classification are compare to fracture modeling and found to match.

Interpreting support vector machine models for multivariate group wise analysis in neuroimaging

PubMed Central

Gaonkar, Bilwaj; Shinohara, Russell T; Davatzikos, Christos

2015-01-01

Machine learning based classification algorithms like support vector machines (SVMs) have shown great promise for turning a high dimensional neuroimaging data into clinically useful decision criteria. However, tracing imaging based patterns that contribute significantly to classifier decisions remains an open problem. This is an issue of critical importance in imaging studies seeking to determine which anatomical or physiological imaging features contribute to the classifier’s decision, thereby allowing users to critically evaluate the findings of such machine learning methods and to understand disease mechanisms. The majority of published work addresses the question of statistical inference for support vector classification using permutation tests based on SVM weight vectors. Such permutation testing ignores the SVM margin, which is critical in SVM theory. In this work we emphasize the use of a statistic that explicitly accounts for the SVM margin and show that the null distributions associated with this statistic are asymptotically normal. Further, our experiments show that this statistic is a lot less conservative as compared to weight based permutation tests and yet specific enough to tease out multivariate patterns in the data. Thus, we can better understand the multivariate patterns that the SVM uses for neuroimaging based classification. PMID:26210913

Binary Image Classification: A Genetic Programming Approach to the Problem of Limited Training Instances.

PubMed

Al-Sahaf, Harith; Zhang, Mengjie; Johnston, Mark

2016-01-01

In the computer vision and pattern recognition fields, image classification represents an important yet difficult task. It is a challenge to build effective computer models to replicate the remarkable ability of the human visual system, which relies on only one or a few instances to learn a completely new class or an object of a class. Recently we proposed two genetic programming (GP) methods, one-shot GP and compound-GP, that aim to evolve a program for the task of binary classification in images. The two methods are designed to use only one or a few instances per class to evolve the model. In this study, we investigate these two methods in terms of performance, robustness, and complexity of the evolved programs. We use ten data sets that vary in difficulty to evaluate these two methods. We also compare them with two other GP and six non-GP methods. The results show that one-shot GP and compound-GP outperform or achieve results comparable to competitor methods. Moreover, the features extracted by these two methods improve the performance of other classifiers with handcrafted features and those extracted by a recently developed GP-based method in most cases.

A comprehensive analysis of earthquake damage patterns using high dimensional model representation feature selection

NASA Astrophysics Data System (ADS)

Taşkin Kaya, Gülşen

2013-10-01

Recently, earthquake damage assessment using satellite images has been a very popular ongoing research direction. Especially with the availability of very high resolution (VHR) satellite images, a quite detailed damage map based on building scale has been produced, and various studies have also been conducted in the literature. As the spatial resolution of satellite images increases, distinguishability of damage patterns becomes more cruel especially in case of using only the spectral information during classification. In order to overcome this difficulty, textural information needs to be involved to the classification to improve the visual quality and reliability of damage map. There are many kinds of textural information which can be derived from VHR satellite images depending on the algorithm used. However, extraction of textural information and evaluation of them have been generally a time consuming process especially for the large areas affected from the earthquake due to the size of VHR image. Therefore, in order to provide a quick damage map, the most useful features describing damage patterns needs to be known in advance as well as the redundant features. In this study, a very high resolution satellite image after Iran, Bam earthquake was used to identify the earthquake damage. Not only the spectral information, textural information was also used during the classification. For textural information, second order Haralick features were extracted from the panchromatic image for the area of interest using gray level co-occurrence matrix with different size of windows and directions. In addition to using spatial features in classification, the most useful features representing the damage characteristic were selected with a novel feature selection method based on high dimensional model representation (HDMR) giving sensitivity of each feature during classification. The method called HDMR was recently proposed as an efficient tool to capture the input-output relationships in high-dimensional systems for many problems in science and engineering. The HDMR method is developed to improve the efficiency of the deducing high dimensional behaviors. The method is formed by a particular organization of low dimensional component functions, in which each function is the contribution of one or more input variables to the output variables.

A Neural-Network-Based Semi-Automated Geospatial Classification Tool

NASA Astrophysics Data System (ADS)

Hale, R. G.; Herzfeld, U. C.

2014-12-01

North America's largest glacier system, the Bering Bagley Glacier System (BBGS) in Alaska, surged in 2011-2013, as shown by rapid mass transfer, elevation change, and heavy crevassing. Little is known about the physics controlling surge glaciers' semi-cyclic patterns; therefore, it is crucial to collect and analyze as much data as possible so that predictive models can be made. In addition, physical signs frozen in ice in the form of crevasses may help serve as a warning for future surges. The BBGS surge provided an opportunity to develop an automated classification tool for crevasse classification based on imagery collected from small aircraft. The classification allows one to link image classification to geophysical processes associated with ice deformation. The tool uses an approach that employs geostatistical functions and a feed-forward perceptron with error back-propagation. The connectionist-geostatistical approach uses directional experimental (discrete) variograms to parameterize images into a form that the Neural Network (NN) can recognize. In an application to preform analysis on airborne video graphic data from the surge of the BBGS, an NN was able to distinguish 18 different crevasse classes with 95 percent or higher accuracy, for over 3,000 images. Recognizing that each surge wave results in different crevasse types and that environmental conditions affect the appearance in imagery, we designed the tool's semi-automated pre-training algorithm to be adaptable. The tool can be optimized to specific settings and variables of image analysis: (airborne and satellite imagery, different camera types, observation altitude, number and types of classes, and resolution). The generalization of the classification tool brings three important advantages: (1) multiple types of problems in geophysics can be studied, (2) the training process is sufficiently formalized to allow non-experts in neural nets to perform the training process, and (3) the time required to manually pre-sort imagery into classes is greatly reduced.

Exploring point-cloud features from partial body views for gender classification

NASA Astrophysics Data System (ADS)

Fouts, Aaron; McCoppin, Ryan; Rizki, Mateen; Tamburino, Louis; Mendoza-Schrock, Olga

2012-06-01

In this paper we extend a previous exploration of histogram features extracted from 3D point cloud images of human subjects for gender discrimination. Feature extraction used a collection of concentric cylinders to define volumes for counting 3D points. The histogram features are characterized by a rotational axis and a selected set of volumes derived from the concentric cylinders. The point cloud images are drawn from the CAESAR anthropometric database provided by the Air Force Research Laboratory (AFRL) Human Effectiveness Directorate and SAE International. This database contains approximately 4400 high resolution LIDAR whole body scans of carefully posed human subjects. Success from our previous investigation was based on extracting features from full body coverage which required integration of multiple camera images. With the full body coverage, the central vertical body axis and orientation are readily obtainable; however, this is not the case with a one camera view providing less than one half body coverage. Assuming that the subjects are upright, we need to determine or estimate the position of the vertical axis and the orientation of the body about this axis relative to the camera. In past experiments the vertical axis was located through the center of mass of torso points projected on the ground plane and the body orientation derived using principle component analysis. In a natural extension of our previous work to partial body views, the absence of rotational invariance about the cylindrical axis greatly increases the difficulty for gender classification. Even the problem of estimating the axis is no longer simple. We describe some simple feasibility experiments that use partial image histograms. Here, the cylindrical axis is assumed to be known. We also discuss experiments with full body images that explore the sensitivity of classification accuracy relative to displacements of the cylindrical axis. Our initial results provide the basis for further investigation of more complex partial body viewing problems and new methods for estimating the two position coordinates for the axis location and the unknown body orientation angle.

A human visual based binarization technique for histological images

NASA Astrophysics Data System (ADS)

Shreyas, Kamath K. M.; Rajendran, Rahul; Panetta, Karen; Agaian, Sos

2017-05-01

In the field of vision-based systems for object detection and classification, thresholding is a key pre-processing step. Thresholding is a well-known technique for image segmentation. Segmentation of medical images, such as Computed Axial Tomography (CAT), Magnetic Resonance Imaging (MRI), X-Ray, Phase Contrast Microscopy, and Histological images, present problems like high variability in terms of the human anatomy and variation in modalities. Recent advances made in computer-aided diagnosis of histological images help facilitate detection and classification of diseases. Since most pathology diagnosis depends on the expertise and ability of the pathologist, there is clearly a need for an automated assessment system. Histological images are stained to a specific color to differentiate each component in the tissue. Segmentation and analysis of such images is problematic, as they present high variability in terms of color and cell clusters. This paper presents an adaptive thresholding technique that aims at segmenting cell structures from Haematoxylin and Eosin stained images. The thresholded result can further be used by pathologists to perform effective diagnosis. The effectiveness of the proposed method is analyzed by visually comparing the results to the state of art thresholding methods such as Otsu, Niblack, Sauvola, Bernsen, and Wolf. Computer simulations demonstrate the efficiency of the proposed method in segmenting critical information.

Locality constrained joint dynamic sparse representation for local matching based face recognition.

PubMed

Wang, Jianzhong; Yi, Yugen; Zhou, Wei; Shi, Yanjiao; Qi, Miao; Zhang, Ming; Zhang, Baoxue; Kong, Jun

2014-01-01

Recently, Sparse Representation-based Classification (SRC) has attracted a lot of attention for its applications to various tasks, especially in biometric techniques such as face recognition. However, factors such as lighting, expression, pose and disguise variations in face images will decrease the performances of SRC and most other face recognition techniques. In order to overcome these limitations, we propose a robust face recognition method named Locality Constrained Joint Dynamic Sparse Representation-based Classification (LCJDSRC) in this paper. In our method, a face image is first partitioned into several smaller sub-images. Then, these sub-images are sparsely represented using the proposed locality constrained joint dynamic sparse representation algorithm. Finally, the representation results for all sub-images are aggregated to obtain the final recognition result. Compared with other algorithms which process each sub-image of a face image independently, the proposed algorithm regards the local matching-based face recognition as a multi-task learning problem. Thus, the latent relationships among the sub-images from the same face image are taken into account. Meanwhile, the locality information of the data is also considered in our algorithm. We evaluate our algorithm by comparing it with other state-of-the-art approaches. Extensive experiments on four benchmark face databases (ORL, Extended YaleB, AR and LFW) demonstrate the effectiveness of LCJDSRC.

Wide field imaging - I. Applications of neural networks to object detection and star/galaxy classification

NASA Astrophysics Data System (ADS)

Andreon, S.; Gargiulo, G.; Longo, G.; Tagliaferri, R.; Capuano, N.

2000-12-01

Astronomical wide-field imaging performed with new large-format CCD detectors poses data reduction problems of unprecedented scale, which are difficult to deal with using traditional interactive tools. We present here NExt (Neural Extractor), a new neural network (NN) based package capable of detecting objects and performing both deblending and star/galaxy classification in an automatic way. Traditionally, in astronomical images, objects are first distinguished from the noisy background by searching for sets of connected pixels having brightnesses above a given threshold; they are then classified as stars or as galaxies through diagnostic diagrams having variables chosen according to the astronomer's taste and experience. In the extraction step, assuming that images are well sampled, NExt requires only the simplest a priori definition of `what an object is' (i.e. it keeps all structures composed of more than one pixel) and performs the detection via an unsupervised NN, approaching detection as a clustering problem that has been thoroughly studied in the artificial intelligence literature. The first part of the NExt procedure consists of an optimal compression of the redundant information contained in the pixels via a mapping from pixel intensities to a subspace individualized through principal component analysis. At magnitudes fainter than the completeness limit, stars are usually almost indistinguishable from galaxies, and therefore the parameters characterizing the two classes do not lie in disconnected subspaces, thus preventing the use of unsupervised methods. We therefore adopted a supervised NN (i.e. a NN that first finds the rules to classify objects from examples and then applies them to the whole data set). In practice, each object is classified depending on its membership of the regions mapping the input feature space in the training set. In order to obtain an objective and reliable classification, instead of using an arbitrarily defined set of features we use a NN to select the most significant features among the large number of measured ones, and then we use these selected features to perform the classification task. In order to optimize the performance of the system, we implemented and tested several different models of NN. The comparison of the NExt performance with that of the best detection and classification package known to the authors (SExtractor) shows that NExt is at least as effective as the best traditional packages.

Objected-oriented remote sensing image classification method based on geographic ontology model

NASA Astrophysics Data System (ADS)

Chu, Z.; Liu, Z. J.; Gu, H. Y.

2016-11-01

Nowadays, with the development of high resolution remote sensing image and the wide application of laser point cloud data, proceeding objected-oriented remote sensing classification based on the characteristic knowledge of multi-source spatial data has been an important trend on the field of remote sensing image classification, which gradually replaced the traditional method through improving algorithm to optimize image classification results. For this purpose, the paper puts forward a remote sensing image classification method that uses the he characteristic knowledge of multi-source spatial data to build the geographic ontology semantic network model, and carries out the objected-oriented classification experiment to implement urban features classification, the experiment uses protégé software which is developed by Stanford University in the United States, and intelligent image analysis software—eCognition software as the experiment platform, uses hyperspectral image and Lidar data that is obtained through flight in DaFeng City of JiangSu as the main data source, first of all, the experiment uses hyperspectral image to obtain feature knowledge of remote sensing image and related special index, the second, the experiment uses Lidar data to generate nDSM(Normalized DSM, Normalized Digital Surface Model),obtaining elevation information, the last, the experiment bases image feature knowledge, special index and elevation information to build the geographic ontology semantic network model that implement urban features classification, the experiment results show that, this method is significantly higher than the traditional classification algorithm on classification accuracy, especially it performs more evidently on the respect of building classification. The method not only considers the advantage of multi-source spatial data, for example, remote sensing image, Lidar data and so on, but also realizes multi-source spatial data knowledge integration and application of the knowledge to the field of remote sensing image classification, which provides an effective way for objected-oriented remote sensing image classification in the future.

Cloud-Based NoSQL Open Database of Pulmonary Nodules for Computer-Aided Lung Cancer Diagnosis and Reproducible Research.

PubMed

Ferreira Junior, José Raniery; Oliveira, Marcelo Costa; de Azevedo-Marques, Paulo Mazzoncini

2016-12-01

Lung cancer is the leading cause of cancer-related deaths in the world, and its main manifestation is pulmonary nodules. Detection and classification of pulmonary nodules are challenging tasks that must be done by qualified specialists, but image interpretation errors make those tasks difficult. In order to aid radiologists on those hard tasks, it is important to integrate the computer-based tools with the lesion detection, pathology diagnosis, and image interpretation processes. However, computer-aided diagnosis research faces the problem of not having enough shared medical reference data for the development, testing, and evaluation of computational methods for diagnosis. In order to minimize this problem, this paper presents a public nonrelational document-oriented cloud-based database of pulmonary nodules characterized by 3D texture attributes, identified by experienced radiologists and classified in nine different subjective characteristics by the same specialists. Our goal with the development of this database is to improve computer-aided lung cancer diagnosis and pulmonary nodule detection and classification research through the deployment of this database in a cloud Database as a Service framework. Pulmonary nodule data was provided by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), image descriptors were acquired by a volumetric texture analysis, and database schema was developed using a document-oriented Not only Structured Query Language (NoSQL) approach. The proposed database is now with 379 exams, 838 nodules, and 8237 images, 4029 of them are CT scans and 4208 manually segmented nodules, and it is allocated in a MongoDB instance on a cloud infrastructure.

Classification of foods by transferring knowledge from ImageNet dataset

NASA Astrophysics Data System (ADS)

Heravi, Elnaz J.; Aghdam, Hamed H.; Puig, Domenec

2017-03-01

Automatic classification of foods is a way to control food intake and tackle with obesity. However, it is a challenging problem since foods are highly deformable and complex objects. Results on ImageNet dataset have revealed that Convolutional Neural Network has a great expressive power to model natural objects. Nonetheless, it is not trivial to train a ConvNet from scratch for classification of foods. This is due to the fact that ConvNets require large datasets and to our knowledge there is not a large public dataset of food for this purpose. Alternative solution is to transfer knowledge from trained ConvNets to the domain of foods. In this work, we study how transferable are state-of-art ConvNets to the task of food classification. We also propose a method for transferring knowledge from a bigger ConvNet to a smaller ConvNet by keeping its accuracy similar to the bigger ConvNet. Our experiments on UECFood256 datasets show that Googlenet, VGG and residual networks produce comparable results if we start transferring knowledge from appropriate layer. In addition, we show that our method is able to effectively transfer knowledge to the smaller ConvNet using unlabeled samples.

Classification of Clouds in Satellite Imagery Using Adaptive Fuzzy Sparse Representation.

PubMed

Jin, Wei; Gong, Fei; Zeng, Xingbin; Fu, Randi

2016-12-16

Automatic cloud detection and classification using satellite cloud imagery have various meteorological applications such as weather forecasting and climate monitoring. Cloud pattern analysis is one of the research hotspots recently. Since satellites sense the clouds remotely from space, and different cloud types often overlap and convert into each other, there must be some fuzziness and uncertainty in satellite cloud imagery. Satellite observation is susceptible to noises, while traditional cloud classification methods are sensitive to noises and outliers; it is hard for traditional cloud classification methods to achieve reliable results. To deal with these problems, a satellite cloud classification method using adaptive fuzzy sparse representation-based classification (AFSRC) is proposed. Firstly, by defining adaptive parameters related to attenuation rate and critical membership, an improved fuzzy membership is introduced to accommodate the fuzziness and uncertainty of satellite cloud imagery; secondly, by effective combination of the improved fuzzy membership function and sparse representation-based classification (SRC), atoms in training dictionary are optimized; finally, an adaptive fuzzy sparse representation classifier for cloud classification is proposed. Experiment results on FY-2G satellite cloud image show that, the proposed method not only improves the accuracy of cloud classification, but also has strong stability and adaptability with high computational efficiency.

An ensemble learning system for a 4-way classification of Alzheimer's disease and mild cognitive impairment.

PubMed

Yao, Dongren; Calhoun, Vince D; Fu, Zening; Du, Yuhui; Sui, Jing

2018-05-15

Discriminating Alzheimer's disease (AD) from its prodromal form, mild cognitive impairment (MCI), is a significant clinical problem that may facilitate early diagnosis and intervention, in which a more challenging issue is to classify MCI subtypes, i.e., those who eventually convert to AD (cMCI) versus those who do not (MCI). To solve this difficult 4-way classification problem (AD, MCI, cMCI and healthy controls), a competition was hosted by Kaggle to invite the scientific community to apply their machine learning approaches on pre-processed sets of T1-weighted magnetic resonance images (MRI) data and the demographic information from the international Alzheimer's disease neuroimaging initiative (ADNI) database. This paper summarizes our competition results. We first proposed a hierarchical process by turning the 4-way classification into five binary classification problems. A new feature selection technology based on relative importance was also proposed, aiming to identify a more informative and concise subset from 426 sMRI morphometric and 3 demographic features, to ensure each binary classifier to achieve its highest accuracy. As a result, about 2% of the original features were selected to build a new feature space, which can achieve the final four-way classification with a 54.38% accuracy on testing data through hierarchical grouping, higher than several alternative methods in comparison. More importantly, the selected discriminative features such as hippocampal volume, parahippocampal surface area, and medial orbitofrontal thickness, etc. as well as the MMSE score, are reasonable and consistent with those reported in AD/MCI deficits. In summary, the proposed method provides a new framework for multi-way classification using hierarchical grouping and precise feature selection. Copyright © 2018 Elsevier B.V. All rights reserved.

Bag-of-visual-ngrams for histopathology image classification

NASA Astrophysics Data System (ADS)

López-Monroy, A. Pastor; Montes-y-Gómez, Manuel; Escalante, Hugo Jair; Cruz-Roa, Angel; González, Fabio A.

2013-11-01

This paper describes an extension of the Bag-of-Visual-Words (BoVW) representation for image categorization (IC) of histophatology images. This representation is one of the most used approaches in several high-level computer vision tasks. However, the BoVW representation has an important limitation: the disregarding of spatial information among visual words. This information may be useful to capture discriminative visual-patterns in specific computer vision tasks. In order to overcome this problem we propose the use of visual n-grams. N-grams based-representations are very popular in the field of natural language processing (NLP), in particular within text mining and information retrieval. We propose building a codebook of n-grams and then representing images by histograms of visual n-grams. We evaluate our proposal in the challenging task of classifying histopathology images. The novelty of our proposal lies in the fact that we use n-grams as attributes for a classification model (together with visual-words, i.e., 1-grams). This is common practice within NLP, although, to the best of our knowledge, this idea has not been explored yet within computer vision. We report experimental results in a database of histopathology images where our proposed method outperforms the traditional BoVWs formulation.

Blind identification of image manipulation type using mixed statistical moments

NASA Astrophysics Data System (ADS)

Jeong, Bo Gyu; Moon, Yong Ho; Eom, Il Kyu

2015-01-01

We present a blind identification of image manipulation types such as blurring, scaling, sharpening, and histogram equalization. Motivated by the fact that image manipulations can change the frequency characteristics of an image, we introduce three types of feature vectors composed of statistical moments. The proposed statistical moments are generated from separated wavelet histograms, the characteristic functions of the wavelet variance, and the characteristic functions of the spatial image. Our method can solve the n-class classification problem. Through experimental simulations, we demonstrate that our proposed method can achieve high performance in manipulation type detection. The average rate of the correctly identified manipulation types is as high as 99.22%, using 10,800 test images and six manipulation types including the authentic image.

Survey statistics of automated segmentations applied to optical imaging of mammalian cells.

PubMed

Bajcsy, Peter; Cardone, Antonio; Chalfoun, Joe; Halter, Michael; Juba, Derek; Kociolek, Marcin; Majurski, Michael; Peskin, Adele; Simon, Carl; Simon, Mylene; Vandecreme, Antoine; Brady, Mary

2015-10-15

The goal of this survey paper is to overview cellular measurements using optical microscopy imaging followed by automated image segmentation. The cellular measurements of primary interest are taken from mammalian cells and their components. They are denoted as two- or three-dimensional (2D or 3D) image objects of biological interest. In our applications, such cellular measurements are important for understanding cell phenomena, such as cell counts, cell-scaffold interactions, cell colony growth rates, or cell pluripotency stability, as well as for establishing quality metrics for stem cell therapies. In this context, this survey paper is focused on automated segmentation as a software-based measurement leading to quantitative cellular measurements. We define the scope of this survey and a classification schema first. Next, all found and manually filteredpublications are classified according to the main categories: (1) objects of interests (or objects to be segmented), (2) imaging modalities, (3) digital data axes, (4) segmentation algorithms, (5) segmentation evaluations, (6) computational hardware platforms used for segmentation acceleration, and (7) object (cellular) measurements. Finally, all classified papers are converted programmatically into a set of hyperlinked web pages with occurrence and co-occurrence statistics of assigned categories. The survey paper presents to a reader: (a) the state-of-the-art overview of published papers about automated segmentation applied to optical microscopy imaging of mammalian cells, (b) a classification of segmentation aspects in the context of cell optical imaging, (c) histogram and co-occurrence summary statistics about cellular measurements, segmentations, segmented objects, segmentation evaluations, and the use of computational platforms for accelerating segmentation execution, and (d) open research problems to pursue. The novel contributions of this survey paper are: (1) a new type of classification of cellular measurements and automated segmentation, (2) statistics about the published literature, and (3) a web hyperlinked interface to classification statistics of the surveyed papers at https://isg.nist.gov/deepzoomweb/resources/survey/index.html.

A new classification scheme of plastic wastes based upon recycling labels

DOE Office of Scientific and Technical Information (OSTI.GOV)

Özkan, Kemal, E-mail: kozkan@ogu.edu.tr; Ergin, Semih, E-mail: sergin@ogu.edu.tr; Işık, Şahin, E-mail: sahini@ogu.edu.tr

Highlights: • PET, HPDE or PP types of plastics are considered. • An automated classification of plastic bottles based on the feature extraction and classification methods is performed. • The decision mechanism consists of PCA, Kernel PCA, FLDA, SVD and Laplacian Eigenmaps methods. • SVM is selected to achieve the classification task and majority voting technique is used. - Abstract: Since recycling of materials is widely assumed to be environmentally and economically beneficial, reliable sorting and processing of waste packaging materials such as plastics is very important for recycling with high efficiency. An automated system that can quickly categorize thesemore » materials is certainly needed for obtaining maximum classification while maintaining high throughput. In this paper, first of all, the photographs of the plastic bottles have been taken and several preprocessing steps were carried out. The first preprocessing step is to extract the plastic area of a bottle from the background. Then, the morphological image operations are implemented. These operations are edge detection, noise removal, hole removing, image enhancement, and image segmentation. These morphological operations can be generally defined in terms of the combinations of erosion and dilation. The effect of bottle color as well as label are eliminated using these operations. Secondly, the pixel-wise intensity values of the plastic bottle images have been used together with the most popular subspace and statistical feature extraction methods to construct the feature vectors in this study. Only three types of plastics are considered due to higher existence ratio of them than the other plastic types in the world. The decision mechanism consists of five different feature extraction methods including as Principal Component Analysis (PCA), Kernel PCA (KPCA), Fisher’s Linear Discriminant Analysis (FLDA), Singular Value Decomposition (SVD) and Laplacian Eigenmaps (LEMAP) and uses a simple experimental setup with a camera and homogenous backlighting. Due to the giving global solution for a classification problem, Support Vector Machine (SVM) is selected to achieve the classification task and majority voting technique is used as the decision mechanism. This technique equally weights each classification result and assigns the given plastic object to the class that the most classification results agree on. The proposed classification scheme provides high accuracy rate, and also it is able to run in real-time applications. It can automatically classify the plastic bottle types with approximately 90% recognition accuracy. Besides this, the proposed methodology yields approximately 96% classification rate for the separation of PET or non-PET plastic types. It also gives 92% accuracy for the categorization of non-PET plastic types into HPDE or PP.« less

Unsupervised active learning based on hierarchical graph-theoretic clustering.

PubMed

Hu, Weiming; Hu, Wei; Xie, Nianhua; Maybank, Steve

2009-10-01

Most existing active learning approaches are supervised. Supervised active learning has the following problems: inefficiency in dealing with the semantic gap between the distribution of samples in the feature space and their labels, lack of ability in selecting new samples that belong to new categories that have not yet appeared in the training samples, and lack of adaptability to changes in the semantic interpretation of sample categories. To tackle these problems, we propose an unsupervised active learning framework based on hierarchical graph-theoretic clustering. In the framework, two promising graph-theoretic clustering algorithms, namely, dominant-set clustering and spectral clustering, are combined in a hierarchical fashion. Our framework has some advantages, such as ease of implementation, flexibility in architecture, and adaptability to changes in the labeling. Evaluations on data sets for network intrusion detection, image classification, and video classification have demonstrated that our active learning framework can effectively reduce the workload of manual classification while maintaining a high accuracy of automatic classification. It is shown that, overall, our framework outperforms the support-vector-machine-based supervised active learning, particularly in terms of dealing much more efficiently with new samples whose categories have not yet appeared in the training samples.

Automatic target recognition and detection in infrared imagery under cluttered background

NASA Astrophysics Data System (ADS)

Gundogdu, Erhan; Koç, Aykut; Alatan, A. Aydın.

2017-10-01

Visual object classification has long been studied in visible spectrum by utilizing conventional cameras. Since the labeled images has recently increased in number, it is possible to train deep Convolutional Neural Networks (CNN) with significant amount of parameters. As the infrared (IR) sensor technology has been improved during the last two decades, labeled images extracted from IR sensors have been started to be used for object detection and recognition tasks. We address the problem of infrared object recognition and detection by exploiting 15K images from the real-field with long-wave and mid-wave IR sensors. For feature learning, a stacked denoising autoencoder is trained in this IR dataset. To recognize the objects, the trained stacked denoising autoencoder is fine-tuned according to the binary classification loss of the target object. Once the training is completed, the test samples are propagated over the network, and the probability of the test sample belonging to a class is computed. Moreover, the trained classifier is utilized in a detect-by-classification method, where the classification is performed in a set of candidate object boxes and the maximum confidence score in a particular location is accepted as the score of the detected object. To decrease the computational complexity, the detection step at every frame is avoided by running an efficient correlation filter based tracker. The detection part is performed when the tracker confidence is below a pre-defined threshold. The experiments conducted on the real field images demonstrate that the proposed detection and tracking framework presents satisfactory results for detecting tanks under cluttered background.

Colony image acquisition and segmentation

NASA Astrophysics Data System (ADS)

Wang, W. X.

2007-12-01

For counting of both colonies and plaques, there is a large number of applications including food, dairy, beverages, hygiene, environmental monitoring, water, toxicology, sterility testing, AMES testing, pharmaceuticals, paints, sterile fluids and fungal contamination. Recently, many researchers and developers have made efforts for this kind of systems. By investigation, some existing systems have some problems. The main problems are image acquisition and image segmentation. In order to acquire colony images with good quality, an illumination box was constructed as: the box includes front lightning and back lightning, which can be selected by users based on properties of colony dishes. With the illumination box, lightning can be uniform; colony dish can be put in the same place every time, which make image processing easy. The developed colony image segmentation algorithm consists of the sub-algorithms: (1) image classification; (2) image processing; and (3) colony delineation. The colony delineation algorithm main contain: the procedures based on grey level similarity, on boundary tracing, on shape information and colony excluding. In addition, a number of algorithms are developed for colony analysis. The system has been tested and satisfactory.

Auto-SEIA: simultaneous optimization of image processing and machine learning algorithms

NASA Astrophysics Data System (ADS)

Negro Maggio, Valentina; Iocchi, Luca

2015-02-01

Object classification from images is an important task for machine vision and it is a crucial ingredient for many computer vision applications, ranging from security and surveillance to marketing. Image based object classification techniques properly integrate image processing and machine learning (i.e., classification) procedures. In this paper we present a system for automatic simultaneous optimization of algorithms and parameters for object classification from images. More specifically, the proposed system is able to process a dataset of labelled images and to return a best configuration of image processing and classification algorithms and of their parameters with respect to the accuracy of classification. Experiments with real public datasets are used to demonstrate the effectiveness of the developed system.

Large Scale Crop Classification in Ukraine using Multi-temporal Landsat-8 Images with Missing Data

NASA Astrophysics Data System (ADS)

Kussul, N.; Skakun, S.; Shelestov, A.; Lavreniuk, M. S.

2014-12-01

At present, there are no globally available Earth observation (EO) derived products on crop maps. This issue is being addressed within the Sentinel-2 for Agriculture initiative where a number of test sites (including from JECAM) participate to provide coherent protocols and best practices for various global agriculture systems, and subsequently crop maps from Sentinel-2. One of the problems in dealing with optical images for large territories (more than 10,000 sq. km) is the presence of clouds and shadows that result in having missing values in data sets. In this abstract, a new approach to classification of multi-temporal optical satellite imagery with missing data due to clouds and shadows is proposed. First, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of satellite imagery. SOMs are trained for each spectral band separately using non-missing values. Missing values are restored through a special procedure that substitutes input sample's missing components with neuron's weight coefficients. After missing data restoration, a supervised classification is performed for multi-temporal satellite images. For this, an ensemble of neural networks, in particular multilayer perceptrons (MLPs), is proposed. Ensembling of neural networks is done by the technique of average committee, i.e. to calculate the average class probability over classifiers and select the class with the highest average posterior probability for the given input sample. The proposed approach is applied for large scale crop classification using multi temporal Landsat-8 images for the JECAM test site in Ukraine [1-2]. It is shown that ensemble of MLPs provides better performance than a single neural network in terms of overall classification accuracy and kappa coefficient. The obtained classification map is also validated through estimated crop and forest areas and comparison to official statistics. 1. A.Yu. Shelestov et al., "Geospatial information system for agricultural monitoring," Cybernetics Syst. Anal., vol. 49, no. 1, pp. 124-132, 2013. 2. J. Gallego et al., "Efficiency Assessment of Different Approaches to Crop Classification Based on Satellite and Ground Observations," J. Autom. Inform. Scie., vol. 44, no. 5, pp. 67-80, 2012.

Iris Image Classification Based on Hierarchical Visual Codebook.

PubMed

Zhenan Sun; Hui Zhang; Tieniu Tan; Jianyu Wang

2014-06-01

Iris recognition as a reliable method for personal identification has been well-studied with the objective to assign the class label of each iris image to a unique subject. In contrast, iris image classification aims to classify an iris image to an application specific category, e.g., iris liveness detection (classification of genuine and fake iris images), race classification (e.g., classification of iris images of Asian and non-Asian subjects), coarse-to-fine iris identification (classification of all iris images in the central database into multiple categories). This paper proposes a general framework for iris image classification based on texture analysis. A novel texture pattern representation method called Hierarchical Visual Codebook (HVC) is proposed to encode the texture primitives of iris images. The proposed HVC method is an integration of two existing Bag-of-Words models, namely Vocabulary Tree (VT), and Locality-constrained Linear Coding (LLC). The HVC adopts a coarse-to-fine visual coding strategy and takes advantages of both VT and LLC for accurate and sparse representation of iris texture. Extensive experimental results demonstrate that the proposed iris image classification method achieves state-of-the-art performance for iris liveness detection, race classification, and coarse-to-fine iris identification. A comprehensive fake iris image database simulating four types of iris spoof attacks is developed as the benchmark for research of iris liveness detection.

Artistic image analysis using graph-based learning approaches.

PubMed

Carneiro, Gustavo

2013-08-01

We introduce a new methodology for the problem of artistic image analysis, which among other tasks, involves the automatic identification of visual classes present in an art work. In this paper, we advocate the idea that artistic image analysis must explore a graph that captures the network of artistic influences by computing the similarities in terms of appearance and manual annotation. One of the novelties of our methodology is the proposed formulation that is a principled way of combining these two similarities in a single graph. Using this graph, we show that an efficient random walk algorithm based on an inverted label propagation formulation produces more accurate annotation and retrieval results compared with the following baseline algorithms: bag of visual words, label propagation, matrix completion, and structural learning. We also show that the proposed approach leads to a more efficient inference and training procedures. This experiment is run on a database containing 988 artistic images (with 49 visual classification problems divided into a multiclass problem with 27 classes and 48 binary problems), where we show the inference and training running times, and quantitative comparisons with respect to several retrieval and annotation performance measures.

Lossless Compression of Classification-Map Data

NASA Technical Reports Server (NTRS)

Hua, Xie; Klimesh, Matthew

2009-01-01

A lossless image-data-compression algorithm intended specifically for application to classification-map data is based on prediction, context modeling, and entropy coding. The algorithm was formulated, in consideration of the differences between classification maps and ordinary images of natural scenes, so as to be capable of compressing classification- map data more effectively than do general-purpose image-data-compression algorithms. Classification maps are typically generated from remote-sensing images acquired by instruments aboard aircraft (see figure) and spacecraft. A classification map is a synthetic image that summarizes information derived from one or more original remote-sensing image(s) of a scene. The value assigned to each pixel in such a map is the index of a class that represents some type of content deduced from the original image data for example, a type of vegetation, a mineral, or a body of water at the corresponding location in the scene. When classification maps are generated onboard the aircraft or spacecraft, it is desirable to compress the classification-map data in order to reduce the volume of data that must be transmitted to a ground station.

Retinex Preprocessing for Improved Multi-Spectral Image Classification

NASA Technical Reports Server (NTRS)

Thompson, B.; Rahman, Z.; Park, S.

2000-01-01

The goal of multi-image classification is to identify and label "similar regions" within a scene. The ability to correctly classify a remotely sensed multi-image of a scene is affected by the ability of the classification process to adequately compensate for the effects of atmospheric variations and sensor anomalies. Better classification may be obtained if the multi-image is preprocessed before classification, so as to reduce the adverse effects of image formation. In this paper, we discuss the overall impact on multi-spectral image classification when the retinex image enhancement algorithm is used to preprocess multi-spectral images. The retinex is a multi-purpose image enhancement algorithm that performs dynamic range compression, reduces the dependence on lighting conditions, and generally enhances apparent spatial resolution. The retinex has been successfully applied to the enhancement of many different types of grayscale and color images. We show in this paper that retinex preprocessing improves the spatial structure of multi-spectral images and thus provides better within-class variations than would otherwise be obtained without the preprocessing. For a series of multi-spectral images obtained with diffuse and direct lighting, we show that without retinex preprocessing the class spectral signatures vary substantially with the lighting conditions. Whereas multi-dimensional clustering without preprocessing produced one-class homogeneous regions, the classification on the preprocessed images produced multi-class non-homogeneous regions. This lack of homogeneity is explained by the interaction between different agronomic treatments applied to the regions: the preprocessed images are closer to ground truth. The principle advantage that the retinex offers is that for different lighting conditions classifications derived from the retinex preprocessed images look remarkably "similar", and thus more consistent, whereas classifications derived from the original images, without preprocessing, are much less similar.

Method: automatic segmentation of mitochondria utilizing patch classification, contour pair classification, and automatically seeded level sets

PubMed Central

2012-01-01

Background While progress has been made to develop automatic segmentation techniques for mitochondria, there remains a need for more accurate and robust techniques to delineate mitochondria in serial blockface scanning electron microscopic data. Previously developed texture based methods are limited for solving this problem because texture alone is often not sufficient to identify mitochondria. This paper presents a new three-step method, the Cytoseg process, for automated segmentation of mitochondria contained in 3D electron microscopic volumes generated through serial block face scanning electron microscopic imaging. The method consists of three steps. The first is a random forest patch classification step operating directly on 2D image patches. The second step consists of contour-pair classification. At the final step, we introduce a method to automatically seed a level set operation with output from previous steps. Results We report accuracy of the Cytoseg process on three types of tissue and compare it to a previous method based on Radon-Like Features. At step 1, we show that the patch classifier identifies mitochondria texture but creates many false positive pixels. At step 2, our contour processing step produces contours and then filters them with a second classification step, helping to improve overall accuracy. We show that our final level set operation, which is automatically seeded with output from previous steps, helps to smooth the results. Overall, our results show that use of contour pair classification and level set operations improve segmentation accuracy beyond patch classification alone. We show that the Cytoseg process performs well compared to another modern technique based on Radon-Like Features. Conclusions We demonstrated that texture based methods for mitochondria segmentation can be enhanced with multiple steps that form an image processing pipeline. While we used a random-forest based patch classifier to recognize texture, it would be possible to replace this with other texture identifiers, and we plan to explore this in future work. PMID:22321695

Hyperspectral small animal fluorescence imaging: spectral selection imaging

NASA Astrophysics Data System (ADS)

Leavesley, Silas; Jiang, Yanan; Patsekin, Valery; Hall, Heidi; Vizard, Douglas; Robinson, J. Paul

2008-02-01

Molecular imaging is a rapidly growing area of research, fueled by needs in pharmaceutical drug-development for methods for high-throughput screening, pre-clinical and clinical screening for visualizing tumor growth and drug targeting, and a growing number of applications in the molecular biology fields. Small animal fluorescence imaging employs fluorescent probes to target molecular events in vivo, with a large number of molecular targeting probes readily available. The ease at which new targeting compounds can be developed, the short acquisition times, and the low cost (compared to microCT, MRI, or PET) makes fluorescence imaging attractive. However, small animal fluorescence imaging suffers from high optical scattering, absorption, and autofluorescence. Much of these problems can be overcome through multispectral imaging techniques, which collect images at different fluorescence emission wavelengths, followed by analysis, classification, and spectral deconvolution methods to isolate signals from fluorescence emission. We present an alternative to the current method, using hyperspectral excitation scanning (spectral selection imaging), a technique that allows excitation at any wavelength in the visible and near-infrared wavelength range. In many cases, excitation imaging may be more effective at identifying specific fluorescence signals because of the higher complexity of the fluorophore excitation spectrum. Because the excitation is filtered and not the emission, the resolution limit and image shift imposed by acousto-optic tunable filters have no effect on imager performance. We will discuss design of the imager, optimizing the imager for use in small animal fluorescence imaging, and application of spectral analysis and classification methods for identifying specific fluorescence signals.

Morphological image analysis for classification of gastrointestinal tissues using optical coherence tomography

NASA Astrophysics Data System (ADS)

Garcia-Allende, P. Beatriz; Amygdalos, Iakovos; Dhanapala, Hiruni; Goldin, Robert D.; Hanna, George B.; Elson, Daniel S.

2012-01-01

Computer-aided diagnosis of ophthalmic diseases using optical coherence tomography (OCT) relies on the extraction of thickness and size measures from the OCT images, but such defined layers are usually not observed in emerging OCT applications aimed at "optical biopsy" such as pulmonology or gastroenterology. Mathematical methods such as Principal Component Analysis (PCA) or textural analyses including both spatial textural analysis derived from the two-dimensional discrete Fourier transform (DFT) and statistical texture analysis obtained independently from center-symmetric auto-correlation (CSAC) and spatial grey-level dependency matrices (SGLDM), as well as, quantitative measurements of the attenuation coefficient have been previously proposed to overcome this problem. We recently proposed an alternative approach consisting of a region segmentation according to the intensity variation along the vertical axis and a pure statistical technology for feature quantification. OCT images were first segmented in the axial direction in an automated manner according to intensity. Afterwards, a morphological analysis of the segmented OCT images was employed for quantifying the features that served for tissue classification. In this study, a PCA processing of the extracted features is accomplished to combine their discriminative power in a lower number of dimensions. Ready discrimination of gastrointestinal surgical specimens is attained demonstrating that the approach further surpasses the algorithms previously reported and is feasible for tissue classification in the clinical setting.

Mammographic mass classification based on possibility theory

NASA Astrophysics Data System (ADS)

Hmida, Marwa; Hamrouni, Kamel; Solaiman, Basel; Boussetta, Sana

2017-03-01

Shape and margin features are very important for differentiating between benign and malignant masses in mammographic images. In fact, benign masses are usually round and oval and have smooth contours. However, malignant tumors have generally irregular shape and appear lobulated or speculated in margins. This knowledge suffers from imprecision and ambiguity. Therefore, this paper deals with the problem of mass classification by using shape and margin features while taking into account the uncertainty linked to the degree of truth of the available information and the imprecision related to its content. Thus, in this work, we proposed a novel mass classification approach which provides a possibility based representation of the extracted shape features and builds a possibility knowledge basis in order to evaluate the possibility degree of malignancy and benignity for each mass. For experimentation, the MIAS database was used and the classification results show the great performance of our approach in spite of using simple features.

Resampling approach for anomalous change detection

NASA Astrophysics Data System (ADS)

Theiler, James; Perkins, Simon

2007-04-01

We investigate the problem of identifying pixels in pairs of co-registered images that correspond to real changes on the ground. Changes that are due to environmental differences (illumination, atmospheric distortion, etc.) or sensor differences (focus, contrast, etc.) will be widespread throughout the image, and the aim is to avoid these changes in favor of changes that occur in only one or a few pixels. Formal outlier detection schemes (such as the one-class support vector machine) can identify rare occurrences, but will be confounded by pixels that are "equally rare" in both images: they may be anomalous, but they are not changes. We describe a resampling scheme we have developed that formally addresses both of these issues, and reduces the problem to a binary classification, a problem for which a large variety of machine learning tools have been developed. In principle, the effects of misregistration will manifest themselves as pervasive changes, and our method will be robust against them - but in practice, misregistration remains a serious issue.

Performance Evaluation of Frequency Transform Based Block Classification of Compound Image Segmentation Techniques

NASA Astrophysics Data System (ADS)

Selwyn, Ebenezer Juliet; Florinabel, D. Jemi

2018-04-01

Compound image segmentation plays a vital role in the compression of computer screen images. Computer screen images are images which are mixed with textual, graphical, or pictorial contents. In this paper, we present a comparison of two transform based block classification of compound images based on metrics like speed of classification, precision and recall rate. Block based classification approaches normally divide the compound images into fixed size blocks of non-overlapping in nature. Then frequency transform like Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) are applied over each block. Mean and standard deviation are computed for each 8 × 8 block and are used as features set to classify the compound images into text/graphics and picture/background block. The classification accuracy of block classification based segmentation techniques are measured by evaluation metrics like precision and recall rate. Compound images of smooth background and complex background images containing text of varying size, colour and orientation are considered for testing. Experimental evidence shows that the DWT based segmentation provides significant improvement in recall rate and precision rate approximately 2.3% than DCT based segmentation with an increase in block classification time for both smooth and complex background images.

Recognition Using Hybrid Classifiers.

PubMed

Osadchy, Margarita; Keren, Daniel; Raviv, Dolev

2016-04-01

A canonical problem in computer vision is category recognition (e.g., find all instances of human faces, cars etc., in an image). Typically, the input for training a binary classifier is a relatively small sample of positive examples, and a huge sample of negative examples, which can be very diverse, consisting of images from a large number of categories. The difficulty of the problem sharply increases with the dimension and size of the negative example set. We propose to alleviate this problem by applying a "hybrid" classifier, which replaces the negative samples by a prior, and then finds a hyperplane which separates the positive samples from this prior. The method is extended to kernel space and to an ensemble-based approach. The resulting binary classifiers achieve an identical or better classification rate than SVM, while requiring far smaller memory and lower computational complexity to train and apply.

Mapping and improving frequency, accuracy, and interpretation of land cover change: Classifying coastal Louisiana with 1990, 1993, 1996, and 1999 Landsat Thematic Mapper image data

USGS Publications Warehouse

Nelson, G.; Ramsey, Elijah W.; Rangoonwala, A.

2005-01-01

Landsat Thematic Mapper images and collateral data sources were used to classify the land cover of the Mermentau River Basin within the chenier coastal plain and the adjacent uplands of Louisiana, USA. Landcover classes followed that of the National Oceanic and Atmospheric Administration's Coastal Change Analysis Program; however, classification methods needed to be developed to meet these national standards. Our first classification was limited to the Mermentau River Basin (MRB) in southcentral Louisiana, and the years of 1990, 1993, and 1996. To overcome problems due to class spectral inseparable, spatial and spectra continuums, mixed landcovers, and abnormal transitions, we separated the coastal area into regions of commonality and applying masks to specific land mixtures. Over the three years and 14 landcover classes (aggregating the cultivated land and grassland, and water and floating vegetation classes), overall accuracies ranged from 82% to 90%. To enhance landcover change interpretation, three indicators were introduced as Location Stability, Residence stability, and Turnover. Implementing methods substantiated in the multiple date MRB classification, we spatially extended the classification to the entire Louisiana coast and temporally extended the original 1990, 1993, 1996 classifications to 1999 (Figure 1). We also advanced the operational functionality of the classification and increased the credibility of change detection results. Increased operational functionality that resulted in diminished user input was for the most part gained by implementing a classification logic based on forbidden transitions. The logic detected and corrected misclassifications and mostly alleviated the necessity of subregion separation prior to the classification. The new methods provided an improved ability for more timely detection and response to landcover impact. ?? 2005 IEEE.

Mapping forested wetlands in the Great Zhan River Basin through integrating optical, radar, and topographical data classification techniques.

PubMed

Na, X D; Zang, S Y; Wu, C S; Li, W L

2015-11-01

Knowledge of the spatial extent of forested wetlands is essential to many studies including wetland functioning assessment, greenhouse gas flux estimation, and wildlife suitable habitat identification. For discriminating forested wetlands from their adjacent land cover types, researchers have resorted to image analysis techniques applied to numerous remotely sensed data. While with some success, there is still no consensus on the optimal approaches for mapping forested wetlands. To address this problem, we examined two machine learning approaches, random forest (RF) and K-nearest neighbor (KNN) algorithms, and applied these two approaches to the framework of pixel-based and object-based classifications. The RF and KNN algorithms were constructed using predictors derived from Landsat 8 imagery, Radarsat-2 advanced synthetic aperture radar (SAR), and topographical indices. The results show that the objected-based classifications performed better than per-pixel classifications using the same algorithm (RF) in terms of overall accuracy and the difference of their kappa coefficients are statistically significant (p<0.01). There were noticeably omissions for forested and herbaceous wetlands based on the per-pixel classifications using the RF algorithm. As for the object-based image analysis, there were also statistically significant differences (p<0.01) of Kappa coefficient between results performed based on RF and KNN algorithms. The object-based classification using RF provided a more visually adequate distribution of interested land cover types, while the object classifications based on the KNN algorithm showed noticeably commissions for forested wetlands and omissions for agriculture land. This research proves that the object-based classification with RF using optical, radar, and topographical data improved the mapping accuracy of land covers and provided a feasible approach to discriminate the forested wetlands from the other land cover types in forestry area.

A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

NASA Astrophysics Data System (ADS)

Zhang, Ce; Pan, Xin; Li, Huapeng; Gardiner, Andy; Sargent, Isabel; Hare, Jonathon; Atkinson, Peter M.

2018-06-01

The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.

An automatic device for detection and classification of malaria parasite species in thick blood film.

PubMed

Kaewkamnerd, Saowaluck; Uthaipibull, Chairat; Intarapanich, Apichart; Pannarut, Montri; Chaotheing, Sastra; Tongsima, Sissades

2012-01-01

Current malaria diagnosis relies primarily on microscopic examination of Giemsa-stained thick and thin blood films. This method requires vigorously trained technicians to efficiently detect and classify the malaria parasite species such as Plasmodium falciparum (Pf) and Plasmodium vivax (Pv) for an appropriate drug administration. However, accurate classification of parasite species is difficult to achieve because of inherent technical limitations and human inconsistency. To improve performance of malaria parasite classification, many researchers have proposed automated malaria detection devices using digital image analysis. These image processing tools, however, focus on detection of parasites on thin blood films, which may not detect the existence of parasites due to the parasite scarcity on the thin blood film. The problem is aggravated with low parasitemia condition. Automated detection and classification of parasites on thick blood films, which contain more numbers of parasite per detection area, would address the previous limitation. The prototype of an automatic malaria parasite identification system is equipped with mountable motorized units for controlling the movements of objective lens and microscope stage. This unit was tested for its precision to move objective lens (vertical movement, z-axis) and microscope stage (in x- and y-horizontal movements). The average precision of x-, y- and z-axes movements were 71.481 ± 7.266 μm, 40.009 ± 0.000 μm, and 7.540 ± 0.889 nm, respectively. Classification of parasites on 60 Giemsa-stained thick blood films (40 blood films containing infected red blood cells and 20 control blood films of normal red blood cells) was tested using the image analysis module. By comparing our results with the ones verified by trained malaria microscopists, the prototype detected parasite-positive and parasite-negative blood films at the rate of 95% and 68.5% accuracy, respectively. For classification performance, the thick blood films with Pv parasite was correctly classified with the success rate of 75% while the accuracy of Pf classification was 90%. This work presents an automatic device for both detection and classification of malaria parasite species on thick blood film. The system is based on digital image analysis and featured with motorized stage units, designed to easily be mounted on most conventional light microscopes used in the endemic areas. The constructed motorized module could control the movements of objective lens and microscope stage at high precision for effective acquisition of quality images for analysis. The analysis program could accurately classify parasite species, into Pf or Pv, based on distribution of chromatin size.

Case base classification on digital mammograms: improving the performance of case base classifier

NASA Astrophysics Data System (ADS)

Raman, Valliappan; Then, H. H.; Sumari, Putra; Venkatesa Mohan, N.

2011-10-01

Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. The aim of the research presented here is in twofold. First stage of research involves machine learning techniques, which segments and extracts features from the mass of digital mammograms. Second level is on problem solving approach which includes classification of mass by performance based case base classifier. In this paper we build a case-based Classifier in order to diagnose mammographic images. We explain different methods and behaviors that have been added to the classifier to improve the performance of the classifier. Currently the initial Performance base Classifier with Bagging is proposed in the paper and it's been implemented and it shows an improvement in specificity and sensitivity.

A new classification scheme of plastic wastes based upon recycling labels.

PubMed

Özkan, Kemal; Ergin, Semih; Işık, Şahin; Işıklı, Idil

2015-01-01

Since recycling of materials is widely assumed to be environmentally and economically beneficial, reliable sorting and processing of waste packaging materials such as plastics is very important for recycling with high efficiency. An automated system that can quickly categorize these materials is certainly needed for obtaining maximum classification while maintaining high throughput. In this paper, first of all, the photographs of the plastic bottles have been taken and several preprocessing steps were carried out. The first preprocessing step is to extract the plastic area of a bottle from the background. Then, the morphological image operations are implemented. These operations are edge detection, noise removal, hole removing, image enhancement, and image segmentation. These morphological operations can be generally defined in terms of the combinations of erosion and dilation. The effect of bottle color as well as label are eliminated using these operations. Secondly, the pixel-wise intensity values of the plastic bottle images have been used together with the most popular subspace and statistical feature extraction methods to construct the feature vectors in this study. Only three types of plastics are considered due to higher existence ratio of them than the other plastic types in the world. The decision mechanism consists of five different feature extraction methods including as Principal Component Analysis (PCA), Kernel PCA (KPCA), Fisher's Linear Discriminant Analysis (FLDA), Singular Value Decomposition (SVD) and Laplacian Eigenmaps (LEMAP) and uses a simple experimental setup with a camera and homogenous backlighting. Due to the giving global solution for a classification problem, Support Vector Machine (SVM) is selected to achieve the classification task and majority voting technique is used as the decision mechanism. This technique equally weights each classification result and assigns the given plastic object to the class that the most classification results agree on. The proposed classification scheme provides high accuracy rate, and also it is able to run in real-time applications. It can automatically classify the plastic bottle types with approximately 90% recognition accuracy. Besides this, the proposed methodology yields approximately 96% classification rate for the separation of PET or non-PET plastic types. It also gives 92% accuracy for the categorization of non-PET plastic types into HPDE or PP. Copyright © 2014 Elsevier Ltd. All rights reserved.

On the Implementation of a Land Cover Classification System for SAR Images Using Khoros

NASA Technical Reports Server (NTRS)

Medina Revera, Edwin J.; Espinosa, Ramon Vasquez

1997-01-01

The Synthetic Aperture Radar (SAR) sensor is widely used to record data about the ground under all atmospheric conditions. The SAR acquired images have very good resolution which necessitates the development of a classification system that process the SAR images to extract useful information for different applications. In this work, a complete system for the land cover classification was designed and programmed using the Khoros, a data flow visual language environment, taking full advantages of the polymorphic data services that it provides. Image analysis was applied to SAR images to improve and automate the processes of recognition and classification of the different regions like mountains and lakes. Both unsupervised and supervised classification utilities were used. The unsupervised classification routines included the use of several Classification/Clustering algorithms like the K-means, ISO2, Weighted Minimum Distance, and the Localized Receptive Field (LRF) training/classifier. Different texture analysis approaches such as Invariant Moments, Fractal Dimension and Second Order statistics were implemented for supervised classification of the images. The results and conclusions for SAR image classification using the various unsupervised and supervised procedures are presented based on their accuracy and performance.

Hierarchical Spatio-Temporal Probabilistic Graphical Model with Multiple Feature Fusion for Binary Facial Attribute Classification in Real-World Face Videos.

PubMed

Demirkus, Meltem; Precup, Doina; Clark, James J; Arbel, Tal

2016-06-01

Recent literature shows that facial attributes, i.e., contextual facial information, can be beneficial for improving the performance of real-world applications, such as face verification, face recognition, and image search. Examples of face attributes include gender, skin color, facial hair, etc. How to robustly obtain these facial attributes (traits) is still an open problem, especially in the presence of the challenges of real-world environments: non-uniform illumination conditions, arbitrary occlusions, motion blur and background clutter. What makes this problem even more difficult is the enormous variability presented by the same subject, due to arbitrary face scales, head poses, and facial expressions. In this paper, we focus on the problem of facial trait classification in real-world face videos. We have developed a fully automatic hierarchical and probabilistic framework that models the collective set of frame class distributions and feature spatial information over a video sequence. The experiments are conducted on a large real-world face video database that we have collected, labelled and made publicly available. The proposed method is flexible enough to be applied to any facial classification problem. Experiments on a large, real-world video database McGillFaces [1] of 18,000 video frames reveal that the proposed framework outperforms alternative approaches, by up to 16.96 and 10.13%, for the facial attributes of gender and facial hair, respectively.

Image classification independent of orientation and scale

NASA Astrophysics Data System (ADS)

Arsenault, Henri H.; Parent, Sebastien; Moisan, Sylvain

1998-04-01

The recognition of targets independently of orientation has become fairly well developed in recent years for in-plane rotation. The out-of-plane rotation problem is much less advanced. When both out-of-plane rotations and changes of scale are present, the problem becomes very difficult. In this paper we describe our research on the combined out-of- plane rotation problem and the scale invariance problem. The rotations were limited to rotations about an axis perpendicular to the line of sight. The objects to be classified were three kinds of military vehicles. The inputs used were infrared imagery and photographs. We used a variation of a method proposed by Neiberg and Casasent, where a neural network is trained with a subset of the database and a minimum distances from lines in feature space are used for classification instead of nearest neighbors. Each line in the feature space corresponds to one class of objects, and points on one line correspond to different orientations of the same target. We found that the training samples needed to be closer for some orientations than for others, and that the most difficult orientations are where the target is head-on to the observer. By means of some additional training of the neural network, we were able to achieve 100% correct classification for 360 degree rotation and a range of scales over a factor of five.

An embedded system for face classification in infrared video using sparse representation

NASA Astrophysics Data System (ADS)

Saavedra M., Antonio; Pezoa, Jorge E.; Zarkesh-Ha, Payman; Figueroa, Miguel

2017-09-01

We propose a platform for robust face recognition in Infrared (IR) images using Compressive Sensing (CS). In line with CS theory, the classification problem is solved using a sparse representation framework, where test images are modeled by means of a linear combination of the training set. Because the training set constitutes an over-complete dictionary, we identify new images by finding their sparsest representation based on the training set, using standard l1-minimization algorithms. Unlike conventional face-recognition algorithms, we feature extraction is performed using random projections with a precomputed binary matrix, as proposed in the CS literature. This random sampling reduces the effects of noise and occlusions such as facial hair, eyeglasses, and disguises, which are notoriously challenging in IR images. Thus, the performance of our framework is robust to these noise and occlusion factors, achieving an average accuracy of approximately 90% when the UCHThermalFace database is used for training and testing purposes. We implemented our framework on a high-performance embedded digital system, where the computation of the sparse representation of IR images was performed by a dedicated hardware using a deeply pipelined architecture on an Field-Programmable Gate Array (FPGA).

Classification of Regional Radiographic Emphysematous Patterns Using Low-Attenuation Gap Length Matrix

NASA Astrophysics Data System (ADS)

Tan, Kok Liang; Tanaka, Toshiyuki; Nakamura, Hidetoshi; Shirahata, Toru; Sugiura, Hiroaki

The standard computer-tomography-based method for measuring emphysema uses percentage of area of low attenuation which is called the pixel index (PI). However, the PI method is susceptible to the problem of averaging effect and this causes the discrepancy between what the PI method describes and what radiologists observe. Knowing that visual recognition of the different types of regional radiographic emphysematous tissues in a CT image can be fuzzy, this paper proposes a low-attenuation gap length matrix (LAGLM) based algorithm for classifying the regional radiographic lung tissues into four emphysema types distinguishing, in particular, radiographic patterns that imply obvious or subtle bullous emphysema from those that imply diffuse emphysema or minor destruction of airway walls. Neural network is used for discrimination. The proposed LAGLM method is inspired by, but different from, former texture-based methods like gray level run length matrix (GLRLM) and gray level gap length matrix (GLGLM). The proposed algorithm is successfully validated by classifying 105 lung regions that are randomly selected from 270 images. The lung regions are hand-annotated by radiologists beforehand. The average four-class classification accuracies in the form of the proposed algorithm/PI/GLRLM/GLGLM methods are: 89.00%/82.97%/52.90%/51.36%, respectively. The p-values from the correlation analyses between the classification results of 270 images and pulmonary function test results are generally less than 0.01. The classification results are useful for a followup study especially for monitoring morphological changes with progression of pulmonary disease.

Optimizing spectral CT parameters for material classification tasks

NASA Astrophysics Data System (ADS)

Rigie, D. S.; La Rivière, P. J.

2016-06-01

In this work, we propose a framework for optimizing spectral CT imaging parameters and hardware design with regard to material classification tasks. Compared with conventional CT, many more parameters must be considered when designing spectral CT systems and protocols. These choices will impact material classification performance in a non-obvious, task-dependent way with direct implications for radiation dose reduction. In light of this, we adapt Hotelling Observer formalisms typically applied to signal detection tasks to the spectral CT, material-classification problem. The result is a rapidly computable metric that makes it possible to sweep out many system configurations, generating parameter optimization curves (POC’s) that can be used to select optimal settings. The proposed model avoids restrictive assumptions about the basis-material decomposition (e.g. linearity) and incorporates signal uncertainty with a stochastic object model. This technique is demonstrated on dual-kVp and photon-counting systems for two different, clinically motivated material classification tasks (kidney stone classification and plaque removal). We show that the POC’s predicted with the proposed analytic model agree well with those derived from computationally intensive numerical simulation studies.

Optimizing Spectral CT Parameters for Material Classification Tasks

PubMed Central

Rigie, D. S.; La Rivière, P. J.

2017-01-01

In this work, we propose a framework for optimizing spectral CT imaging parameters and hardware design with regard to material classification tasks. Compared with conventional CT, many more parameters must be considered when designing spectral CT systems and protocols. These choices will impact material classification performance in a non-obvious, task-dependent way with direct implications for radiation dose reduction. In light of this, we adapt Hotelling Observer formalisms typically applied to signal detection tasks to the spectral CT, material-classification problem. The result is a rapidly computable metric that makes it possible to sweep out many system configurations, generating parameter optimization curves (POC’s) that can be used to select optimal settings. The proposed model avoids restrictive assumptions about the basis-material decomposition (e.g. linearity) and incorporates signal uncertainty with a stochastic object model. This technique is demonstrated on dual-kVp and photon-counting systems for two different, clinically motivated material classification tasks (kidney stone classification and plaque removal). We show that the POC’s predicted with the proposed analytic model agree well with those derived from computationally intensive numerical simulation studies. PMID:27227430

Semantic and topological classification of images in magnetically guided capsule endoscopy

NASA Astrophysics Data System (ADS)

Mewes, P. W.; Rennert, P.; Juloski, A. L.; Lalande, A.; Angelopoulou, E.; Kuth, R.; Hornegger, J.

2012-03-01

Magnetically-guided capsule endoscopy (MGCE) is a nascent technology with the goal to allow the steering of a capsule endoscope inside a water filled stomach through an external magnetic field. We developed a classification cascade for MGCE images with groups images in semantic and topological categories. Results can be used in a post-procedure review or as a starting point for algorithms classifying pathologies. The first semantic classification step discards over-/under-exposed images as well as images with a large amount of debris. The second topological classification step groups images with respect to their position in the upper gastrointestinal tract (mouth, esophagus, stomach, duodenum). In the third stage two parallel classifications steps distinguish topologically different regions inside the stomach (cardia, fundus, pylorus, antrum, peristaltic view). For image classification, global image features and local texture features were applied and their performance was evaluated. We show that the third classification step can be improved by a bubble and debris segmentation because it limits feature extraction to discriminative areas only. We also investigated the impact of segmenting intestinal folds on the identification of different semantic camera positions. The results of classifications with a support-vector-machine show the significance of color histogram features for the classification of corrupted images (97%). Features extracted from intestinal fold segmentation lead only to a minor improvement (3%) in discriminating different camera positions.

Robust Image Regression Based on the Extended Matrix Variate Power Exponential Distribution of Dependent Noise.

PubMed

Luo, Lei; Yang, Jian; Qian, Jianjun; Tai, Ying; Lu, Gui-Fu

2017-09-01

Dealing with partial occlusion or illumination is one of the most challenging problems in image representation and classification. In this problem, the characterization of the representation error plays a crucial role. In most current approaches, the error matrix needs to be stretched into a vector and each element is assumed to be independently corrupted. This ignores the dependence between the elements of error. In this paper, it is assumed that the error image caused by partial occlusion or illumination changes is a random matrix variate and follows the extended matrix variate power exponential distribution. This has the heavy tailed regions and can be used to describe a matrix pattern of l×m dimensional observations that are not independent. This paper reveals the essence of the proposed distribution: it actually alleviates the correlations between pixels in an error matrix E and makes E approximately Gaussian. On the basis of this distribution, we derive a Schatten p -norm-based matrix regression model with L q regularization. Alternating direction method of multipliers is applied to solve this model. To get a closed-form solution in each step of the algorithm, two singular value function thresholding operators are introduced. In addition, the extended Schatten p -norm is utilized to characterize the distance between the test samples and classes in the design of the classifier. Extensive experimental results for image reconstruction and classification with structural noise demonstrate that the proposed algorithm works much more robustly than some existing regression-based methods.

Creating a classification of image types in the medical literature for visual categorization

NASA Astrophysics Data System (ADS)

Müller, Henning; Kalpathy-Cramer, Jayashree; Demner-Fushman, Dina; Antani, Sameer

2012-02-01

Content-based image retrieval (CBIR) from specialized collections has often been proposed for use in such areas as diagnostic aid, clinical decision support, and teaching. The visual retrieval from broad image collections such as teaching files, the medical literature or web images, by contrast, has not yet reached a high maturity level compared to textual information retrieval. Visual image classification into a relatively small number of classes (20-100) on the other hand, has shown to deliver good results in several benchmarks. It is, however, currently underused as a basic technology for retrieval tasks, for example, to limit the search space. Most classification schemes for medical images are focused on specific areas and consider mainly the medical image types (modalities), imaged anatomy, and view, and merge them into a single descriptor or classification hierarchy. Furthermore, they often ignore other important image types such as biological images, statistical figures, flowcharts, and diagrams that frequently occur in the biomedical literature. Most of the current classifications have also been created for radiology images, which are not the only types to be taken into account. With Open Access becoming increasingly widespread particularly in medicine, images from the biomedical literature are more easily available for use. Visual information from these images and knowledge that an image is of a specific type or medical modality could enrich retrieval. This enrichment is hampered by the lack of a commonly agreed image classification scheme. This paper presents a hierarchy for classification of biomedical illustrations with the goal of using it for visual classification and thus as a basis for retrieval. The proposed hierarchy is based on relevant parts of existing terminologies, such as the IRMA-code (Image Retrieval in Medical Applications), ad hoc classifications and hierarchies used in imageCLEF (Image retrieval task at the Cross-Language Evaluation Forum) and NLM's (National Library of Medicine) OpenI. Furtheron, mappings to NLM's MeSH (Medical Subject Headings), RSNA's RadLex (Radiological Society of North America, Radiology Lexicon), and the IRMA code are also attempted for relevant image types. Advantages derived from such hierarchical classification for medical image retrieval are being evaluated through benchmarks such as imageCLEF, and R&D systems such as NLM's OpenI. The goal is to extend this hierarchy progressively and (through adding image types occurring in the biomedical literature) to have a terminology for visual image classification based on image types distinguishable by visual means and occurring in the medical open access literature.

Classification of visible and infrared hyperspectral images based on image segmentation and edge-preserving filtering

NASA Astrophysics Data System (ADS)

Cui, Binge; Ma, Xiudan; Xie, Xiaoyun; Ren, Guangbo; Ma, Yi

2017-03-01

The classification of hyperspectral images with a few labeled samples is a major challenge which is difficult to meet unless some spatial characteristics can be exploited. In this study, we proposed a novel spectral-spatial hyperspectral image classification method that exploited spatial autocorrelation of hyperspectral images. First, image segmentation is performed on the hyperspectral image to assign each pixel to a homogeneous region. Second, the visible and infrared bands of hyperspectral image are partitioned into multiple subsets of adjacent bands, and each subset is merged into one band. Recursive edge-preserving filtering is performed on each merged band which utilizes the spectral information of neighborhood pixels. Third, the resulting spectral and spatial feature band set is classified using the SVM classifier. Finally, bilateral filtering is performed to remove "salt-and-pepper" noise in the classification result. To preserve the spatial structure of hyperspectral image, edge-preserving filtering is applied independently before and after the classification process. Experimental results on different hyperspectral images prove that the proposed spectral-spatial classification approach is robust and offers more classification accuracy than state-of-the-art methods when the number of labeled samples is small.

Brain medical image diagnosis based on corners with importance-values.

PubMed

Gao, Linlin; Pan, Haiwei; Li, Qing; Xie, Xiaoqin; Zhang, Zhiqiang; Han, Jinming; Zhai, Xiao

2017-11-21

Brain disorders are one of the top causes of human death. Generally, neurologists analyze brain medical images for diagnosis. In the image analysis field, corners are one of the most important features, which makes corner detection and matching studies essential. However, existing corner detection studies do not consider the domain information of brain. This leads to many useless corners and the loss of significant information. Regarding corner matching, the uncertainty and structure of brain are not employed in existing methods. Moreover, most corner matching studies are used for 3D image registration. They are inapplicable for 2D brain image diagnosis because of the different mechanisms. To address these problems, we propose a novel corner-based brain medical image classification method. Specifically, we automatically extract multilayer texture images (MTIs) which embody diagnostic information from neurologists. Moreover, we present a corner matching method utilizing the uncertainty and structure of brain medical images and a bipartite graph model. Finally, we propose a similarity calculation method for diagnosis. Brain CT and MRI image sets are utilized to evaluate the proposed method. First, classifiers are trained in N-fold cross-validation analysis to produce the best θ and K. Then independent brain image sets are tested to evaluate the classifiers. Moreover, the classifiers are also compared with advanced brain image classification studies. For the brain CT image set, the proposed classifier outperforms the comparison methods by at least 8% on accuracy and 2.4% on F1-score. Regarding the brain MRI image set, the proposed classifier is superior to the comparison methods by more than 7.3% on accuracy and 4.9% on F1-score. Results also demonstrate that the proposed method is robust to different intensity ranges of brain medical image. In this study, we develop a robust corner-based brain medical image classifier. Specifically, we propose a corner detection method utilizing the diagnostic information from neurologists and a corner matching method based on the uncertainty and structure of brain medical images. Additionally, we present a similarity calculation method for brain image classification. Experimental results on two brain image sets show the proposed corner-based brain medical image classifier outperforms the state-of-the-art studies.

Segmentation of the spinous process and its acoustic shadow in vertebral ultrasound images.

PubMed

Berton, Florian; Cheriet, Farida; Miron, Marie-Claude; Laporte, Catherine

2016-05-01

Spinal ultrasound imaging is emerging as a low-cost, radiation-free alternative to conventional X-ray imaging for the clinical follow-up of patients with scoliosis. Currently, deformity measurement relies almost entirely on manual identification of key vertebral landmarks. However, the interpretation of vertebral ultrasound images is challenging, primarily because acoustic waves are entirely reflected by bone. To alleviate this problem, we propose an algorithm to segment these images into three regions: the spinous process, its acoustic shadow and other tissues. This method consists, first, in the extraction of several image features and the selection of the most relevant ones for the discrimination of the three regions. Then, using this set of features and linear discriminant analysis, each pixel of the image is classified as belonging to one of the three regions. Finally, the image is segmented by regularizing the pixel-wise classification results to account for some geometrical properties of vertebrae. The feature set was first validated by analyzing the classification results across a learning database. The database contained 107 vertebral ultrasound images acquired with convex and linear probes. Classification rates of 84%, 92% and 91% were achieved for the spinous process, the acoustic shadow and other tissues, respectively. Dice similarity coefficients of 0.72 and 0.88 were obtained respectively for the spinous process and acoustic shadow, confirming that the proposed method accurately segments the spinous process and its acoustic shadow in vertebral ultrasound images. Furthermore, the centroid of the automatically segmented spinous process was located at an average distance of 0.38 mm from that of the manually labeled spinous process, which is on the order of image resolution. This suggests that the proposed method is a promising tool for the measurement of the Spinous Process Angle and, more generally, for assisting ultrasound-based assessment of scoliosis progression. Copyright © 2016 Elsevier Ltd. All rights reserved.

Land Cover Analysis by Using Pixel-Based and Object-Based Image Classification Method in Bogor

NASA Astrophysics Data System (ADS)

Amalisana, Birohmatin; Rokhmatullah; Hernina, Revi

2017-12-01

The advantage of image classification is to provide earth’s surface information like landcover and time-series changes. Nowadays, pixel-based image classification technique is commonly performed with variety of algorithm such as minimum distance, parallelepiped, maximum likelihood, mahalanobis distance. On the other hand, landcover classification can also be acquired by using object-based image classification technique. In addition, object-based classification uses image segmentation from parameter such as scale, form, colour, smoothness and compactness. This research is aimed to compare the result of landcover classification and its change detection between parallelepiped pixel-based and object-based classification method. Location of this research is Bogor with 20 years range of observation from 1996 until 2016. This region is famous as urban areas which continuously change due to its rapid development, so that time-series landcover information of this region will be interesting.

Semantic classification of urban buildings combining VHR image and GIS data: An improved random forest approach

NASA Astrophysics Data System (ADS)

Du, Shihong; Zhang, Fangli; Zhang, Xiuyuan

2015-07-01

While most existing studies have focused on extracting geometric information on buildings, only a few have concentrated on semantic information. The lack of semantic information cannot satisfy many demands on resolving environmental and social issues. This study presents an approach to semantically classify buildings into much finer categories than those of existing studies by learning random forest (RF) classifier from a large number of imbalanced samples with high-dimensional features. First, a two-level segmentation mechanism combining GIS and VHR image produces single image objects at a large scale and intra-object components at a small scale. Second, a semi-supervised method chooses a large number of unbiased samples by considering the spatial proximity and intra-cluster similarity of buildings. Third, two important improvements in RF classifier are made: a voting-distribution ranked rule for reducing the influences of imbalanced samples on classification accuracy and a feature importance measurement for evaluating each feature's contribution to the recognition of each category. Fourth, the semantic classification of urban buildings is practically conducted in Beijing city, and the results demonstrate that the proposed approach is effective and accurate. The seven categories used in the study are finer than those in existing work and more helpful to studying many environmental and social problems.

Statistical analysis of spectral data: a methodology for designing an intelligent monitoring system for the diabetic foot

NASA Astrophysics Data System (ADS)

Liu, Chanjuan; van Netten, Jaap J.; Klein, Marvin E.; van Baal, Jeff G.; Bus, Sicco A.; van der Heijden, Ferdi

2013-12-01

Early detection of (pre-)signs of ulceration on a diabetic foot is valuable for clinical practice. Hyperspectral imaging is a promising technique for detection and classification of such (pre-)signs. However, the number of the spectral bands should be limited to avoid overfitting, which is critical for pixel classification with hyperspectral image data. The goal was to design a detector/classifier based on spectral imaging (SI) with a small number of optical bandpass filters. The performance and stability of the design were also investigated. The selection of the bandpass filters boils down to a feature selection problem. A dataset was built, containing reflectance spectra of 227 skin spots from 64 patients, measured with a spectrometer. Each skin spot was annotated manually by clinicians as "healthy" or a specific (pre-)sign of ulceration. Statistical analysis on the data set showed the number of required filters is between 3 and 7, depending on additional constraints on the filter set. The stability analysis revealed that shot noise was the most critical factor affecting the classification performance. It indicated that this impact could be avoided in future SI systems with a camera sensor whose saturation level is higher than 106, or by postimage processing.

Automated radial basis function neural network based image classification system for diabetic retinopathy detection in retinal images

NASA Astrophysics Data System (ADS)

Anitha, J.; Vijila, C. Kezi Selva; Hemanth, D. Jude

2010-02-01

Diabetic retinopathy (DR) is a chronic eye disease for which early detection is highly essential to avoid any fatal results. Image processing of retinal images emerge as a feasible tool for this early diagnosis. Digital image processing techniques involve image classification which is a significant technique to detect the abnormality in the eye. Various automated classification systems have been developed in the recent years but most of them lack high classification accuracy. Artificial neural networks are the widely preferred artificial intelligence technique since it yields superior results in terms of classification accuracy. In this work, Radial Basis function (RBF) neural network based bi-level classification system is proposed to differentiate abnormal DR Images and normal retinal images. The results are analyzed in terms of classification accuracy, sensitivity and specificity. A comparative analysis is performed with the results of the probabilistic classifier namely Bayesian classifier to show the superior nature of neural classifier. Experimental results show promising results for the neural classifier in terms of the performance measures.

Feature extraction based on extended multi-attribute profiles and sparse autoencoder for remote sensing image classification

NASA Astrophysics Data System (ADS)

Teffahi, Hanane; Yao, Hongxun; Belabid, Nasreddine; Chaib, Souleyman

2018-02-01

The satellite images with very high spatial resolution have been recently widely used in image classification topic as it has become challenging task in remote sensing field. Due to a number of limitations such as the redundancy of features and the high dimensionality of the data, different classification methods have been proposed for remote sensing images classification particularly the methods using feature extraction techniques. This paper propose a simple efficient method exploiting the capability of extended multi-attribute profiles (EMAP) with sparse autoencoder (SAE) for remote sensing image classification. The proposed method is used to classify various remote sensing datasets including hyperspectral and multispectral images by extracting spatial and spectral features based on the combination of EMAP and SAE by linking them to kernel support vector machine (SVM) for classification. Experiments on new hyperspectral image "Huston data" and multispectral image "Washington DC data" shows that this new scheme can achieve better performance of feature learning than the primitive features, traditional classifiers and ordinary autoencoder and has huge potential to achieve higher accuracy for classification in short running time.

A comparative study of deep learning models for medical image classification

NASA Astrophysics Data System (ADS)

Dutta, Suvajit; Manideep, B. C. S.; Rai, Shalva; Vijayarajan, V.

2017-11-01

Deep Learning(DL) techniques are conquering over the prevailing traditional approaches of neural network, when it comes to the huge amount of dataset, applications requiring complex functions demanding increase accuracy with lower time complexities. Neurosciences has already exploited DL techniques, thus portrayed itself as an inspirational source for researchers exploring the domain of Machine learning. DL enthusiasts cover the areas of vision, speech recognition, motion planning and NLP as well, moving back and forth among fields. This concerns with building models that can successfully solve variety of tasks requiring intelligence and distributed representation. The accessibility to faster CPUs, introduction of GPUs-performing complex vector and matrix computations, supported agile connectivity to network. Enhanced software infrastructures for distributed computing worked in strengthening the thought that made researchers suffice DL methodologies. The paper emphases on the following DL procedures to traditional approaches which are performed manually for classifying medical images. The medical images are used for the study Diabetic Retinopathy(DR) and computed tomography (CT) emphysema data. Both DR and CT data diagnosis is difficult task for normal image classification methods. The initial work was carried out with basic image processing along with K-means clustering for identification of image severity levels. After determining image severity levels ANN has been applied on the data to get the basic classification result, then it is compared with the result of DNNs (Deep Neural Networks), which performed efficiently because of its multiple hidden layer features basically which increases accuracy factors, but the problem of vanishing gradient in DNNs made to consider Convolution Neural Networks (CNNs) as well for better results. The CNNs are found to be providing better outcomes when compared to other learning models aimed at classification of images. CNNs are favoured as they provide better visual processing models successfully classifying the noisy data as well. The work centres on the detection on Diabetic Retinopathy-loss in vision and recognition of computed tomography (CT) emphysema data measuring the severity levels for both cases. The paper discovers how various Machine Learning algorithms can be implemented ensuing a supervised approach, so as to get accurate results with less complexity possible.

Classification of Clouds in Satellite Imagery Using Adaptive Fuzzy Sparse Representation

PubMed Central

Jin, Wei; Gong, Fei; Zeng, Xingbin; Fu, Randi

2016-01-01

Automatic cloud detection and classification using satellite cloud imagery have various meteorological applications such as weather forecasting and climate monitoring. Cloud pattern analysis is one of the research hotspots recently. Since satellites sense the clouds remotely from space, and different cloud types often overlap and convert into each other, there must be some fuzziness and uncertainty in satellite cloud imagery. Satellite observation is susceptible to noises, while traditional cloud classification methods are sensitive to noises and outliers; it is hard for traditional cloud classification methods to achieve reliable results. To deal with these problems, a satellite cloud classification method using adaptive fuzzy sparse representation-based classification (AFSRC) is proposed. Firstly, by defining adaptive parameters related to attenuation rate and critical membership, an improved fuzzy membership is introduced to accommodate the fuzziness and uncertainty of satellite cloud imagery; secondly, by effective combination of the improved fuzzy membership function and sparse representation-based classification (SRC), atoms in training dictionary are optimized; finally, an adaptive fuzzy sparse representation classifier for cloud classification is proposed. Experiment results on FY-2G satellite cloud image show that, the proposed method not only improves the accuracy of cloud classification, but also has strong stability and adaptability with high computational efficiency. PMID:27999261

Cascade classification of endocytoscopic images of colorectal lesions for automated pathological diagnosis

NASA Astrophysics Data System (ADS)

Itoh, Hayato; Mori, Yuichi; Misawa, Masashi; Oda, Masahiro; Kudo, Shin-ei; Mori, Kensaku

2018-02-01

This paper presents a new classification method for endocytoscopic images. Endocytoscopy is a new endoscope that enables us to perform conventional endoscopic observation and ultramagnified observation of cell level. This ultramagnified views (endocytoscopic images) make possible to perform pathological diagnosis only on endo-scopic views of polyps during colonoscopy. However, endocytoscopic image diagnosis requires higher experiences for physicians. An automated pathological diagnosis system is required to prevent the overlooking of neoplastic lesions in endocytoscopy. For this purpose, we propose a new automated endocytoscopic image classification method that classifies neoplastic and non-neoplastic endocytoscopic images. This method consists of two classification steps. At the first step, we classify an input image by support vector machine. We forward the image to the second step if the confidence of the first classification is low. At the second step, we classify the forwarded image by convolutional neural network. We reject the input image if the confidence of the second classification is also low. We experimentally evaluate the classification performance of the proposed method. In this experiment, we use about 16,000 and 4,000 colorectal endocytoscopic images as training and test data, respectively. The results show that the proposed method achieves high sensitivity 93.4% with small rejection rate 9.3% even for difficult test data.

Joint tumor segmentation and dense deformable registration of brain MR images.

PubMed

Parisot, Sarah; Duffau, Hugues; Chemouny, Stéphane; Paragios, Nikos

2012-01-01

In this paper we propose a novel graph-based concurrent registration and segmentation framework. Registration is modeled with a pairwise graphical model formulation that is modular with respect to the data and regularization term. Segmentation is addressed by adopting a similar graphical model, using image-based classification techniques while producing a smooth solution. The two problems are coupled via a relaxation of the registration criterion in the presence of tumors as well as a segmentation through a registration term aiming the separation between healthy and diseased tissues. Efficient linear programming is used to solve both problems simultaneously. State of the art results demonstrate the potential of our method on a large and challenging low-grade glioma data set.

Robust multitask learning with three-dimensional empirical mode decomposition-based features for hyperspectral classification

NASA Astrophysics Data System (ADS)

He, Zhi; Liu, Lin

2016-11-01

Empirical mode decomposition (EMD) and its variants have recently been applied for hyperspectral image (HSI) classification due to their ability to extract useful features from the original HSI. However, it remains a challenging task to effectively exploit the spectral-spatial information by the traditional vector or image-based methods. In this paper, a three-dimensional (3D) extension of EMD (3D-EMD) is proposed to naturally treat the HSI as a cube and decompose the HSI into varying oscillations (i.e. 3D intrinsic mode functions (3D-IMFs)). To achieve fast 3D-EMD implementation, 3D Delaunay triangulation (3D-DT) is utilized to determine the distances of extrema, while separable filters are adopted to generate the envelopes. Taking the extracted 3D-IMFs as features of different tasks, robust multitask learning (RMTL) is further proposed for HSI classification. In RMTL, pairs of low-rank and sparse structures are formulated by trace-norm and l1,2 -norm to capture task relatedness and specificity, respectively. Moreover, the optimization problems of RMTL can be efficiently solved by the inexact augmented Lagrangian method (IALM). Compared with several state-of-the-art feature extraction and classification methods, the experimental results conducted on three benchmark data sets demonstrate the superiority of the proposed methods.

Hierarchy-associated semantic-rule inference framework for classifying indoor scenes

NASA Astrophysics Data System (ADS)

Yu, Dan; Liu, Peng; Ye, Zhipeng; Tang, Xianglong; Zhao, Wei

2016-03-01

Typically, the initial task of classifying indoor scenes is challenging, because the spatial layout and decoration of a scene can vary considerably. Recent efforts at classifying object relationships commonly depend on the results of scene annotation and predefined rules, making classification inflexible. Furthermore, annotation results are easily affected by external factors. Inspired by human cognition, a scene-classification framework was proposed using the empirically based annotation (EBA) and a match-over rule-based (MRB) inference system. The semantic hierarchy of images is exploited by EBA to construct rules empirically for MRB classification. The problem of scene classification is divided into low-level annotation and high-level inference from a macro perspective. Low-level annotation involves detecting the semantic hierarchy and annotating the scene with a deformable-parts model and a bag-of-visual-words model. In high-level inference, hierarchical rules are extracted to train the decision tree for classification. The categories of testing samples are generated from the parts to the whole. Compared with traditional classification strategies, the proposed semantic hierarchy and corresponding rules reduce the effect of a variable background and improve the classification performance. The proposed framework was evaluated on a popular indoor scene dataset, and the experimental results demonstrate its effectiveness.

IRIS COLOUR CLASSIFICATION SCALES – THEN AND NOW

PubMed Central

Grigore, Mariana; Avram, Alina

2015-01-01

Eye colour is one of the most obvious phenotypic traits of an individual. Since the first documented classification scale developed in 1843, there have been numerous attempts to classify the iris colour. In the past centuries, iris colour classification scales has had various colour categories and mostly relied on comparison of an individual’s eye with painted glass eyes. Once photography techniques were refined, standard iris photographs replaced painted eyes, but this did not solve the problem of painted/ printed colour variability in time. Early clinical scales were easy to use, but lacked objectivity and were not standardised or statistically tested for reproducibility. The era of automated iris colour classification systems came with the technological development. Spectrophotometry, digital analysis of high-resolution iris images, hyper spectral analysis of the human real iris and the dedicated iris colour analysis software, all accomplished an objective, accurate iris colour classification, but are quite expensive and limited in use to research environment. Iris colour classification systems evolved continuously due to their use in a wide range of studies, especially in the fields of anthropology, epidemiology and genetics. Despite the wide range of the existing scales, up until present there has been no generally accepted iris colour classification scale. PMID:27373112

IRIS COLOUR CLASSIFICATION SCALES--THEN AND NOW.

PubMed

Grigore, Mariana; Avram, Alina

2015-01-01

Eye colour is one of the most obvious phenotypic traits of an individual. Since the first documented classification scale developed in 1843, there have been numerous attempts to classify the iris colour. In the past centuries, iris colour classification scales has had various colour categories and mostly relied on comparison of an individual's eye with painted glass eyes. Once photography techniques were refined, standard iris photographs replaced painted eyes, but this did not solve the problem of painted/ printed colour variability in time. Early clinical scales were easy to use, but lacked objectivity and were not standardised or statistically tested for reproducibility. The era of automated iris colour classification systems came with the technological development. Spectrophotometry, digital analysis of high-resolution iris images, hyper spectral analysis of the human real iris and the dedicated iris colour analysis software, all accomplished an objective, accurate iris colour classification, but are quite expensive and limited in use to research environment. Iris colour classification systems evolved continuously due to their use in a wide range of studies, especially in the fields of anthropology, epidemiology and genetics. Despite the wide range of the existing scales, up until present there has been no generally accepted iris colour classification scale.

Significance of perceptually relevant image decolorization for scene classification

NASA Astrophysics Data System (ADS)

Viswanathan, Sowmya; Divakaran, Govind; Soman, Kutti Padanyl

2017-11-01

Color images contain luminance and chrominance components representing the intensity and color information, respectively. The objective of this paper is to show the significance of incorporating chrominance information to the task of scene classification. An improved color-to-grayscale image conversion algorithm that effectively incorporates chrominance information is proposed using the color-to-gray structure similarity index and singular value decomposition to improve the perceptual quality of the converted grayscale images. The experimental results based on an image quality assessment for image decolorization and its success rate (using the Cadik and COLOR250 datasets) show that the proposed image decolorization technique performs better than eight existing benchmark algorithms for image decolorization. In the second part of the paper, the effectiveness of incorporating the chrominance component for scene classification tasks is demonstrated using a deep belief network-based image classification system developed using dense scale-invariant feature transforms. The amount of chrominance information incorporated into the proposed image decolorization technique is confirmed with the improvement to the overall scene classification accuracy. Moreover, the overall scene classification performance improved by combining the models obtained using the proposed method and conventional decolorization methods.

Can glenoid wear be accurately assessed using x-ray imaging? Evaluating agreement of x-ray and magnetic resonance imaging (MRI) Walch classification.

PubMed

Kopka, Michaela; Fourman, Mitchell; Soni, Ashish; Cordle, Andrew C; Lin, Albert

2017-09-01

The Walch classification is the most recognized means of assessing glenoid wear in preoperative planning for shoulder arthroplasty. This classification relies on advanced imaging, which is more expensive and less practical than plain radiographs. The purpose of this study was to determine whether the Walch classification could be accurately applied to x-ray images compared with magnetic resonance imaging (MRI) as the gold standard. We hypothesized that x-ray images cannot adequately replace advanced imaging in the evaluation of glenoid wear. Preoperative axillary x-ray images and MRI scans of 50 patients assessed for shoulder arthroplasty were independently reviewed by 5 raters. Glenoid wear was individually classified according to the Walch classification using each imaging modality. The raters then collectively reviewed the MRI scans and assigned a consensus classification to serve as the gold standard. The κ coefficient was used to determine interobserver agreement for x-ray images and independent MRI reads, as well as the agreement between x-ray images and consensus MRI. The inter-rater agreement for x-ray images and MRIs was "moderate" (κ = 0.42 and κ = 0.47, respectively) for the 5-category Walch classification (A1, A2, B1, B2, C) and "moderate" (κ = 0.54 and κ = 0.59, respectively) for the 3-category Walch classification (A, B, C). The agreement between x-ray images and consensus MRI was much lower: "fair-to-moderate" (κ = 0.21-0.51) for the 5-category and "moderate" (κ = 0.36-0.60) for the 3-category Walch classification. The inter-rater agreement between x-ray images and consensus MRI is "fair-to-moderate." This is lower than the previously reported reliability of the Walch classification using computed tomography scans. Accordingly, x-ray images are inferior to advanced imaging when assessing glenoid wear. Copyright © 2017 Journal of Shoulder and Elbow Surgery Board of Trustees. Published by Elsevier Inc. All rights reserved.

A spectrum fractal feature classification algorithm for agriculture crops with hyper spectrum image

NASA Astrophysics Data System (ADS)

Su, Junying

2011-11-01

A fractal dimension feature analysis method in spectrum domain for hyper spectrum image is proposed for agriculture crops classification. Firstly, a fractal dimension calculation algorithm in spectrum domain is presented together with the fast fractal dimension value calculation algorithm using the step measurement method. Secondly, the hyper spectrum image classification algorithm and flowchart is presented based on fractal dimension feature analysis in spectrum domain. Finally, the experiment result of the agricultural crops classification with FCL1 hyper spectrum image set with the proposed method and SAM (spectral angle mapper). The experiment results show it can obtain better classification result than the traditional SAM feature analysis which can fulfill use the spectrum information of hyper spectrum image to realize precision agricultural crops classification.

Image-classification-based global dimming algorithm for LED backlights in LCDs

NASA Astrophysics Data System (ADS)

Qibin, Feng; Huijie, He; Dong, Han; Lei, Zhang; Guoqiang, Lv

2015-07-01

Backlight dimming can help LCDs reduce power consumption and improve CR. With fixed parameters, dimming algorithm cannot achieve satisfied effects for all kinds of images. The paper introduces an image-classification-based global dimming algorithm. The proposed classification method especially for backlight dimming is based on luminance and CR of input images. The parameters for backlight dimming level and pixel compensation are adaptive with image classifications. The simulation results show that the classification based dimming algorithm presents 86.13% power reduction improvement compared with dimming without classification, with almost same display quality. The prototype is developed. There are no perceived distortions when playing videos. The practical average power reduction of the prototype TV is 18.72%, compared with common TV without dimming.

Application of Sensor Fusion to Improve Uav Image Classification

NASA Astrophysics Data System (ADS)

Jabari, S.; Fathollahi, F.; Zhang, Y.

2017-08-01

Image classification is one of the most important tasks of remote sensing projects including the ones that are based on using UAV images. Improving the quality of UAV images directly affects the classification results and can save a huge amount of time and effort in this area. In this study, we show that sensor fusion can improve image quality which results in increasing the accuracy of image classification. Here, we tested two sensor fusion configurations by using a Panchromatic (Pan) camera along with either a colour camera or a four-band multi-spectral (MS) camera. We use the Pan camera to benefit from its higher sensitivity and the colour or MS camera to benefit from its spectral properties. The resulting images are then compared to the ones acquired by a high resolution single Bayer-pattern colour camera (here referred to as HRC). We assessed the quality of the output images by performing image classification tests. The outputs prove that the proposed sensor fusion configurations can achieve higher accuracies compared to the images of the single Bayer-pattern colour camera. Therefore, incorporating a Pan camera on-board in the UAV missions and performing image fusion can help achieving higher quality images and accordingly higher accuracy classification results.

a Novel Framework for Remote Sensing Image Scene Classification

NASA Astrophysics Data System (ADS)

Jiang, S.; Zhao, H.; Wu, W.; Tan, Q.

2018-04-01

High resolution remote sensing (HRRS) images scene classification aims to label an image with a specific semantic category. HRRS images contain more details of the ground objects and their spatial distribution patterns than low spatial resolution images. Scene classification can bridge the gap between low-level features and high-level semantics. It can be applied in urban planning, target detection and other fields. This paper proposes a novel framework for HRRS images scene classification. This framework combines the convolutional neural network (CNN) and XGBoost, which utilizes CNN as feature extractor and XGBoost as a classifier. Then, this framework is evaluated on two different HRRS images datasets: UC-Merced dataset and NWPU-RESISC45 dataset. Our framework achieved satisfying accuracies on two datasets, which is 95.57 % and 83.35 % respectively. From the experiments result, our framework has been proven to be effective for remote sensing images classification. Furthermore, we believe this framework will be more practical for further HRRS scene classification, since it costs less time on training stage.

NutriNet: A Deep Learning Food and Drink Image Recognition System for Dietary Assessment.

PubMed

Mezgec, Simon; Koroušić Seljak, Barbara

2017-06-27

Automatic food image recognition systems are alleviating the process of food-intake estimation and dietary assessment. However, due to the nature of food images, their recognition is a particularly challenging task, which is why traditional approaches in the field have achieved a low classification accuracy. Deep neural networks have outperformed such solutions, and we present a novel approach to the problem of food and drink image detection and recognition that uses a newly-defined deep convolutional neural network architecture, called NutriNet. This architecture was tuned on a recognition dataset containing 225,953 512 × 512 pixel images of 520 different food and drink items from a broad spectrum of food groups, on which we achieved a classification accuracy of 86 . 72 % , along with an accuracy of 94 . 47 % on a detection dataset containing 130 , 517 images. We also performed a real-world test on a dataset of self-acquired images, combined with images from Parkinson's disease patients, all taken using a smartphone camera, achieving a top-five accuracy of 55 % , which is an encouraging result for real-world images. Additionally, we tested NutriNet on the University of Milano-Bicocca 2016 (UNIMIB2016) food image dataset, on which we improved upon the provided baseline recognition result. An online training component was implemented to continually fine-tune the food and drink recognition model on new images. The model is being used in practice as part of a mobile app for the dietary assessment of Parkinson's disease patients.

Constrained Low-Rank Learning Using Least Squares-Based Regularization.

PubMed

Li, Ping; Yu, Jun; Wang, Meng; Zhang, Luming; Cai, Deng; Li, Xuelong

2017-12-01

Low-rank learning has attracted much attention recently due to its efficacy in a rich variety of real-world tasks, e.g., subspace segmentation and image categorization. Most low-rank methods are incapable of capturing low-dimensional subspace for supervised learning tasks, e.g., classification and regression. This paper aims to learn both the discriminant low-rank representation (LRR) and the robust projecting subspace in a supervised manner. To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization. Naturally, the data label structure tends to resemble that of the corresponding low-dimensional representation, which is derived from the robust subspace projection of clean data by low-rank learning. Moreover, the low-dimensional representation of original data can be paired with some informative structure by imposing an appropriate constraint, e.g., Laplacian regularizer. Therefore, we propose a novel constrained LRR method. The objective function is formulated as a constrained nuclear norm minimization problem, which can be solved by the inexact augmented Lagrange multiplier algorithm. Extensive experiments on image classification, human pose estimation, and robust face recovery have confirmed the superiority of our method.

Manifold Regularized Experimental Design for Active Learning.

PubMed

Zhang, Lining; Shum, Hubert P H; Shao, Ling

2016-12-02

Various machine learning and data mining tasks in classification require abundant data samples to be labeled for training. Conventional active learning methods aim at labeling the most informative samples for alleviating the labor of the user. Many previous studies in active learning select one sample after another in a greedy manner. However, this is not very effective because the classification models has to be retrained for each newly labeled sample. Moreover, many popular active learning approaches utilize the most uncertain samples by leveraging the classification hyperplane of the classifier, which is not appropriate since the classification hyperplane is inaccurate when the training data are small-sized. The problem of insufficient training data in real-world systems limits the potential applications of these approaches. This paper presents a novel method of active learning called manifold regularized experimental design (MRED), which can label multiple informative samples at one time for training. In addition, MRED gives an explicit geometric explanation for the selected samples to be labeled by the user. Different from existing active learning methods, our method avoids the intrinsic problems caused by insufficiently labeled samples in real-world applications. Various experiments on synthetic datasets, the Yale face database and the Corel image database have been carried out to show how MRED outperforms existing methods.

Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): A new radiomics descriptor.

PubMed

Prasanna, Prateek; Tiwari, Pallavi; Madabhushi, Anant

2016-11-22

In this paper, we introduce a new radiomic descriptor, Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe) for capturing subtle differences between benign and pathologic phenotypes which may be visually indistinguishable on routine anatomic imaging. CoLlAGe seeks to capture and exploit local anisotropic differences in voxel-level gradient orientations to distinguish similar appearing phenotypes. CoLlAGe involves assigning every image voxel an entropy value associated with the co-occurrence matrix of gradient orientations computed around every voxel. The hypothesis behind CoLlAGe is that benign and pathologic phenotypes even though they may appear similar on anatomic imaging, will differ in their local entropy patterns, in turn reflecting subtle local differences in tissue microarchitecture. We demonstrate CoLlAGe's utility in three clinically challenging classification problems: distinguishing (1) radiation necrosis, a benign yet confounding effect of radiation treatment, from recurrent tumors on T1-w MRI in 42 brain tumor patients, (2) different molecular sub-types of breast cancer on DCE-MRI in 65 studies and (3) non-small cell lung cancer (adenocarcinomas) from benign fungal infection (granulomas) on 120 non-contrast CT studies. For each of these classification problems, CoLlAGE in conjunction with a random forest classifier outperformed state of the art radiomic descriptors (Haralick, Gabor, Histogram of Gradient Orientations).

Wishart Deep Stacking Network for Fast POLSAR Image Classification.

PubMed

Jiao, Licheng; Liu, Fang

2016-05-11

Inspired by the popular deep learning architecture - Deep Stacking Network (DSN), a specific deep model for polarimetric synthetic aperture radar (POLSAR) image classification is proposed in this paper, which is named as Wishart Deep Stacking Network (W-DSN). First of all, a fast implementation of Wishart distance is achieved by a special linear transformation, which speeds up the classification of POLSAR image and makes it possible to use this polarimetric information in the following Neural Network (NN). Then a single-hidden-layer neural network based on the fast Wishart distance is defined for POLSAR image classification, which is named as Wishart Network (WN) and improves the classification accuracy. Finally, a multi-layer neural network is formed by stacking WNs, which is in fact the proposed deep learning architecture W-DSN for POLSAR image classification and improves the classification accuracy further. In addition, the structure of WN can be expanded in a straightforward way by adding hidden units if necessary, as well as the structure of the W-DSN. As a preliminary exploration on formulating specific deep learning architecture for POLSAR image classification, the proposed methods may establish a simple but clever connection between POLSAR image interpretation and deep learning. The experiment results tested on real POLSAR image show that the fast implementation of Wishart distance is very efficient (a POLSAR image with 768000 pixels can be classified in 0.53s), and both the single-hidden-layer architecture WN and the deep learning architecture W-DSN for POLSAR image classification perform well and work efficiently.

Object-based land cover classification based on fusion of multifrequency SAR data and THAICHOTE optical imagery

NASA Astrophysics Data System (ADS)

Sukawattanavijit, Chanika; Srestasathiern, Panu

2017-10-01

Land Use and Land Cover (LULC) information are significant to observe and evaluate environmental change. LULC classification applying remotely sensed data is a technique popularly employed on a global and local dimension particularly, in urban areas which have diverse land cover types. These are essential components of the urban terrain and ecosystem. In the present, object-based image analysis (OBIA) is becoming widely popular for land cover classification using the high-resolution image. COSMO-SkyMed SAR data was fused with THAICHOTE (namely, THEOS: Thailand Earth Observation Satellite) optical data for land cover classification using object-based. This paper indicates a comparison between object-based and pixel-based approaches in image fusion. The per-pixel method, support vector machines (SVM) was implemented to the fused image based on Principal Component Analysis (PCA). For the objectbased classification was applied to the fused images to separate land cover classes by using nearest neighbor (NN) classifier. Finally, the accuracy assessment was employed by comparing with the classification of land cover mapping generated from fused image dataset and THAICHOTE image. The object-based data fused COSMO-SkyMed with THAICHOTE images demonstrated the best classification accuracies, well over 85%. As the results, an object-based data fusion provides higher land cover classification accuracy than per-pixel data fusion.

Artificial intelligence techniques for embryo and oocyte classification.

PubMed

Manna, Claudio; Nanni, Loris; Lumini, Alessandra; Pappalardo, Sebastiana

2013-01-01

One of the most relevant aspects in assisted reproduction technology is the possibility of characterizing and identifying the most viable oocytes or embryos. In most cases, embryologists select them by visual examination and their evaluation is totally subjective. Recently, due to the rapid growth in the capacity to extract texture descriptors from a given image, a growing interest has been shown in the use of artificial intelligence methods for embryo or oocyte scoring/selection in IVF programmes. This work concentrates the efforts on the possible prediction of the quality of embryos and oocytes in order to improve the performance of assisted reproduction technology, starting from their images. The artificial intelligence system proposed in this work is based on a set of Levenberg-Marquardt neural networks trained using textural descriptors (the local binary patterns). The proposed system was tested on two data sets of 269 oocytes and 269 corresponding embryos from 104 women and compared with other machine learning methods already proposed in the past for similar classification problems. Although the results are only preliminary, they show an interesting classification performance. This technique may be of particular interest in those countries where legislation restricts embryo selection. One of the most relevant aspects in assisted reproduction technology is the possibility of characterizing and identifying the most viable oocytes or embryos. In most cases, embryologists select them by visual examination and their evaluation is totally subjective. Recently, due to the rapid growth in our capacity to extract texture descriptors from a given image, a growing interest has been shown in the use of artificial intelligence methods for embryo or oocyte scoring/selection in IVF programmes. In this work, we concentrate our efforts on the possible prediction of the quality of embryos and oocytes in order to improve the performance of assisted reproduction technology, starting from their images. The artificial intelligence system proposed in this work is based on a set of Levenberg-Marquardt neural networks trained using textural descriptors (the 'local binary patterns'). The proposed system is tested on two data sets, of 269 oocytes and 269 corresponding embryos from 104 women, and compared with other machine learning methods already proposed in the past for similar classification problems. Although the results are only preliminary, they showed an interesting classification performance. This technique may be of particular interest in those countries where legislation restricts embryo selection. Copyright © 2012 Reproductive Healthcare Ltd. Published by Elsevier Ltd. All rights reserved.

Fusion of 3D laser scanner and depth images for obstacle recognition in mobile applications

NASA Astrophysics Data System (ADS)

Budzan, Sebastian; Kasprzyk, Jerzy

2016-02-01

The problem of obstacle detection and recognition or, generally, scene mapping is one of the most investigated problems in computer vision, especially in mobile applications. In this paper a fused optical system using depth information with color images gathered from the Microsoft Kinect sensor and 3D laser range scanner data is proposed for obstacle detection and ground estimation in real-time mobile systems. The algorithm consists of feature extraction in the laser range images, processing of the depth information from the Kinect sensor, fusion of the sensor information, and classification of the data into two separate categories: road and obstacle. Exemplary results are presented and it is shown that fusion of information gathered from different sources increases the effectiveness of the obstacle detection in different scenarios, and it can be used successfully for road surface mapping.

Quantification and Segmentation of Brain Tissues from MR Images: A Probabilistic Neural Network Approach

PubMed Central

Wang, Yue; Adalý, Tülay; Kung, Sun-Yuan; Szabo, Zsolt

2007-01-01

This paper presents a probabilistic neural network based technique for unsupervised quantification and segmentation of brain tissues from magnetic resonance images. It is shown that this problem can be solved by distribution learning and relaxation labeling, resulting in an efficient method that may be particularly useful in quantifying and segmenting abnormal brain tissues where the number of tissue types is unknown and the distributions of tissue types heavily overlap. The new technique uses suitable statistical models for both the pixel and context images and formulates the problem in terms of model-histogram fitting and global consistency labeling. The quantification is achieved by probabilistic self-organizing mixtures and the segmentation by a probabilistic constraint relaxation network. The experimental results show the efficient and robust performance of the new algorithm and that it outperforms the conventional classification based approaches. PMID:18172510

Do we need annotation experts? A case study in celiac disease classification.

PubMed

Kwitt, Roland; Hegenbart, Sebastian; Rasiwasia, Nikhil; Vécsei, Andreas; Uhl, Andreas

2014-01-01

Inference of clinically-relevant findings from the visual appearance of images has become an essential part of processing pipelines for many problems in medical imaging. Typically, a sufficient amount labeled training data is assumed to be available, provided by domain experts. However, acquisition of this data is usually a time-consuming and expensive endeavor. In this work, we ask the question if, for certain problems, expert knowledge is actually required. In fact, we investigate the impact of letting non-expert volunteers annotate a database of endoscopy images which are then used to assess the absence/presence of celiac disease. Contrary to previous approaches, we are not interested in algorithms that can handle the label noise. Instead, we present compelling empirical evidence that label noise can be compensated by a sufficiently large corpus of training data, labeled by the non-experts.

Weighted Discriminative Dictionary Learning based on Low-rank Representation

NASA Astrophysics Data System (ADS)

Chang, Heyou; Zheng, Hao

2017-01-01

Low-rank representation has been widely used in the field of pattern classification, especially when both training and testing images are corrupted with large noise. Dictionary plays an important role in low-rank representation. With respect to the semantic dictionary, the optimal representation matrix should be block-diagonal. However, traditional low-rank representation based dictionary learning methods cannot effectively exploit the discriminative information between data and dictionary. To address this problem, this paper proposed weighted discriminative dictionary learning based on low-rank representation, where a weighted representation regularization term is constructed. The regularization associates label information of both training samples and dictionary atoms, and encourages to generate a discriminative representation with class-wise block-diagonal structure, which can further improve the classification performance where both training and testing images are corrupted with large noise. Experimental results demonstrate advantages of the proposed method over the state-of-the-art methods.

COVARIANCE ESTIMATION USING CONJUGATE GRADIENT FOR 3D CLASSIFICATION IN CRYO-EM.

PubMed

Andén, Joakim; Katsevich, Eugene; Singer, Amit

2015-04-01

Classifying structural variability in noisy projections of biological macromolecules is a central problem in Cryo-EM. In this work, we build on a previous method for estimating the covariance matrix of the three-dimensional structure present in the molecules being imaged. Our proposed method allows for incorporation of contrast transfer function and non-uniform distribution of viewing angles, making it more suitable for real-world data. We evaluate its performance on a synthetic dataset and an experimental dataset obtained by imaging a 70S ribosome complex.

Multiple directed graph large-class multi-spectral processor

NASA Technical Reports Server (NTRS)

Casasent, David; Liu, Shiaw-Dong; Yoneyama, Hideyuki

1988-01-01

Numerical analysis techniques for the interpretation of high-resolution imaging-spectrometer data are described and demonstrated. The method proposed involves the use of (1) a hierarchical classifier with a tree structure generated automatically by a Fisher linear-discriminant-function algorithm and (2) a novel multiple-directed-graph scheme which reduces the local maxima and the number of perturbations required. Results for a 500-class test problem involving simulated imaging-spectrometer data are presented in tables and graphs; 100-percent-correct classification is achieved with an improvement factor of 5.

MUSIC-type imaging of small perfectly conducting cracks with an unknown frequency

NASA Astrophysics Data System (ADS)

Park, Won-Kwang

2015-09-01

MUltiple SIgnal Classification (MUSIC) is a famous non-iterative detection algorithm in inverse scattering problems. However, when the applied frequency is unknown, inaccurate locations are identified via MUSIC. This fact has been confirmed through numerical simulations. However, the reason behind this phenomenon has not been investigated theoretically. Motivated by this fact, we identify the structure of MUSIC-type imaging functionals with unknown frequency, by establishing a relationship with Bessel functions of order zero of the first kind. Through this, we can explain why inaccurate results appear.

Automated image processing of Landsat II digital data for watershed runoff prediction

NASA Technical Reports Server (NTRS)

Sasso, R. R.; Jensen, J. R.; Estes, J. E.

1977-01-01

Digital image processing of Landsat data from a 230 sq km area was examined as a possible means of generating soil cover information for use in the watershed runoff prediction of Kern County, California. The soil cover information included data on brush, grass, pasture lands and forests. A classification accuracy of 94% for the Landsat-based soil cover survey suggested that the technique could be applied to the watershed runoff estimate. However, problems involving the survey of complex mountainous environments may require further attention

Robust Feature Matching in Terrestrial Image Sequences

NASA Astrophysics Data System (ADS)

Abbas, A.; Ghuffar, S.

2018-04-01

From the last decade, the feature detection, description and matching techniques are most commonly exploited in various photogrammetric and computer vision applications, which includes: 3D reconstruction of scenes, image stitching for panoramic creation, image classification, or object recognition etc. However, in terrestrial imagery of urban scenes contains various issues, which include duplicate and identical structures (i.e. repeated windows and doors) that cause the problem in feature matching phase and ultimately lead to failure of results specially in case of camera pose and scene structure estimation. In this paper, we will address the issue related to ambiguous feature matching in urban environment due to repeating patterns.

Semantic Segmentation of Forest Stands of Pure Species as a Global Optimization Problem

NASA Astrophysics Data System (ADS)

Dechesne, C.; Mallet, C.; Le Bris, A.; Gouet-Brunet, V.

2017-05-01

Forest stand delineation is a fundamental task for forest management purposes, that is still mainly manually performed through visual inspection of geospatial (very) high spatial resolution images. Stand detection has been barely addressed in the literature which has mainly focused, in forested environments, on individual tree extraction and tree species classification. From a methodological point of view, stand detection can be considered as a semantic segmentation problem. It offers two advantages. First, one can retrieve the dominant tree species per segment. Secondly, one can benefit from existing low-level tree species label maps from the literature as a basis for high-level object extraction. Thus, the semantic segmentation issue becomes a regularization issue in a weakly structured environment and can be formulated in an energetical framework. This papers aims at investigating which regularization strategies of the literature are the most adapted to delineate and classify forest stands of pure species. Both airborne lidar point clouds and multispectral very high spatial resolution images are integrated for that purpose. The local methods (such as filtering and probabilistic relaxation) are not adapted for such problem since the increase of the classification accuracy is below 5%. The global methods, based on an energy model, tend to be more efficient with an accuracy gain up to 15%. The segmentation results using such models have an accuracy ranging from 96% to 99%.

APPLEPIPS /Apple Personal Image Processing System/ - An interactive digital image processing system for the Apple II microcomputer

NASA Technical Reports Server (NTRS)

Masuoka, E.; Rose, J.; Quattromani, M.

1981-01-01

Recent developments related to microprocessor-based personal computers have made low-cost digital image processing systems a reality. Image analysis systems built around these microcomputers provide color image displays for images as large as 256 by 240 pixels in sixteen colors. Descriptive statistics can be computed for portions of an image, and supervised image classification can be obtained. The systems support Basic, Fortran, Pascal, and assembler language. A description is provided of a system which is representative of the new microprocessor-based image processing systems currently on the market. While small systems may never be truly independent of larger mainframes, because they lack 9-track tape drives, the independent processing power of the microcomputers will help alleviate some of the turn-around time problems associated with image analysis and display on the larger multiuser systems.

Cascaded discrimination of normal, abnormal, and confounder classes in histopathology: Gleason grading of prostate cancer

PubMed Central

2012-01-01

Background Automated classification of histopathology involves identification of multiple classes, including benign, cancerous, and confounder categories. The confounder tissue classes can often mimic and share attributes with both the diseased and normal tissue classes, and can be particularly difficult to identify, both manually and by automated classifiers. In the case of prostate cancer, they may be several confounding tissue types present in a biopsy sample, posing as major sources of diagnostic error for pathologists. Two common multi-class approaches are one-shot classification (OSC), where all classes are identified simultaneously, and one-versus-all (OVA), where a “target” class is distinguished from all “non-target” classes. OSC is typically unable to handle discrimination of classes of varying similarity (e.g. with images of prostate atrophy and high grade cancer), while OVA forces several heterogeneous classes into a single “non-target” class. In this work, we present a cascaded (CAS) approach to classifying prostate biopsy tissue samples, where images from different classes are grouped to maximize intra-group homogeneity while maximizing inter-group heterogeneity. Results We apply the CAS approach to categorize 2000 tissue samples taken from 214 patient studies into seven classes: epithelium, stroma, atrophy, prostatic intraepithelial neoplasia (PIN), and prostate cancer Gleason grades 3, 4, and 5. A series of increasingly granular binary classifiers are used to split the different tissue classes until the images have been categorized into a single unique class. Our automatically-extracted image feature set includes architectural features based on location of the nuclei within the tissue sample as well as texture features extracted on a per-pixel level. The CAS strategy yields a positive predictive value (PPV) of 0.86 in classifying the 2000 tissue images into one of 7 classes, compared with the OVA (0.77 PPV) and OSC approaches (0.76 PPV). Conclusions Use of the CAS strategy increases the PPV for a multi-category classification system over two common alternative strategies. In classification problems such as histopathology, where multiple class groups exist with varying degrees of heterogeneity, the CAS system can intelligently assign class labels to objects by performing multiple binary classifications according to domain knowledge. PMID:23110677

Boosting instance prototypes to detect local dermoscopic features.

PubMed

Situ, Ning; Yuan, Xiaojing; Zouridakis, George

2010-01-01

Local dermoscopic features are useful in many dermoscopic criteria for skin cancer detection. We address the problem of detecting local dermoscopic features from epiluminescence (ELM) microscopy skin lesion images. We formulate the recognition of local dermoscopic features as a multi-instance learning (MIL) problem. We employ the method of diverse density (DD) and evidence confidence (EC) function to convert MIL to a single-instance learning (SIL) problem. We apply Adaboost to improve the classification performance with support vector machines (SVMs) as the base classifier. We also propose to boost the selection of instance prototypes through changing the data weights in the DD function. We validate the methods on detecting ten local dermoscopic features from a dataset with 360 images. We compare the performance of the MIL approach, its boosting version, and a baseline method without using MIL. Our results show that boosting can provide performance improvement compared to the other two methods.

Deep learning classifier with optical coherence tomography images for early dental caries detection

NASA Astrophysics Data System (ADS)

Karimian, Nima; Salehi, Hassan S.; Mahdian, Mina; Alnajjar, Hisham; Tadinada, Aditya

2018-02-01

Dental caries is a microbial disease that results in localized dissolution of the mineral content of dental tissue. Despite considerable decline in the incidence of dental caries, it remains a major health problem in many societies. Early detection of incipient lesions at initial stages of demineralization can result in the implementation of non-surgical preventive approaches to reverse the demineralization process. In this paper, we present a novel approach combining deep convolutional neural networks (CNN) and optical coherence tomography (OCT) imaging modality for classification of human oral tissues to detect early dental caries. OCT images of oral tissues with various densities were input to a CNN classifier to determine variations in tissue densities resembling the demineralization process. The CNN automatically learns a hierarchy of increasingly complex features and a related classifier directly from training data sets. The initial CNN layer parameters were randomly selected. The training set is split into minibatches, with 10 OCT images per batch. Given a batch of training patches, the CNN employs two convolutional and pooling layers to extract features and then classify each patch based on the probabilities from the SoftMax classification layer (output-layer). Afterward, the CNN calculates the error between the classification result and the reference label, and then utilizes the backpropagation process to fine-tune all the layer parameters to minimize this error using batch gradient descent algorithm. We validated our proposed technique on ex-vivo OCT images of human oral tissues (enamel, cortical-bone, trabecular-bone, muscular-tissue, and fatty-tissue), which attested to effectiveness of our proposed method.

Searching for patterns in remote sensing image databases using neural networks

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1995-01-01

We have investigated a method, based on a successful neural network multispectral image classification system, of searching for single patterns in remote sensing databases. While defining the pattern to search for and the feature to be used for that search (spectral, spatial, temporal, etc.) is challenging, a more difficult task is selecting competing patterns to train against the desired pattern. Schemes for competing pattern selection, including random selection and human interpreted selection, are discussed in the context of an example detection of dense urban areas in Landsat Thematic Mapper imagery. When applying the search to multiple images, a simple normalization method can alleviate the problem of inconsistent image calibration. Another potential problem, that of highly compressed data, was found to have a minimal effect on the ability to detect the desired pattern. The neural network algorithm has been implemented using the PVM (Parallel Virtual Machine) library and nearly-optimal speedups have been obtained that help alleviate the long process of searching through imagery.

Contribution of non-negative matrix factorization to the classification of remote sensing images

NASA Astrophysics Data System (ADS)

Karoui, M. S.; Deville, Y.; Hosseini, S.; Ouamri, A.; Ducrot, D.

2008-10-01

Remote sensing has become an unavoidable tool for better managing our environment, generally by realizing maps of land cover using classification techniques. The classification process requires some pre-processing, especially for data size reduction. The most usual technique is Principal Component Analysis. Another approach consists in regarding each pixel of the multispectral image as a mixture of pure elements contained in the observed area. Using Blind Source Separation (BSS) methods, one can hope to unmix each pixel and to perform the recognition of the classes constituting the observed scene. Our contribution consists in using Non-negative Matrix Factorization (NMF) combined with sparse coding as a solution to BSS, in order to generate new images (which are at least partly separated images) using HRV SPOT images from Oran area, Algeria). These images are then used as inputs of a supervised classifier integrating textural information. The results of classifications of these "separated" images show a clear improvement (correct pixel classification rate improved by more than 20%) compared to classification of initial (i.e. non separated) images. These results show the contribution of NMF as an attractive pre-processing for classification of multispectral remote sensing imagery.

Manifold Preserving: An Intrinsic Approach for Semisupervised Distance Metric Learning.

PubMed

Ying, Shihui; Wen, Zhijie; Shi, Jun; Peng, Yaxin; Peng, Jigen; Qiao, Hong

2017-05-18

In this paper, we address the semisupervised distance metric learning problem and its applications in classification and image retrieval. First, we formulate a semisupervised distance metric learning model by considering the metric information of inner classes and interclasses. In this model, an adaptive parameter is designed to balance the inner metrics and intermetrics by using data structure. Second, we convert the model to a minimization problem whose variable is symmetric positive-definite matrix. Third, in implementation, we deduce an intrinsic steepest descent method, which assures that the metric matrix is strictly symmetric positive-definite at each iteration, with the manifold structure of the symmetric positive-definite matrix manifold. Finally, we test the proposed algorithm on conventional data sets, and compare it with other four representative methods. The numerical results validate that the proposed method significantly improves the classification with the same computational efficiency.

Review of Medical Image Classification using the Adaptive Neuro-Fuzzy Inference System

PubMed Central

Hosseini, Monireh Sheikh; Zekri, Maryam

2012-01-01

Image classification is an issue that utilizes image processing, pattern recognition and classification methods. Automatic medical image classification is a progressive area in image classification, and it is expected to be more developed in the future. Because of this fact, automatic diagnosis can assist pathologists by providing second opinions and reducing their workload. This paper reviews the application of the adaptive neuro-fuzzy inference system (ANFIS) as a classifier in medical image classification during the past 16 years. ANFIS is a fuzzy inference system (FIS) implemented in the framework of an adaptive fuzzy neural network. It combines the explicit knowledge representation of an FIS with the learning power of artificial neural networks. The objective of ANFIS is to integrate the best features of fuzzy systems and neural networks. A brief comparison with other classifiers, main advantages and drawbacks of this classifier are investigated. PMID:23493054

Advancing Bag-of-Visual-Words Representations for Lesion Classification in Retinal Images

PubMed Central

Pires, Ramon; Jelinek, Herbert F.; Wainer, Jacques; Valle, Eduardo; Rocha, Anderson

2014-01-01

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.22.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors. PMID:24886780

Validation of the international labour office digitized standard images for recognition and classification of radiographs of pneumoconiosis.

PubMed

Halldin, Cara N; Petsonk, Edward L; Laney, A Scott

2014-03-01

Chest radiographs are recommended for prevention and detection of pneumoconiosis. In 2011, the International Labour Office (ILO) released a revision of the International Classification of Radiographs of Pneumoconioses that included a digitized standard images set. The present study compared results of classifications of digital chest images performed using the new ILO 2011 digitized standard images to classification approaches used in the past. Underground coal miners (N = 172) were examined using both digital and film-screen radiography (FSR) on the same day. Seven National Institute for Occupational Safety and Health-certified B Readers independently classified all 172 digital radiographs, once using the ILO 2011 digitized standard images (DRILO2011-D) and once using digitized standard images used in the previous research (DRRES). The same seven B Readers classified all the miners' chest films using the ILO film-based standards. Agreement between classifications of FSR and digital radiography was identical, using a standard image set (either DRILO2011-D or DRRES). The overall weighted κ value was 0.58. Some specific differences in the results were seen and noted. However, intrareader variability in this study was similar to the published values and did not appear to be affected by the use of the new ILO 2011 digitized standard images. These findings validate the use of the ILO digitized standard images for classification of small pneumoconiotic opacities. When digital chest radiographs are obtained and displayed appropriately, results of pneumoconiosis classifications using the 2011 ILO digitized standards are comparable to film-based ILO classifications and to classifications using earlier research standards. Published by Elsevier Inc.

HCP: A Flexible CNN Framework for Multi-label Image Classification.

PubMed

Wei, Yunchao; Xia, Wei; Lin, Min; Huang, Junshi; Ni, Bingbing; Dong, Jian; Zhao, Yao; Yan, Shuicheng

2015-10-26

Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still remains an open problem, mainly due to the complex underlying object layouts and insufficient multi-label training images. In this work, we propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Some unique characteristics of this flexible deep CNN infrastructure include: 1) no ground-truth bounding box information is required for training; 2) the whole HCP infrastructure is robust to possibly noisy and/or redundant hypotheses; 3) the shared CNN is flexible and can be well pre-trained with a large-scale single-label image dataset, e.g., ImageNet; and 4) it may naturally output multi-label prediction results. Experimental results on Pascal VOC 2007 and VOC 2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts. In particular, the mAP reaches 90.5% by HCP only and 93.2% after the fusion with our complementary result in [44] based on hand-crafted features on the VOC 2012 dataset.

Skimming Digits: Neuromorphic Classification of Spike-Encoded Images

PubMed Central

Cohen, Gregory K.; Orchard, Garrick; Leng, Sio-Hoi; Tapson, Jonathan; Benosman, Ryad B.; van Schaik, André

2016-01-01

The growing demands placed upon the field of computer vision have renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST, a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM), a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serve to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value. PMID:27199646

Land-cover classification in a moist tropical region of Brazil with Landsat TM imagery.

PubMed

Li, Guiying; Lu, Dengsheng; Moran, Emilio; Hetrick, Scott

2011-01-01

This research aims to improve land-cover classification accuracy in a moist tropical region in Brazil by examining the use of different remote sensing-derived variables and classification algorithms. Different scenarios based on Landsat Thematic Mapper (TM) spectral data and derived vegetation indices and textural images, and different classification algorithms - maximum likelihood classification (MLC), artificial neural network (ANN), classification tree analysis (CTA), and object-based classification (OBC), were explored. The results indicated that a combination of vegetation indices as extra bands into Landsat TM multispectral bands did not improve the overall classification performance, but the combination of textural images was valuable for improving vegetation classification accuracy. In particular, the combination of both vegetation indices and textural images into TM multispectral bands improved overall classification accuracy by 5.6% and kappa coefficient by 6.25%. Comparison of the different classification algorithms indicated that CTA and ANN have poor classification performance in this research, but OBC improved primary forest and pasture classification accuracies. This research indicates that use of textural images or use of OBC are especially valuable for improving the vegetation classes such as upland and liana forest classes having complex stand structures and having relatively large patch sizes.

Land-cover classification in a moist tropical region of Brazil with Landsat TM imagery

PubMed Central

LI, GUIYING; LU, DENGSHENG; MORAN, EMILIO; HETRICK, SCOTT

2011-01-01

This research aims to improve land-cover classification accuracy in a moist tropical region in Brazil by examining the use of different remote sensing-derived variables and classification algorithms. Different scenarios based on Landsat Thematic Mapper (TM) spectral data and derived vegetation indices and textural images, and different classification algorithms – maximum likelihood classification (MLC), artificial neural network (ANN), classification tree analysis (CTA), and object-based classification (OBC), were explored. The results indicated that a combination of vegetation indices as extra bands into Landsat TM multispectral bands did not improve the overall classification performance, but the combination of textural images was valuable for improving vegetation classification accuracy. In particular, the combination of both vegetation indices and textural images into TM multispectral bands improved overall classification accuracy by 5.6% and kappa coefficient by 6.25%. Comparison of the different classification algorithms indicated that CTA and ANN have poor classification performance in this research, but OBC improved primary forest and pasture classification accuracies. This research indicates that use of textural images or use of OBC are especially valuable for improving the vegetation classes such as upland and liana forest classes having complex stand structures and having relatively large patch sizes. PMID:22368311

Computer-aided diagnostics of screening mammography using content-based image retrieval

NASA Astrophysics Data System (ADS)

Deserno, Thomas M.; Soiron, Michael; de Oliveira, Júlia E. E.; de A. Araújo, Arnaldo

2012-03-01

Breast cancer is one of the main causes of death among women in occidental countries. In the last years, screening mammography has been established worldwide for early detection of breast cancer, and computer-aided diagnostics (CAD) is being developed to assist physicians reading mammograms. A promising method for CAD is content-based image retrieval (CBIR). Recently, we have developed a classification scheme of suspicious tissue pattern based on the support vector machine (SVM). In this paper, we continue moving towards automatic CAD of screening mammography. The experiments are based on in total 10,509 radiographs that have been collected from different sources. From this, 3,375 images are provided with one and 430 radiographs with more than one chain code annotation of cancerous regions. In different experiments, this data is divided into 12 and 20 classes, distinguishing between four categories of tissue density, three categories of pathology and in the 20 class problem two categories of different types of lesions. Balancing the number of images in each class yields 233 and 45 images remaining in each of the 12 and 20 classes, respectively. Using a two-dimensional principal component analysis, features are extracted from small patches of 128 x 128 pixels and classified by means of a SVM. Overall, the accuracy of the raw classification was 61.6 % and 52.1 % for the 12 and the 20 class problem, respectively. The confusion matrices are assessed for detailed analysis. Furthermore, an implementation of a SVM-based CBIR system for CADx in screening mammography is presented. In conclusion, with a smarter patch extraction, the CBIR approach might reach precision rates that are helpful for the physicians. This, however, needs more comprehensive evaluation on clinical data.

Classification of large-scale fundus image data sets: a cloud-computing framework.

PubMed

Roychowdhury, Sohini

2016-08-01

Large medical image data sets with high dimensionality require substantial amount of computation time for data creation and data processing. This paper presents a novel generalized method that finds optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracy for detection of diabetic retinopathy (DR). First, region-based and pixel-based features are extracted from fundus images for classification of DR lesions and vessel-like structures. Next, feature ranking strategies are used to distinguish the optimal classification feature sets. DR lesion and vessel classification accuracies are computed using the boosted decision tree and decision forest classifiers in the Microsoft Azure Machine Learning Studio platform, respectively. For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90.1% in 792 seconds. Also, for classification of red lesion regions and hemorrhages from microaneurysms, accuracies of 85% and 72% are observed, respectively. For images from STARE data set, 40 high-ranked features can classify minor blood vessels with an accuracy of 83.5% in 326 seconds. Such cloud-based fundus image analysis systems can significantly enhance the borderline classification performances in automated screening systems.

The artificial object detection and current velocity measurement using SAR ocean surface images

NASA Astrophysics Data System (ADS)

Alpatov, Boris; Strotov, Valery; Ershov, Maksim; Muraviev, Vadim; Feldman, Alexander; Smirnov, Sergey

2017-10-01

Due to the fact that water surface covers wide areas, remote sensing is the most appropriate way of getting information about ocean environment for vessel tracking, security purposes, ecological studies and others. Processing of synthetic aperture radar (SAR) images is extensively used for control and monitoring of the ocean surface. Image data can be acquired from Earth observation satellites, such as TerraSAR-X, ERS, and COSMO-SkyMed. Thus, SAR image processing can be used to solve many problems arising in this field of research. This paper discusses some of them including ship detection, oil pollution control and ocean currents mapping. Due to complexity of the problem several specialized algorithm are necessary to develop. The oil spill detection algorithm consists of the following main steps: image preprocessing, detection of dark areas, parameter extraction and classification. The ship detection algorithm consists of the following main steps: prescreening, land masking, image segmentation combined with parameter measurement, ship orientation estimation and object discrimination. The proposed approach to ocean currents mapping is based on Doppler's law. The results of computer modeling on real SAR images are presented. Based on these results it is concluded that the proposed approaches can be used in maritime applications.

Analysis of MUSIC-type imaging functional for single, thin electromagnetic inhomogeneity in limited-view inverse scattering problem

NASA Astrophysics Data System (ADS)

Ahn, Chi Young; Jeon, Kiwan; Park, Won-Kwang

2015-06-01

This study analyzes the well-known MUltiple SIgnal Classification (MUSIC) algorithm to identify unknown support of thin penetrable electromagnetic inhomogeneity from scattered field data collected within the so-called multi-static response matrix in limited-view inverse scattering problems. The mathematical theories of MUSIC are partially discovered, e.g., in the full-view problem, for an unknown target of dielectric contrast or a perfectly conducting crack with the Dirichlet boundary condition (Transverse Magnetic-TM polarization) and so on. Hence, we perform further research to analyze the MUSIC-type imaging functional and to certify some well-known but theoretically unexplained phenomena. For this purpose, we establish a relationship between the MUSIC imaging functional and an infinite series of Bessel functions of integer order of the first kind. This relationship is based on the rigorous asymptotic expansion formula in the existence of a thin inhomogeneity with a smooth supporting curve. Various results of numerical simulation are presented in order to support the identified structure of MUSIC. Although a priori information of the target is needed, we suggest a least condition of range of incident and observation directions to apply MUSIC in the limited-view problem.

Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images †

PubMed Central

Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

2017-01-01

Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications. PMID:28604624

Computer-Aided Diagnosis of Anterior Segment Eye Abnormalities using Visible Wavelength Image Analysis Based Machine Learning.

PubMed

S V, Mahesh Kumar; R, Gunasundari

2018-06-02

Eye disease is a major health problem among the elderly people. Cataract and corneal arcus are the major abnormalities that exist in the anterior segment eye region of aged people. Hence, computer-aided diagnosis of anterior segment eye abnormalities will be helpful for mass screening and grading in ophthalmology. In this paper, we propose a multiclass computer-aided diagnosis (CAD) system using visible wavelength (VW) eye images to diagnose anterior segment eye abnormalities. In the proposed method, the input VW eye images are pre-processed for specular reflection removal and the iris circle region is segmented using a circular Hough Transform (CHT)-based approach. The first-order statistical features and wavelet-based features are extracted from the segmented iris circle and used for classification. The Support Vector Machine (SVM) by Sequential Minimal Optimization (SMO) algorithm was used for the classification. In experiments, we used 228 VW eye images that belong to three different classes of anterior segment eye abnormalities. The proposed method achieved a predictive accuracy of 96.96% with 97% sensitivity and 99% specificity. The experimental results show that the proposed method has significant potential for use in clinical applications.

Training set size, scale, and features in Geographic Object-Based Image Analysis of very high resolution unmanned aerial vehicle imagery

NASA Astrophysics Data System (ADS)

Ma, Lei; Cheng, Liang; Li, Manchun; Liu, Yongxue; Ma, Xiaoxue

2015-04-01

Unmanned Aerial Vehicle (UAV) has been used increasingly for natural resource applications in recent years due to their greater availability and the miniaturization of sensors. In addition, Geographic Object-Based Image Analysis (GEOBIA) has received more attention as a novel paradigm for remote sensing earth observation data. However, GEOBIA generates some new problems compared with pixel-based methods. In this study, we developed a strategy for the semi-automatic optimization of object-based classification, which involves an area-based accuracy assessment that analyzes the relationship between scale and the training set size. We found that the Overall Accuracy (OA) increased as the training set ratio (proportion of the segmented objects used for training) increased when the Segmentation Scale Parameter (SSP) was fixed. The OA increased more slowly as the training set ratio became larger and a similar rule was obtained according to the pixel-based image analysis. The OA decreased as the SSP increased when the training set ratio was fixed. Consequently, the SSP should not be too large during classification using a small training set ratio. By contrast, a large training set ratio is required if classification is performed using a high SSP. In addition, we suggest that the optimal SSP for each class has a high positive correlation with the mean area obtained by manual interpretation, which can be summarized by a linear correlation equation. We expect that these results will be applicable to UAV imagery classification to determine the optimal SSP for each class.

The Analysis of Burrows Recognition Accuracy in XINJIANG'S Pasture Area Based on Uav Visible Images with Different Spatial Resolution

NASA Astrophysics Data System (ADS)

Sun, D.; Zheng, J. H.; Ma, T.; Chen, J. J.; Li, X.

2018-04-01

The rodent disaster is one of the main biological disasters in grassland in northern Xinjiang. The eating and digging behaviors will cause the destruction of ground vegetation, which seriously affected the development of animal husbandry and grassland ecological security. UAV low altitude remote sensing, as an emerging technique with high spatial resolution, can effectively recognize the burrows. However, how to select the appropriate spatial resolution to monitor the calamity of the rodent disaster is the first problem we need to pay attention to. The purpose of this study is to explore the optimal spatial scale on identification of the burrows by evaluating the impact of different spatial resolution for the burrows identification accuracy. In this study, we shoot burrows from different flight heights to obtain visible images of different spatial resolution. Then an object-oriented method is used to identify the caves, and we also evaluate the accuracy of the classification. We found that the highest classification accuracy of holes, the average has reached more than 80 %. At the altitude of 24 m and the spatial resolution of 1cm, the accuracy of the classification is the highest We have created a unique and effective way to identify burrows by using UAVs visible images. We draw the following conclusion: the best spatial resolution of burrows recognition is 1 cm using DJI PHANTOM-3 UAV, and the improvement of spatial resolution does not necessarily lead to the improvement of classification accuracy. This study lays the foundation for future research and can be extended to similar studies elsewhere.

Natural image classification driven by human brain activity

NASA Astrophysics Data System (ADS)

Zhang, Dai; Peng, Hanyang; Wang, Jinqiao; Tang, Ming; Xue, Rong; Zuo, Zhentao

2016-03-01

Natural image classification has been a hot topic in computer vision and pattern recognition research field. Since the performance of an image classification system can be improved by feature selection, many image feature selection methods have been developed. However, the existing supervised feature selection methods are typically driven by the class label information that are identical for different samples from the same class, ignoring with-in class image variability and therefore degrading the feature selection performance. In this study, we propose a novel feature selection method, driven by human brain activity signals collected using fMRI technique when human subjects were viewing natural images of different categories. The fMRI signals associated with subjects viewing different images encode the human perception of natural images, and therefore may capture image variability within- and cross- categories. We then select image features with the guidance of fMRI signals from brain regions with active response to image viewing. Particularly, bag of words features based on GIST descriptor are extracted from natural images for classification, and a sparse regression base feature selection method is adapted to select image features that can best predict fMRI signals. Finally, a classification model is built on the select image features to classify images without fMRI signals. The validation experiments for classifying images from 4 categories of two subjects have demonstrated that our method could achieve much better classification performance than the classifiers built on image feature selected by traditional feature selection methods.

Spatial-spectral blood cell classification with microscopic hyperspectral imagery

NASA Astrophysics Data System (ADS)

Ran, Qiong; Chang, Lan; Li, Wei; Xu, Xiaofeng

2017-10-01

Microscopic hyperspectral images provide a new way for blood cell examination. The hyperspectral imagery can greatly facilitate the classification of different blood cells. In this paper, the microscopic hyperspectral images are acquired by connecting the microscope and the hyperspectral imager, and then tested for blood cell classification. For combined use of the spectral and spatial information provided by hyperspectral images, a spatial-spectral classification method is improved from the classical extreme learning machine (ELM) by integrating spatial context into the image classification task with Markov random field (MRF) model. Comparisons are done among ELM, ELM-MRF, support vector machines(SVM) and SVMMRF methods. Results show the spatial-spectral classification methods(ELM-MRF, SVM-MRF) perform better than pixel-based methods(ELM, SVM), and the proposed ELM-MRF has higher precision and show more accurate location of cells.

Computational optical tomography using 3-D deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Nguyen, Thanh; Bui, Vy; Nehmetallah, George

2018-04-01

Deep convolutional neural networks (DCNNs) offer a promising performance for many image processing areas, such as super-resolution, deconvolution, image classification, denoising, and segmentation, with outstanding results. Here, we develop for the first time, to our knowledge, a method to perform 3-D computational optical tomography using 3-D DCNN. A simulated 3-D phantom dataset was first constructed and converted to a dataset of phase objects imaged on a spatial light modulator. For each phase image in the dataset, the corresponding diffracted intensity image was experimentally recorded on a CCD. We then experimentally demonstrate the ability of the developed 3-D DCNN algorithm to solve the inverse problem by reconstructing the 3-D index of refraction distributions of test phantoms from the dataset from their corresponding diffraction patterns.

Successive Over-Relaxation Technique for High-Performance Blind Image Deconvolution

DTIC Science & Technology

2015-06-08

deconvolution, space surveillance, Gauss - Seidel iteration 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT SAR 18, NUMBER OF PAGES 5...sensible approximate solutions to the ill-posed nonlinear inverse problem. These solutions are addresses as fixed points of the iteration which consists in...alternating approximations (AA) for the object and for the PSF performed with a prescribed number of inner iterative descents from trivial (zero

Visual Recognition Software for Binary Classification and its Application to Pollen Identification

NASA Astrophysics Data System (ADS)

Punyasena, S. W.; Tcheng, D. K.; Nayak, A.

2014-12-01

An underappreciated source of uncertainty in paleoecology is the uncertainty of palynological identifications. The confidence of any given identification is not regularly reported in published results, so cannot be incorporated into subsequent meta-analyses. Automated identifications systems potentially provide a means of objectively measuring the confidence of a given count or single identification, as well as a mechanism for increasing sample sizes and throughput. We developed the software ARLO (Automated Recognition with Layered Optimization) to tackle difficult visual classification problems such as pollen identification. ARLO applies pattern recognition and machine learning to the analysis of pollen images. The features that the system discovers are not the traditional features of pollen morphology. Instead, general purpose image features, such as pixel lines and grids of different dimensions, size, spacing, and resolution, are used. ARLO adapts to a given problem by searching for the most effective combination of feature representation and learning strategy. We present a two phase approach which uses our machine learning process to first segment pollen grains from the background and then classify pollen pixels and report species ratios. We conducted two separate experiments that utilized two distinct sets of algorithms and optimization procedures. The first analysis focused on reconstructing black and white spruce pollen ratios, training and testing our classification model at the slide level. This allowed us to directly compare our automated counts and expert counts to slides of known spruce ratios. Our second analysis focused on maximizing classification accuracy at the individual pollen grain level. Instead of predicting ratios of given slides, we predicted the species represented in a given image window. The resulting analysis was more scalable, as we were able to adapt the most efficient parts of the methodology from our first analysis. ARLO was able to distinguish between the pollen of black and white spruce with an accuracy of ~83.61%. This compared favorably to human expert performance. At the writing of this abstract, we are also experimenting with experimenting with the analysis of higher diversity samples, including modern tropical pollen material collected from ground pollen traps.

Determination of The Water Catchment Area in Semarang City Using a Combination of Object Based Image Analysis (OBIA) Classification, InSAR and Geographic Information System (GIS) Methods Based On a High-Resolution SPOT 6 Image and Radar Imagery

NASA Astrophysics Data System (ADS)

Prasetyo, Yudo; Ardi Gunawan, Setyo; Maksum, Zia Ul

2016-11-01

Semarang is the biggest city in central Java-Indonesia which has a rapid and massive infrastructure development nowadays. In order to control water resources and flood, the local goverment has been built east and west flood canal in Kaligarang and West Semarang River. One of main problem in Semarang city is the lack of fresh water in dry season because ground water is not rechargeable well. Rechargeable groundwater ability depends on underground water recharge rate and catchment area condition. The objective of the study is to determine condition and classification of water catchment area in Semarang city. The catchment area conditions will be determine by five parameters as follows soil type, land use, slope, ground water potential and rainfall intensity. In this study, we use three methods approach to solve the problem which is segmentation classification to acquire land use classification from high resolution imagery using nearest neighborhood algorithm, Interferometric Synthetic Aperture Radar (SAR) to derive DTM from SAR Imagery and multi criteria weighting and spatial analysis using GIS method. There are three types optical image (ALOS PRISM, SPOT-6 and ALOS PALSAR) to calculate water catchment area condition in Semarang city. For final result, this research will divide the water catchment into six criteria as follows good, naturally normal, early critical, a little bit critical, critical and very critical condition. The result shows that water catchment area condition is in an early critical condition around 2607,523 Ha (33,17 %), naturally normal condition around 1507,674 Ha (19,18 %), a little bit critical condition around 1452,931 Ha (18,48 %), good with 1157,04 Ha (14,72 %), critical with 1058,639 Ha (13,47 %) and very critical with 75,0387 Ha (0,95 %). The distribution of water catchment area conditions in West and East Flood Canal have an irreguler pattern. In northern area of watershed consists of begin to critical, naturally normal and good condition. Meanwhile in southern area of watershed consists of a little bit critical, critical and very critical condition.

Steganalysis based on reducing the differences of image statistical characteristics

NASA Astrophysics Data System (ADS)

Wang, Ran; Niu, Shaozhang; Ping, Xijian; Zhang, Tao

2018-04-01

Compared with the process of embedding, the image contents make a more significant impact on the differences of image statistical characteristics. This makes the image steganalysis to be a classification problem with bigger withinclass scatter distances and smaller between-class scatter distances. As a result, the steganalysis features will be inseparate caused by the differences of image statistical characteristics. In this paper, a new steganalysis framework which can reduce the differences of image statistical characteristics caused by various content and processing methods is proposed. The given images are segmented to several sub-images according to the texture complexity. Steganalysis features are separately extracted from each subset with the same or close texture complexity to build a classifier. The final steganalysis result is figured out through a weighted fusing process. The theoretical analysis and experimental results can demonstrate the validity of the framework.

Rotationally Invariant Image Representation for Viewing Direction Classification in Cryo-EM

PubMed Central

Zhao, Zhizhen; Singer, Amit

2014-01-01

We introduce a new rotationally invariant viewing angle classification method for identifying, among a large number of cryo-EM projection images, similar views without prior knowledge of the molecule. Our rotationally invariant features are based on the bispectrum. Each image is denoised and compressed using steerable principal component analysis (PCA) such that rotating an image is equivalent to phase shifting the expansion coefficients. Thus we are able to extend the theory of bispectrum of 1D periodic signals to 2D images. The randomized PCA algorithm is then used to efficiently reduce the dimensionality of the bispectrum coefficients, enabling fast computation of the similarity between any pair of images. The nearest neighbors provide an initial classification of similar viewing angles. In this way, rotational alignment is only performed for images with their nearest neighbors. The initial nearest neighbor classification and alignment are further improved by a new classification method called vector diffusion maps. Our pipeline for viewing angle classification and alignment is experimentally shown to be faster and more accurate than reference-free alignment with rotationally invariant K-means clustering, MSA/MRA 2D classification, and their modern approximations. PMID:24631969

Two fast approximate wavelet algorithms for image processing, classification, and recognition

NASA Astrophysics Data System (ADS)

Wickerhauser, Mladen V.

1994-07-01

We use large libraries of template waveforms with remarkable orthogonality properties to recast the relatively complex principal orthogonal decomposition (POD) into an optimization problem with a fast solution algorithm. Then it becomes practical to use POD to solve two related problems: recognizing or classifying images, and inverting a complicated map from a low-dimensional configuration space to a high-dimensional measurement space. In the case where the number N of pixels or measurements is more than 1000 or so, the classical O(N3) POD algorithms becomes very costly, but it can be replaced with an approximate best-basis method that has complexity O(N2logN). A variation of POD can also be used to compute an approximate Jacobian for the complicated map.

Fuzzy Classification of High Resolution Remote Sensing Scenes Using Visual Attention Features.

PubMed

Li, Linyi; Xu, Tingbao; Chen, Yun

2017-01-01

In recent years the spatial resolutions of remote sensing images have been improved greatly. However, a higher spatial resolution image does not always lead to a better result of automatic scene classification. Visual attention is an important characteristic of the human visual system, which can effectively help to classify remote sensing scenes. In this study, a novel visual attention feature extraction algorithm was proposed, which extracted visual attention features through a multiscale process. And a fuzzy classification method using visual attention features (FC-VAF) was developed to perform high resolution remote sensing scene classification. FC-VAF was evaluated by using remote sensing scenes from widely used high resolution remote sensing images, including IKONOS, QuickBird, and ZY-3 images. FC-VAF achieved more accurate classification results than the others according to the quantitative accuracy evaluation indices. We also discussed the role and impacts of different decomposition levels and different wavelets on the classification accuracy. FC-VAF improves the accuracy of high resolution scene classification and therefore advances the research of digital image analysis and the applications of high resolution remote sensing images.

Fuzzy Classification of High Resolution Remote Sensing Scenes Using Visual Attention Features

PubMed Central

Xu, Tingbao; Chen, Yun

2017-01-01

In recent years the spatial resolutions of remote sensing images have been improved greatly. However, a higher spatial resolution image does not always lead to a better result of automatic scene classification. Visual attention is an important characteristic of the human visual system, which can effectively help to classify remote sensing scenes. In this study, a novel visual attention feature extraction algorithm was proposed, which extracted visual attention features through a multiscale process. And a fuzzy classification method using visual attention features (FC-VAF) was developed to perform high resolution remote sensing scene classification. FC-VAF was evaluated by using remote sensing scenes from widely used high resolution remote sensing images, including IKONOS, QuickBird, and ZY-3 images. FC-VAF achieved more accurate classification results than the others according to the quantitative accuracy evaluation indices. We also discussed the role and impacts of different decomposition levels and different wavelets on the classification accuracy. FC-VAF improves the accuracy of high resolution scene classification and therefore advances the research of digital image analysis and the applications of high resolution remote sensing images. PMID:28761440

A Method of Spatial Mapping and Reclassification for High-Spatial-Resolution Remote Sensing Image Classification

PubMed Central

Wang, Guizhou; Liu, Jianbo; He, Guojin

2013-01-01

This paper presents a new classification method for high-spatial-resolution remote sensing images based on a strategic mechanism of spatial mapping and reclassification. The proposed method includes four steps. First, the multispectral image is classified by a traditional pixel-based classification method (support vector machine). Second, the panchromatic image is subdivided by watershed segmentation. Third, the pixel-based multispectral image classification result is mapped to the panchromatic segmentation result based on a spatial mapping mechanism and the area dominant principle. During the mapping process, an area proportion threshold is set, and the regional property is defined as unclassified if the maximum area proportion does not surpass the threshold. Finally, unclassified regions are reclassified based on spectral information using the minimum distance to mean algorithm. Experimental results show that the classification method for high-spatial-resolution remote sensing images based on the spatial mapping mechanism and reclassification strategy can make use of both panchromatic and multispectral information, integrate the pixel- and object-based classification methods, and improve classification accuracy. PMID:24453808

On the Performance Evaluation of 3D Reconstruction Techniques from a Sequence of Images

NASA Astrophysics Data System (ADS)

Eid, Ahmed; Farag, Aly

2005-12-01

The performance evaluation of 3D reconstruction techniques is not a simple problem to solve. This is not only due to the increased dimensionality of the problem but also due to the lack of standardized and widely accepted testing methodologies. This paper presents a unified framework for the performance evaluation of different 3D reconstruction techniques. This framework includes a general problem formalization, different measuring criteria, and a classification method as a first step in standardizing the evaluation process. Performance characterization of two standard 3D reconstruction techniques, stereo and space carving, is also presented. The evaluation is performed on the same data set using an image reprojection testing methodology to reduce the dimensionality of the evaluation domain. Also, different measuring strategies are presented and applied to the stereo and space carving techniques. These measuring strategies have shown consistent results in quantifying the performance of these techniques. Additional experiments are performed on the space carving technique to study the effect of the number of input images and the camera pose on its performance.

Drug related webpages classification using images and text information based on multi-kernel learning

NASA Astrophysics Data System (ADS)

Hu, Ruiguang; Xiao, Liping; Zheng, Wenjuan

2015-12-01

In this paper, multi-kernel learning(MKL) is used for drug-related webpages classification. First, body text and image-label text are extracted through HTML parsing, and valid images are chosen by the FOCARSS algorithm. Second, text based BOW model is used to generate text representation, and image-based BOW model is used to generate images representation. Last, text and images representation are fused with a few methods. Experimental results demonstrate that the classification accuracy of MKL is higher than those of all other fusion methods in decision level and feature level, and much higher than the accuracy of single-modal classification.

Brain-Computer Interface Based on Generation of Visual Images

PubMed Central

Bobrov, Pavel; Frolov, Alexander; Cantor, Charles; Fedulova, Irina; Bakhnyan, Mikhail; Zhavoronkov, Alexander

2011-01-01

This paper examines the task of recognizing EEG patterns that correspond to performing three mental tasks: relaxation and imagining of two types of pictures: faces and houses. The experiments were performed using two EEG headsets: BrainProducts ActiCap and Emotiv EPOC. The Emotiv headset becomes widely used in consumer BCI application allowing for conducting large-scale EEG experiments in the future. Since classification accuracy significantly exceeded the level of random classification during the first three days of the experiment with EPOC headset, a control experiment was performed on the fourth day using ActiCap. The control experiment has shown that utilization of high-quality research equipment can enhance classification accuracy (up to 68% in some subjects) and that the accuracy is independent of the presence of EEG artifacts related to blinking and eye movement. This study also shows that computationally-inexpensive Bayesian classifier based on covariance matrix analysis yields similar classification accuracy in this problem as a more sophisticated Multi-class Common Spatial Patterns (MCSP) classifier. PMID:21695206

Two-Stage Approach to Image Classification by Deep Neural Networks

NASA Astrophysics Data System (ADS)

Ososkov, Gennady; Goncharov, Pavel

2018-02-01

The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying. An autoassociative neural network is used as a standalone autoencoder for prior extraction of the most informative features of the input data for neural networks to be compared further as classifiers. The main efforts to deal with deep learning networks are spent for a quite painstaking work of optimizing the structures of those networks and their components, as activation functions, weights, as well as the procedures of minimizing their loss function to improve their performances and speed up their learning time. It is also shown that the deep autoencoders develop the remarkable ability for denoising images after being specially trained. Convolutional Neural Networks are also used to solve a quite actual problem of protein genetics on the example of the durum wheat classification. Results of our comparative study demonstrate the undoubted advantage of the deep networks, as well as the denoising power of the autoencoders. In our work we use both GPU and cloud services to speed up the calculations.

Incremental classification learning for anomaly detection in medical images

NASA Astrophysics Data System (ADS)

Giritharan, Balathasan; Yuan, Xiaohui; Liu, Jianguo

2009-02-01

Computer-aided diagnosis usually screens thousands of instances to find only a few positive cases that indicate probable presence of disease.The amount of patient data increases consistently all the time. In diagnosis of new instances, disagreement occurs between a CAD system and physicians, which suggests inaccurate classifiers. Intuitively, misclassified instances and the previously acquired data should be used to retrain the classifier. This, however, is very time consuming and, in some cases where dataset is too large, becomes infeasible. In addition, among the patient data, only a small percentile shows positive sign, which is known as imbalanced data.We present an incremental Support Vector Machines(SVM) as a solution for the class imbalance problem in classification of anomaly in medical images. The support vectors provide a concise representation of the distribution of the training data. Here we use bootstrapping to identify potential candidate support vectors for future iterations. Experiments were conducted using images from endoscopy videos, and the sensitivity and specificity were close to that of SVM trained using all samples available at a given incremental step with significantly improved efficiency in training the classifier.

Finding regional models of the Alzheimer disease by fusing information from neuropsychological tests and structural MR images

NASA Astrophysics Data System (ADS)

Giraldo, Diana L.; García-Arteaga, Juan D.; Romero, Eduardo

2016-03-01

Initial diagnosis of Alzheimer's disease (AD) is based on the patient's clinical history and a battery of neuropsy-chological tests. This work presents an automatic strategy that uses Structural Magnetic Resonance Imaging (MRI) to learn brain models for different stages of the disease using information from clinical assessments. Then, a comparison of the discriminant power of the models in different anatomical areas is made by using the brain region of the models as a reference frame for the classification problem, by using the projection into the AD model a Receiver Operating Characteristic (ROC) curve is constructed. Validation was performed using a leave- one-out scheme with 86 subjects (20 AD and 60 NC) from the Open Access Series of Imaging Studies (OASIS) database. The region with the best classification performance was the left amygdala where it is possible to achieve a sensibility and specificity of 85% at the same time. The regions with the best performance, in terms of the AUC, are in strong agreement with those described as important for the diagnosis of AD in clinical practice.

Joint classification and contour extraction of large 3D point clouds

NASA Astrophysics Data System (ADS)

Hackel, Timo; Wegner, Jan D.; Schindler, Konrad

2017-08-01

We present an effective and efficient method for point-wise semantic classification and extraction of object contours of large-scale 3D point clouds. What makes point cloud interpretation challenging is the sheer size of several millions of points per scan and the non-grid, sparse, and uneven distribution of points. Standard image processing tools like texture filters, for example, cannot handle such data efficiently, which calls for dedicated point cloud labeling methods. It turns out that one of the major drivers for efficient computation and handling of strong variations in point density, is a careful formulation of per-point neighborhoods at multiple scales. This allows, both, to define an expressive feature set and to extract topologically meaningful object contours. Semantic classification and contour extraction are interlaced problems. Point-wise semantic classification enables extracting a meaningful candidate set of contour points while contours help generating a rich feature representation that benefits point-wise classification. These methods are tailored to have fast run time and small memory footprint for processing large-scale, unstructured, and inhomogeneous point clouds, while still achieving high classification accuracy. We evaluate our methods on the semantic3d.net benchmark for terrestrial laser scans with >109 points.

The effect of lossy image compression on image classification

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1995-01-01

We have classified four different images, under various levels of JPEG compression, using the following classification algorithms: minimum-distance, maximum-likelihood, and neural network. The training site accuracy and percent difference from the original classification were tabulated for each image compression level, with maximum-likelihood showing the poorest results. In general, as compression ratio increased, the classification retained its overall appearance, but much of the pixel-to-pixel detail was eliminated. We also examined the effect of compression on spatial pattern detection using a neural network.

Automatic Gleason grading of H and E stained microscopic prostate images using deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Gummeson, Anna; Arvidsson, Ida; Ohlsson, Mattias; Overgaard, Niels C.; Krzyzanowska, Agnieszka; Heyden, Anders; Bjartell, Anders; Aström, Kalle

2017-03-01

Prostate cancer is the most diagnosed cancer in men. The diagnosis is confirmed by pathologists based on ocular inspection of prostate biopsies in order to classify them according to Gleason score. The main goal of this paper is to automate the classification using convolutional neural networks (CNNs). The introduction of CNNs has broadened the field of pattern recognition. It replaces the classical way of designing and extracting hand-made features used for classification with the substantially different strategy of letting the computer itself decide which features are of importance. For automated prostate cancer classification into the classes: Benign, Gleason grade 3, 4 and 5 we propose a CNN with small convolutional filters that has been trained from scratch using stochastic gradient descent with momentum. The input consists of microscopic images of haematoxylin and eosin stained tissue, the output is a coarse segmentation into regions of the four different classes. The dataset used consists of 213 images, each considered to be of one class only. Using four-fold cross-validation we obtained an error rate of 7.3%, which is significantly better than previous state of the art using the same dataset. Although the dataset was rather small, good results were obtained. From this we conclude that CNN is a promising method for this problem. Future work includes obtaining a larger dataset, which potentially could diminish the error margin.

Tissue classification for laparoscopic image understanding based on multispectral texture analysis

NASA Astrophysics Data System (ADS)

Zhang, Yan; Wirkert, Sebastian J.; Iszatt, Justin; Kenngott, Hannes; Wagner, Martin; Mayer, Benjamin; Stock, Christian; Clancy, Neil T.; Elson, Daniel S.; Maier-Hein, Lena

2016-03-01

Intra-operative tissue classification is one of the prerequisites for providing context-aware visualization in computer-assisted minimally invasive surgeries. As many anatomical structures are difficult to differentiate in conventional RGB medical images, we propose a classification method based on multispectral image patches. In a comprehensive ex vivo study we show (1) that multispectral imaging data is superior to RGB data for organ tissue classification when used in conjunction with widely applied feature descriptors and (2) that combining the tissue texture with the reflectance spectrum improves the classification performance. Multispectral tissue analysis could thus evolve as a key enabling technique in computer-assisted laparoscopy.

NutriNet: A Deep Learning Food and Drink Image Recognition System for Dietary Assessment

PubMed Central

Koroušić Seljak, Barbara

2017-01-01

Automatic food image recognition systems are alleviating the process of food-intake estimation and dietary assessment. However, due to the nature of food images, their recognition is a particularly challenging task, which is why traditional approaches in the field have achieved a low classification accuracy. Deep neural networks have outperformed such solutions, and we present a novel approach to the problem of food and drink image detection and recognition that uses a newly-defined deep convolutional neural network architecture, called NutriNet. This architecture was tuned on a recognition dataset containing 225,953 512 × 512 pixel images of 520 different food and drink items from a broad spectrum of food groups, on which we achieved a classification accuracy of 86.72%, along with an accuracy of 94.47% on a detection dataset containing 130,517 images. We also performed a real-world test on a dataset of self-acquired images, combined with images from Parkinson’s disease patients, all taken using a smartphone camera, achieving a top-five accuracy of 55%, which is an encouraging result for real-world images. Additionally, we tested NutriNet on the University of Milano-Bicocca 2016 (UNIMIB2016) food image dataset, on which we improved upon the provided baseline recognition result. An online training component was implemented to continually fine-tune the food and drink recognition model on new images. The model is being used in practice as part of a mobile app for the dietary assessment of Parkinson’s disease patients. PMID:28653995

Realtime automatic metal extraction of medical x-ray images for contrast improvement

NASA Astrophysics Data System (ADS)

Prangl, Martin; Hellwagner, Hermann; Spielvogel, Christian; Bischof, Horst; Szkaliczki, Tibor

2006-03-01

This paper focuses on an approach for real-time metal extraction of x-ray images taken from modern x-ray machines like C-arms. Such machines are used for vessel diagnostics, surgical interventions, as well as cardiology, neurology and orthopedic examinations. They are very fast in taking images from different angles. For this reason, manual adjustment of contrast is infeasible and automatic adjustment algorithms have been applied to try to select the optimal radiation dose for contrast adjustment. Problems occur when metallic objects, e.g., a prosthesis or a screw, are in the absorption area of interest. In this case, the automatic adjustment mostly fails because the dark, metallic objects lead the algorithm to overdose the x-ray tube. This outshining effect results in overexposed images and bad contrast. To overcome this limitation, metallic objects have to be detected and extracted from images that are taken as input for the adjustment algorithm. In this paper, we present a real-time solution for extracting metallic objects of x-ray images. We will explore the characteristic features of metallic objects in x-ray images and their distinction from bone fragments which form the basis to find a successful way for object segmentation and classification. Subsequently, we will present our edge based real-time approach for successful and fast automatic segmentation and classification of metallic objects. Finally, experimental results on the effectiveness and performance of our approach based on a vast amount of input image data sets will be presented.

Use of Binary Partition Tree and energy minimization for object-based classification of urban land cover

NASA Astrophysics Data System (ADS)

Li, Mengmeng; Bijker, Wietske; Stein, Alfred

2015-04-01

Two main challenges are faced when classifying urban land cover from very high resolution satellite images: obtaining an optimal image segmentation and distinguishing buildings from other man-made objects. For optimal segmentation, this work proposes a hierarchical representation of an image by means of a Binary Partition Tree (BPT) and an unsupervised evaluation of image segmentations by energy minimization. For building extraction, we apply fuzzy sets to create a fuzzy landscape of shadows which in turn involves a two-step procedure. The first step is a preliminarily image classification at a fine segmentation level to generate vegetation and shadow information. The second step models the directional relationship between building and shadow objects to extract building information at the optimal segmentation level. We conducted the experiments on two datasets of Pléiades images from Wuhan City, China. To demonstrate its performance, the proposed classification is compared at the optimal segmentation level with Maximum Likelihood Classification and Support Vector Machine classification. The results show that the proposed classification produced the highest overall accuracies and kappa coefficients, and the smallest over-classification and under-classification geometric errors. We conclude first that integrating BPT with energy minimization offers an effective means for image segmentation. Second, we conclude that the directional relationship between building and shadow objects represented by a fuzzy landscape is important for building extraction.

Pet fur color and texture classification

NASA Astrophysics Data System (ADS)

Yen, Jonathan; Mukherjee, Debarghar; Lim, SukHwan; Tretter, Daniel

2007-01-01

Object segmentation is important in image analysis for imaging tasks such as image rendering and image retrieval. Pet owners have been known to be quite vocal about how important it is to render their pets perfectly. We present here an algorithm for pet (mammal) fur color classification and an algorithm for pet (animal) fur texture classification. Per fur color classification can be applied as a necessary condition for identifying the regions in an image that may contain pets much like the skin tone classification for human flesh detection. As a result of the evolution, fur coloration of all mammals is caused by a natural organic pigment called Melanin and Melanin has only very limited color ranges. We have conducted a statistical analysis and concluded that mammal fur colors can be only in levels of gray or in two colors after the proper color quantization. This pet fur color classification algorithm has been applied for peteye detection. We also present here an algorithm for animal fur texture classification using the recently developed multi-resolution directional sub-band Contourlet transform. The experimental results are very promising as these transforms can identify regions of an image that may contain fur of mammals, scale of reptiles and feather of birds, etc. Combining the color and texture classification, one can have a set of strong classifiers for identifying possible animals in an image.

Five-class differential diagnostics of neurodegenerative diseases using random undersampling boosting.

PubMed

Tong, Tong; Ledig, Christian; Guerrero, Ricardo; Schuh, Andreas; Koikkalainen, Juha; Tolonen, Antti; Rhodius, Hanneke; Barkhof, Frederik; Tijms, Betty; Lemstra, Afina W; Soininen, Hilkka; Remes, Anne M; Waldemar, Gunhild; Hasselbalch, Steen; Mecocci, Patrizia; Baroni, Marta; Lötjönen, Jyrki; Flier, Wiesje van der; Rueckert, Daniel

2017-01-01

Differentiating between different types of neurodegenerative diseases is not only crucial in clinical practice when treatment decisions have to be made, but also has a significant potential for the enrichment of clinical trials. The purpose of this study is to develop a classification framework for distinguishing the four most common neurodegenerative diseases, including Alzheimer's disease, frontotemporal lobe degeneration, Dementia with Lewy bodies and vascular dementia, as well as patients with subjective memory complaints. Different biomarkers including features from images (volume features, region-wise grading features) and non-imaging features (CSF measures) were extracted for each subject. In clinical practice, the prevalence of different dementia types is imbalanced, posing challenges for learning an effective classification model. Therefore, we propose the use of the RUSBoost algorithm in order to train classifiers and to handle the class imbalance training problem. Furthermore, a multi-class feature selection method based on sparsity is integrated into the proposed framework to improve the classification performance. It also provides a way for investigating the importance of different features and regions. Using a dataset of 500 subjects, the proposed framework achieved a high accuracy of 75.2% with a balanced accuracy of 69.3% for the five-class classification using ten-fold cross validation, which is significantly better than the results using support vector machine or random forest, demonstrating the feasibility of the proposed framework to support clinical decision making.

In search of a consumer-focused food classification system. An experimental heuristic approach to differentiate degrees of quality.

PubMed

Torres-Ruiz, Francisco J; Marano-Marcolini, Carla; Lopez-Zafra, Esther

2018-06-01

The present paper focuses on the problems that arise in food classification systems (FCSs), especially when the food product type has different levels or grades of quality. Despite the principal function of these systems being to assist the consumer (to inform, clarify and facilitate choice and purchase), they frequently have the opposite effect. Thus, the main aim of the present research involves providing orientations for the design of effective food classification systems. To address this objective, considering the context of food product consumption (related to heuristic processing), we conducted an experimental study with 720 participants. We analysed the usefulness of heuristic elements by a factorial 2 (category length: short and long) × 3 (visual signs: colours, numbers and images) design in relation to recall and recognition activities. The results showed that the elements used to make the classification more effective for consumers vary depending on whether the user seeks to prioritize the recall or the recognition of product categories. Thus, long categories with images significantly improve recognition, and short categories with colours improve recall. A series of recommendations are provided that can help to enhance FCSs and to make them more intuitive and easier to understand for consumers. Implications with regard to theory and practice are discussed. Copyright © 2018 Elsevier Ltd. All rights reserved.

Exploring the impact of wavelet-based denoising in the classification of remote sensing hyperspectral images

NASA Astrophysics Data System (ADS)

Quesada-Barriuso, Pablo; Heras, Dora B.; Argüello, Francisco

2016-10-01

The classification of remote sensing hyperspectral images for land cover applications is a very intensive topic. In the case of supervised classification, Support Vector Machines (SVMs) play a dominant role. Recently, the Extreme Learning Machine algorithm (ELM) has been extensively used. The classification scheme previously published by the authors, and called WT-EMP, introduces spatial information in the classification process by means of an Extended Morphological Profile (EMP) that is created from features extracted by wavelets. In addition, the hyperspectral image is denoised in the 2-D spatial domain, also using wavelets and it is joined to the EMP via a stacked vector. In this paper, the scheme is improved achieving two goals. The first one is to reduce the classification time while preserving the accuracy of the classification by using ELM instead of SVM. The second one is to improve the accuracy results by performing not only a 2-D denoising for every spectral band, but also a previous additional 1-D spectral signature denoising applied to each pixel vector of the image. For each denoising the image is transformed by applying a 1-D or 2-D wavelet transform, and then a NeighShrink thresholding is applied. Improvements in terms of classification accuracy are obtained, especially for images with close regions in the classification reference map, because in these cases the accuracy of the classification in the edges between classes is more relevant.

A new tool for supervised classification of satellite images available on web servers: Google Maps as a case study

NASA Astrophysics Data System (ADS)

García-Flores, Agustín.; Paz-Gallardo, Abel; Plaza, Antonio; Li, Jun

2016-10-01

This paper describes a new web platform dedicated to the classification of satellite images called Hypergim. The current implementation of this platform enables users to perform classification of satellite images from any part of the world thanks to the worldwide maps provided by Google Maps. To perform this classification, Hypergim uses unsupervised algorithms like Isodata and K-means. Here, we present an extension of the original platform in which we adapt Hypergim in order to use supervised algorithms to improve the classification results. This involves a significant modification of the user interface, providing the user with a way to obtain samples of classes present in the images to use in the training phase of the classification process. Another main goal of this development is to improve the runtime of the image classification process. To achieve this goal, we use a parallel implementation of the Random Forest classification algorithm. This implementation is a modification of the well-known CURFIL software package. The use of this type of algorithms to perform image classification is widespread today thanks to its precision and ease of training. The actual implementation of Random Forest was developed using CUDA platform, which enables us to exploit the potential of several models of NVIDIA graphics processing units using them to execute general purpose computing tasks as image classification algorithms. As well as CUDA, we use other parallel libraries as Intel Boost, taking advantage of the multithreading capabilities of modern CPUs. To ensure the best possible results, the platform is deployed in a cluster of commodity graphics processing units (GPUs), so that multiple users can use the tool in a concurrent way. The experimental results indicate that this new algorithm widely outperform the previous unsupervised algorithms implemented in Hypergim, both in runtime as well as precision of the actual classification of the images.

Psychology Problem Classification for Children and Youth.

ERIC Educational Resources Information Center

Minnesota Systems Research, Inc., Washington, DC.

The development of Psychology Problem Classification is an early step in the direction of providing a uniform nomenclature for classifying the needs and problems of children and youth. There are many potential uses for a diagnostic classification and coding system. The two most important uses for the practitioner are problem identification and…

Diagnostic discrepancies in retinopathy of prematurity classification

PubMed Central

Campbell, J. Peter; Ryan, Michael C.; Lore, Emily; Tian, Peng; Ostmo, Susan; Jonas, Karyn; Chan, R.V. Paul; Chiang, Michael F.

2016-01-01

Objective To identify the most common areas for discrepancy in retinopathy of prematurity (ROP) classification between experts. Design Prospective cohort study. Subjects, Participants, and/or Controls 281 infants were identified as part of a multi-center, prospective, ROP cohort study from 7 participating centers. Each site had participating ophthalmologists who provided the clinical classification after routine examination using binocular indirect ophthalmoscopy (BIO), and obtained wide-angle retinal images, which were independently classified by two study experts. Methods Wide-angle retinal images (RetCam; Clarity Medical Systems, Pleasanton, CA) were obtained from study subjects, and two experts evaluated each image using a secure web-based module. Image-based classifications for zone, stage, plus disease, overall disease category (no ROP, mild ROP, Type II or pre-plus, and Type I) were compared between the two experts, and to the clinical classification obtained by BIO. Main Outcome Measures Inter-expert image-based agreement and image-based vs. ophthalmoscopic diagnostic agreement using absolute agreement and weighted kappa statistic. Results 1553 study eye examinations from 281 infants were included in the study. Experts disagreed on the stage classification in 620/1553 (40%) of comparisons, plus disease classification (including pre-plus) in 287/1553 (18%), zone in 117/1553 (8%), and overall ROP category in 618/1553 (40%). However, agreement for presence vs. absence of type 1 disease was >95%. There were no differences between image-based and clinical classification except for zone III disease. Conclusions The most common area of discrepancy in ROP classification is stage, although inter-expert agreement for clinically-significant disease such as presence vs. absence of type 1 and type 2 disease is high. There were no differences between image-based grading and the clinical exam in the ability to detect clinically-significant disease. This study provides additional evidence that image-based classification of ROP reliably detects clinically significant levels of ROP with high accuracy compared to the clinical exam. PMID:27238376

Content-based image retrieval from a database of fracture images

NASA Astrophysics Data System (ADS)

Müller, Henning; Do Hoang, Phuong Anh; Depeursinge, Adrien; Hoffmeyer, Pierre; Stern, Richard; Lovis, Christian; Geissbuhler, Antoine

2007-03-01

This article describes the use of a medical image retrieval system on a database of 16'000 fractures, selected from surgical routine over several years. Image retrieval has been a very active domain of research for several years. It was frequently proposed for the medical domain, but only few running systems were ever tested in clinical routine. For the planning of surgical interventions after fractures, x-ray images play an important role. The fractures are classified according to exact fracture location, plus whether and to which degree the fracture is damaging articulations to see how complicated a reparation will be. Several classification systems for fractures exist and the classification plus the experience of the surgeon lead in the end to the choice of surgical technique (screw, metal plate, ...). This choice is strongly influenced by the experience and knowledge of the surgeons with respect to a certain technique. Goal of this article is to describe a prototype that supplies similar cases to an example to help treatment planning and find the most appropriate technique for a surgical intervention. Our database contains over 16'000 fracture images before and after a surgical intervention. We use an image retrieval system (GNU Image Finding Tool, GIFT) to find cases/images similar to an example case currently under observation. Problems encountered are varying illumination of images as well as strong anatomic differences between patients. Regions of interest are usually small and the retrieval system needs to focus on this region. Results show that GIFT is capable of supplying similar cases, particularly when using relevance feedback, on such a large database. Usual image retrieval is based on a single image as search target but for this application we have to select images by case as similar cases need to be found and not images. A few false positive cases often remain in the results but they can be sorted out quickly by the surgeons. Image retrieval can well be used for the planning of operations by supplying similar cases. A variety of challenges has been identified and partly solved (varying luminosity, small region of interested, case-based instead of image-based). This article mainly presents a case study to identify potential benefits and problems. Several steps for improving the system have been identified as well and will be described at the end of the paper.

A unified material decomposition framework for quantitative dual- and triple-energy CT imaging.

PubMed

Zhao, Wei; Vernekohl, Don; Han, Fei; Han, Bin; Peng, Hao; Yang, Yong; Xing, Lei; Min, James K

2018-04-21

Many clinical applications depend critically on the accurate differentiation and classification of different types of materials in patient anatomy. This work introduces a unified framework for accurate nonlinear material decomposition and applies it, for the first time, in the concept of triple-energy CT (TECT) for enhanced material differentiation and classification as well as dual-energy CT (DECT). We express polychromatic projection into a linear combination of line integrals of material-selective images. The material decomposition is then turned into a problem of minimizing the least-squares difference between measured and estimated CT projections. The optimization problem is solved iteratively by updating the line integrals. The proposed technique is evaluated by using several numerical phantom measurements under different scanning protocols. The triple-energy data acquisition is implemented at the scales of micro-CT and clinical CT imaging with commercial "TwinBeam" dual-source DECT configuration and a fast kV switching DECT configuration. Material decomposition and quantitative comparison with a photon counting detector and with the presence of a bow-tie filter are also performed. The proposed method provides quantitative material- and energy-selective images examining realistic configurations for both DECT and TECT measurements. Compared to the polychromatic kV CT images, virtual monochromatic images show superior image quality. For the mouse phantom, quantitative measurements show that the differences between gadodiamide and iodine concentrations obtained using TECT and idealized photon counting CT (PCCT) are smaller than 8 and 1 mg/mL, respectively. TECT outperforms DECT for multicontrast CT imaging and is robust with respect to spectrum estimation. For the thorax phantom, the differences between the concentrations of the contrast map and the corresponding true reference values are smaller than 7 mg/mL for all of the realistic configurations. A unified framework for both DECT and TECT imaging has been established for the accurate extraction of material compositions using currently available commercial DECT configurations. The novel technique is promising to provide an urgently needed solution for several CT-based diagnostic and therapy applications, especially for the diagnosis of cardiovascular and abdominal diseases where multicontrast imaging is involved. © 2018 American Association of Physicists in Medicine.

Hair segmentation using adaptive threshold from edge and branch length measures.

PubMed

Lee, Ian; Du, Xian; Anthony, Brian

2017-10-01

Non-invasive imaging techniques allow the monitoring of skin structure and diagnosis of skin diseases in clinical applications. However, hair in skin images hampers the imaging and classification of the skin structure of interest. Although many hair segmentation methods have been proposed for digital hair removal, a major challenge in hair segmentation remains in detecting hairs that are thin, overlapping, of similar contrast or color to underlying skin, or overlaid on highly-textured skin structure. To solve the problem, we present an automatic hair segmentation method that uses edge density (ED) and mean branch length (MBL) to measure hair. First, hair is detected by the integration of top-hat transform and modified second-order Gaussian filter. Second, we employ a robust adaptive threshold of ED and MBL to generate a hair mask. Third, the hair mask is refined by k-NN classification of hair and skin pixels. The proposed algorithm was tested using two datasets of healthy skin images and lesion images respectively. These datasets were taken from different imaging platforms in various illumination levels and varying skin colors. We compared the hair detection and segmentation results from our algorithm and six other hair segmentation methods of state of the art. Our method exhibits high value of sensitivity: 75% and specificity: 95%, which indicates significantly higher accuracy and better balance between true positive and false positive detection than the other methods. Published by Elsevier Ltd.

Unsupervised learning of discriminative edge measures for vehicle matching between nonoverlapping cameras.

PubMed

Shan, Ying; Sawhney, Harpreet S; Kumar, Rakesh

2008-04-01

This paper proposes a novel unsupervised algorithm learning discriminative features in the context of matching road vehicles between two non-overlapping cameras. The matching problem is formulated as a same-different classification problem, which aims to compute the probability of vehicle images from two distinct cameras being from the same vehicle or different vehicle(s). We employ a novel measurement vector that consists of three independent edge-based measures and their associated robust measures computed from a pair of aligned vehicle edge maps. The weight of each measure is determined by an unsupervised learning algorithm that optimally separates the same-different classes in the combined measurement space. This is achieved with a weak classification algorithm that automatically collects representative samples from same-different classes, followed by a more discriminative classifier based on Fisher' s Linear Discriminants and Gibbs Sampling. The robustness of the match measures and the use of unsupervised discriminant analysis in the classification ensures that the proposed method performs consistently in the presence of missing/false features, temporally and spatially changing illumination conditions, and systematic misalignment caused by different camera configurations. Extensive experiments based on real data of over 200 vehicles at different times of day demonstrate promising results.

Neural net classification of x-ray pistachio nut data

NASA Astrophysics Data System (ADS)

Casasent, David P.; Sipe, Michael A.; Schatzki, Thomas F.; Keagy, Pamela M.; Le, Lan Chau

1996-12-01

Classification results for agricultural products are presented using a new neural network. This neural network inherently produces higher-order decision surfaces. It achieves this with fewer hidden layer neurons than other classifiers require. This gives better generalization. It uses new techniques to select the number of hidden layer neurons and adaptive algorithms that avoid other such ad hoc parameter selection problems; it allows selection of the best classifier parameters without the need to analyze the test set results. The agriculture case study considered is the inspection and classification of pistachio nuts using x- ray imagery. Present inspection techniques cannot provide good rejection of worm damaged nuts without rejecting too many good nuts. X-ray imagery has the potential to provide 100% inspection of such agricultural products in real time. Only preliminary results are presented, but these indicate the potential to reduce major defects to 2% of the crop with 1% of good nuts rejected. Future image processing techniques that should provide better features to improve performance and allow inspection of a larger variety of nuts are noted. These techniques and variations of them have uses in a number of other agricultural product inspection problems.

Remote Sensing Image Classification Applied to the First National Geographical Information Census of China

NASA Astrophysics Data System (ADS)

Yu, Xin; Wen, Zongyong; Zhu, Zhaorong; Xia, Qiang; Shun, Lan

2016-06-01

Image classification will still be a long way in the future, although it has gone almost half a century. In fact, researchers have gained many fruits in the image classification domain, but there is still a long distance between theory and practice. However, some new methods in the artificial intelligence domain will be absorbed into the image classification domain and draw on the strength of each to offset the weakness of the other, which will open up a new prospect. Usually, networks play the role of a high-level language, as is seen in Artificial Intelligence and statistics, because networks are used to build complex model from simple components. These years, Bayesian Networks, one of probabilistic networks, are a powerful data mining technique for handling uncertainty in complex domains. In this paper, we apply Tree Augmented Naive Bayesian Networks (TAN) to texture classification of High-resolution remote sensing images and put up a new method to construct the network topology structure in terms of training accuracy based on the training samples. Since 2013, China government has started the first national geographical information census project, which mainly interprets geographical information based on high-resolution remote sensing images. Therefore, this paper tries to apply Bayesian network to remote sensing image classification, in order to improve image interpretation in the first national geographical information census project. In the experiment, we choose some remote sensing images in Beijing. Experimental results demonstrate TAN outperform than Naive Bayesian Classifier (NBC) and Maximum Likelihood Classification Method (MLC) in the overall classification accuracy. In addition, the proposed method can reduce the workload of field workers and improve the work efficiency. Although it is time consuming, it will be an attractive and effective method for assisting office operation of image interpretation.

Maturity assessment of harumanis mango using thermal camera sensor

NASA Astrophysics Data System (ADS)

Sa'ad, F. S. A.; Shakaff, A. Y. Md.; Zakaria, A.; Abdullah, A. H.; Ibrahim, M. F.

2017-03-01

The perceived quality of fruits, such as mangoes, is greatly dependent on many parameters such as ripeness, shape, size, and is influenced by other factors such as harvesting time. Unfortunately, a manual fruit grading has several drawbacks such as subjectivity, tediousness and inconsistency. By automating the procedure, as well as developing new classification technique, it may solve these problems. This paper presents the novel work on the using Infrared as a Tool in Quality Monitoring of Harumanis Mangoes. The histogram of infrared image was used to distinguish and classify the level of ripeness of the fruits based on the colour spectrum by week. The approach proposed thermal data was able to achieve 90.5% correct classification.

SkyDiscovery: Humans and Machines Working Together

NASA Astrophysics Data System (ADS)

Donalek, Ciro; Fang, K.; Drake, A. J.; Djorgovski, S. G.; Graham, M. J.; Mahabal, A.; Williams, R.

2011-01-01

Synoptic sky surveys are now discovering tens to hundreds of transient events every clear night, and that data rate is expected to increase dramatically as we move towards the LSST. A key problem is classification of transients, which determines their scientific interest and possible follow-up. Some of the relevant information is contextual, and easily recognizable by humans looking at images, but it is very hard to encode in the data pipelines. Crowdsourcing (aka Citizen Science) provides one possible way to gather such information. SkyDiscovery.org is a website that allows experts and citizen science enthusiasts to work together and share information in a collaborative scientific discovery environment. Currently there are two projects running on the website. In the Event Classification project users help finding candidate transients through a series of questions related to the images shown. Event classification depends very much form the contextual information and humans are remarkably effective at recognizing noise in incomplete heterogeneous data and figuring out which contextual information is important. In the SNHunt project users are requested to look for new objects appearing on images of galaxies taken by the Catalina Real-time Transient Survey, in order to find all the supernovae occurring in nearby bright galaxies. Images are served alongside with other tools that can help the discovery. A multi level approach allows the complexity of the interface to be tailored to the expertise level of the user. An entry level user can just review images and validate events as being real, while a more advanced user would be able to interact with the data associated to an event. The data gathered will not be only analyzed and used directly for some specific science project, but also to train well-defined algorithms to be used in automating such data analysis in the future.

Multiscale Rotation-Invariant Convolutional Neural Networks for Lung Texture Classification.

PubMed

Wang, Qiangchang; Zheng, Yuanjie; Yang, Gongping; Jin, Weidong; Chen, Xinjian; Yin, Yilong

2018-01-01

We propose a new multiscale rotation-invariant convolutional neural network (MRCNN) model for classifying various lung tissue types on high-resolution computed tomography. MRCNN employs Gabor-local binary pattern that introduces a good property in image analysis-invariance to image scales and rotations. In addition, we offer an approach to deal with the problems caused by imbalanced number of samples between different classes in most of the existing works, accomplished by changing the overlapping size between the adjacent patches. Experimental results on a public interstitial lung disease database show a superior performance of the proposed method to state of the art.

Kernel Wiener filter and its application to pattern recognition.

PubMed

Yoshino, Hirokazu; Dong, Chen; Washizawa, Yoshikazu; Yamashita, Yukihiko

2010-11-01

The Wiener filter (WF) is widely used for inverse problems. From an observed signal, it provides the best estimated signal with respect to the squared error averaged over the original and the observed signals among linear operators. The kernel WF (KWF), extended directly from WF, has a problem that an additive noise has to be handled by samples. Since the computational complexity of kernel methods depends on the number of samples, a huge computational cost is necessary for the case. By using the first-order approximation of kernel functions, we realize KWF that can handle such a noise not by samples but as a random variable. We also propose the error estimation method for kernel filters by using the approximations. In order to show the advantages of the proposed methods, we conducted the experiments to denoise images and estimate errors. We also apply KWF to classification since KWF can provide an approximated result of the maximum a posteriori classifier that provides the best recognition accuracy. The noise term in the criterion can be used for the classification in the presence of noise or a new regularization to suppress changes in the input space, whereas the ordinary regularization for the kernel method suppresses changes in the feature space. In order to show the advantages of the proposed methods, we conducted experiments of binary and multiclass classifications and classification in the presence of noise.

Building confidence and credibility into CAD with belief decision trees

NASA Astrophysics Data System (ADS)

Affenit, Rachael N.; Barns, Erik R.; Furst, Jacob D.; Rasin, Alexander; Raicu, Daniela S.

2017-03-01

Creating classifiers for computer-aided diagnosis in the absence of ground truth is a challenging problem. Using experts' opinions as reference truth is difficult because the variability in the experts' interpretations introduces uncertainty in the labeled diagnostic data. This uncertainty translates into noise, which can significantly affect the performance of any classifier on test data. To address this problem, we propose a new label set weighting approach to combine the experts' interpretations and their variability, as well as a selective iterative classification (SIC) approach that is based on conformal prediction. Using the NIH/NCI Lung Image Database Consortium (LIDC) dataset in which four radiologists interpreted the lung nodule characteristics, including the degree of malignancy, we illustrate the benefits of the proposed approach. Our results show that the proposed 2-label-weighted approach significantly outperforms the accuracy of the original 5- label and 2-label-unweighted classification approaches by 39.9% and 7.6%, respectively. We also found that the weighted 2-label models produce higher skewness values by 1.05 and 0.61 for non-SIC and SIC respectively on root mean square error (RMSE) distributions. When each approach was combined with selective iterative classification, this further improved the accuracy of classification for the 2-weighted-label by 7.5% over the original, and improved the skewness of the 5-label and 2-unweighted-label by 0.22 and 0.44 respectively.

Classification image analysis: estimation and statistical inference for two-alternative forced-choice experiments

NASA Technical Reports Server (NTRS)

Abbey, Craig K.; Eckstein, Miguel P.

2002-01-01

We consider estimation and statistical hypothesis testing on classification images obtained from the two-alternative forced-choice experimental paradigm. We begin with a probabilistic model of task performance for simple forced-choice detection and discrimination tasks. Particular attention is paid to general linear filter models because these models lead to a direct interpretation of the classification image as an estimate of the filter weights. We then describe an estimation procedure for obtaining classification images from observer data. A number of statistical tests are presented for testing various hypotheses from classification images based on some more compact set of features derived from them. As an example of how the methods we describe can be used, we present a case study investigating detection of a Gaussian bump profile.

Postprocessing classification images

NASA Technical Reports Server (NTRS)

Kan, E. P.

1979-01-01

Program cleans up remote-sensing maps. It can be used with existing image-processing software. Remapped images closely resemble familiar resource information maps and can replace or supplement classification images not postprocessed by this program.

Cupping artifact correction and automated classification for high-resolution dedicated breast CT images.

PubMed

Yang, Xiaofeng; Wu, Shengyong; Sechopoulos, Ioannis; Fei, Baowei

2012-10-01

To develop and test an automated algorithm to classify the different tissues present in dedicated breast CT images. The original CT images are first corrected to overcome cupping artifacts, and then a multiscale bilateral filter is used to reduce noise while keeping edge information on the images. As skin and glandular tissues have similar CT values on breast CT images, morphologic processing is used to identify the skin mask based on its position information. A modified fuzzy C-means (FCM) classification method is then used to classify breast tissue as fat and glandular tissue. By combining the results of the skin mask with the FCM, the breast tissue is classified as skin, fat, and glandular tissue. To evaluate the authors' classification method, the authors use Dice overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on eight patient images. The correction method was able to correct the cupping artifacts and improve the quality of the breast CT images. For glandular tissue, the overlap ratios between the authors' automatic classification and manual segmentation were 91.6% ± 2.0%. A cupping artifact correction method and an automatic classification method were applied and evaluated for high-resolution dedicated breast CT images. Breast tissue classification can provide quantitative measurements regarding breast composition, density, and tissue distribution.

Cupping artifact correction and automated classification for high-resolution dedicated breast CT images

PubMed Central

Yang, Xiaofeng; Wu, Shengyong; Sechopoulos, Ioannis; Fei, Baowei

2012-01-01

Purpose: To develop and test an automated algorithm to classify the different tissues present in dedicated breast CT images. Methods: The original CT images are first corrected to overcome cupping artifacts, and then a multiscale bilateral filter is used to reduce noise while keeping edge information on the images. As skin and glandular tissues have similar CT values on breast CT images, morphologic processing is used to identify the skin mask based on its position information. A modified fuzzy C-means (FCM) classification method is then used to classify breast tissue as fat and glandular tissue. By combining the results of the skin mask with the FCM, the breast tissue is classified as skin, fat, and glandular tissue. To evaluate the authors’ classification method, the authors use Dice overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on eight patient images. Results: The correction method was able to correct the cupping artifacts and improve the quality of the breast CT images. For glandular tissue, the overlap ratios between the authors’ automatic classification and manual segmentation were 91.6% ± 2.0%. Conclusions: A cupping artifact correction method and an automatic classification method were applied and evaluated for high-resolution dedicated breast CT images. Breast tissue classification can provide quantitative measurements regarding breast composition, density, and tissue distribution. PMID:23039675

"Relative CIR": an image enhancement and visualization technique

USGS Publications Warehouse

Fleming, Michael D.

1993-01-01

Many techniques exist to spectrally and spatially enhance digital multispectral scanner data. One technique enhances an image while keeping the colors as they would appear in a color-infrared (CIR) image. This "relative CIR" technique generates an image that is both spectrally and spatially enhanced, while displaying a maximum range of colors. The technique enables an interpreter to visualize either spectral or land cover classes by their relative CIR characteristics. A relative CIR image is generated by developed spectral statistics for each class in the classifications and then, using a nonparametric approach for spectral enhancement, the means of the classes for each band are ranked. A 3 by 3 pixel smoothing filter is applied to the classification for spatial enhancement and the classes are mapped to the representative rank for each band. Practical applications of the technique include displaying an image classification product as a CIR image that was not derived directly from a spectral image, visualizing how a land cover classification would look as a CIR image, and displaying a spectral classification or intermediate product that will be used to label spectral classes.

Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries.

PubMed

Noor, Siti Salwa Md; Michael, Kaleena; Marshall, Stephen; Ren, Jinchang

2017-11-16

In our preliminary study, the reflectance signatures obtained from hyperspectral imaging (HSI) of normal and abnormal corneal epithelium tissues of porcine show similar morphology with subtle differences. Here we present image enhancement algorithms that can be used to improve the interpretability of data into clinically relevant information to facilitate diagnostics. A total of 25 corneal epithelium images without the application of eye staining were used. Three image feature extraction approaches were applied for image classification: (i) image feature classification from histogram using a support vector machine with a Gaussian radial basis function (SVM-GRBF); (ii) physical image feature classification using deep-learning Convolutional Neural Networks (CNNs) only; and (iii) the combined classification of CNNs and SVM-Linear. The performance results indicate that our chosen image features from the histogram and length-scale parameter were able to classify with up to 100% accuracy; particularly, at CNNs and CNNs-SVM, by employing 80% of the data sample for training and 20% for testing. Thus, in the assessment of corneal epithelium injuries, HSI has high potential as a method that could surpass current technologies regarding speed, objectivity, and reliability.

Training sample selection based on self-training for liver cirrhosis classification using ultrasound images

NASA Astrophysics Data System (ADS)

Fujita, Yusuke; Mitani, Yoshihiro; Hamamoto, Yoshihiko; Segawa, Makoto; Terai, Shuji; Sakaida, Isao

2017-03-01

Ultrasound imaging is a popular and non-invasive tool used in the diagnoses of liver disease. Cirrhosis is a chronic liver disease and it can advance to liver cancer. Early detection and appropriate treatment are crucial to prevent liver cancer. However, ultrasound image analysis is very challenging, because of the low signal-to-noise ratio of ultrasound images. To achieve the higher classification performance, selection of training regions of interest (ROIs) is very important that effect to classification accuracy. The purpose of our study is cirrhosis detection with high accuracy using liver ultrasound images. In our previous works, training ROI selection by MILBoost and multiple-ROI classification based on the product rule had been proposed, to achieve high classification performance. In this article, we propose self-training method to select training ROIs effectively. Evaluation experiments were performed to evaluate effect of self-training, using manually selected ROIs and also automatically selected ROIs. Experimental results show that self-training for manually selected ROIs achieved higher classification performance than other approaches, including our conventional methods. The manually ROI definition and sample selection are important to improve classification accuracy in cirrhosis detection using ultrasound images.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

NASA Astrophysics Data System (ADS)

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-12-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification.

PubMed

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-12-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value.

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

PubMed Central

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-01-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value. PMID:27905520

Image search engine with selective filtering and feature-element-based classification

NASA Astrophysics Data System (ADS)

Li, Qing; Zhang, Yujin; Dai, Shengyang

2001-12-01

With the growth of Internet and storage capability in recent years, image has become a widespread information format in World Wide Web. However, it has become increasingly harder to search for images of interest, and effective image search engine for the WWW needs to be developed. We propose in this paper a selective filtering process and a novel approach for image classification based on feature element in the image search engine we developed for the WWW. First a selective filtering process is embedded in a general web crawler to filter out the meaningless images with GIF format. Two parameters that can be obtained easily are used in the filtering process. Our classification approach first extract feature elements from images instead of feature vectors. Compared with feature vectors, feature elements can better capture visual meanings of the image according to subjective perception of human beings. Different from traditional image classification method, our classification approach based on feature element doesn't calculate the distance between two vectors in the feature space, while trying to find associations between feature element and class attribute of the image. Experiments are presented to show the efficiency of the proposed approach.

Markerless gating for lung cancer radiotherapy based on machine learning techniques

NASA Astrophysics Data System (ADS)

Lin, Tong; Li, Ruijiang; Tang, Xiaoli; Dy, Jennifer G.; Jiang, Steve B.

2009-03-01

In lung cancer radiotherapy, radiation to a mobile target can be delivered by respiratory gating, for which we need to know whether the target is inside or outside a predefined gating window at any time point during the treatment. This can be achieved by tracking one or more fiducial markers implanted inside or near the target, either fluoroscopically or electromagnetically. However, the clinical implementation of marker tracking is limited for lung cancer radiotherapy mainly due to the risk of pneumothorax. Therefore, gating without implanted fiducial markers is a promising clinical direction. We have developed several template-matching methods for fluoroscopic marker-less gating. Recently, we have modeled the gating problem as a binary pattern classification problem, in which principal component analysis (PCA) and support vector machine (SVM) are combined to perform the classification task. Following the same framework, we investigated different combinations of dimensionality reduction techniques (PCA and four nonlinear manifold learning methods) and two machine learning classification methods (artificial neural networks—ANN and SVM). Performance was evaluated on ten fluoroscopic image sequences of nine lung cancer patients. We found that among all combinations of dimensionality reduction techniques and classification methods, PCA combined with either ANN or SVM achieved a better performance than the other nonlinear manifold learning methods. ANN when combined with PCA achieves a better performance than SVM in terms of classification accuracy and recall rate, although the target coverage is similar for the two classification methods. Furthermore, the running time for both ANN and SVM with PCA is within tolerance for real-time applications. Overall, ANN combined with PCA is a better candidate than other combinations we investigated in this work for real-time gated radiotherapy.

Social Work Problem Classification for Children and Youth.

ERIC Educational Resources Information Center

Minnesota Systems Research, Inc., Washington, DC.

The development of the Social Work Problem Classification is an early step in the provision of a uniform nomenclature for classifying the needs and problems of children and youth. There are many potential uses for a diagnostic classification and coding system. The two most important for the practitioner are: (1) problem identification and…

Toward semantic-based retrieval of visual information: a model-based approach

NASA Astrophysics Data System (ADS)

Park, Youngchoon; Golshani, Forouzan; Panchanathan, Sethuraman

2002-07-01

This paper center around the problem of automated visual content classification. To enable classification based image or visual object retrieval, we propose a new image representation scheme called visual context descriptor (VCD) that is a multidimensional vector in which each element represents the frequency of a unique visual property of an image or a region. VCD utilizes the predetermined quality dimensions (i.e., types of features and quantization level) and semantic model templates mined in priori. Not only observed visual cues, but also contextually relevant visual features are proportionally incorporated in VCD. Contextual relevance of a visual cue to a semantic class is determined by using correlation analysis of ground truth samples. Such co-occurrence analysis of visual cues requires transformation of a real-valued visual feature vector (e.g., color histogram, Gabor texture, etc.,) into a discrete event (e.g., terms in text). Good-feature to track, rule of thirds, iterative k-means clustering and TSVQ are involved in transformation of feature vectors into unified symbolic representations called visual terms. Similarity-based visual cue frequency estimation is also proposed and used for ensuring the correctness of model learning and matching since sparseness of sample data causes the unstable results of frequency estimation of visual cues. The proposed method naturally allows integration of heterogeneous visual or temporal or spatial cues in a single classification or matching framework, and can be easily integrated into a semantic knowledge base such as thesaurus, and ontology. Robust semantic visual model template creation and object based image retrieval are demonstrated based on the proposed content description scheme.

Radio Galaxy Zoo: compact and extended radio source classification with deep learning

NASA Astrophysics Data System (ADS)

Lukic, V.; Brüggen, M.; Banfield, J. K.; Wong, O. I.; Rudnick, L.; Norris, R. P.; Simmons, B.

2018-05-01

Machine learning techniques have been increasingly useful in astronomical applications over the last few years, for example in the morphological classification of galaxies. Convolutional neural networks have proven to be highly effective in classifying objects in image data. In the context of radio-interferometric imaging in astronomy, we looked for ways to identify multiple components of individual sources. To this effect, we design a convolutional neural network to differentiate between different morphology classes using sources from the Radio Galaxy Zoo (RGZ) citizen science project. In this first step, we focus on exploring the factors that affect the performance of such neural networks, such as the amount of training data, number and nature of layers, and the hyperparameters. We begin with a simple experiment in which we only differentiate between two extreme morphologies, using compact and multiple-component extended sources. We found that a three-convolutional layer architecture yielded very good results, achieving a classification accuracy of 97.4 per cent on a test data set. The same architecture was then tested on a four-class problem where we let the network classify sources into compact and three classes of extended sources, achieving a test accuracy of 93.5 per cent. The best-performing convolutional neural network set-up has been verified against RGZ Data Release 1 where a final test accuracy of 94.8 per cent was obtained, using both original and augmented images. The use of sigma clipping does not offer a significant benefit overall, except in cases with a small number of training images.

Use of a remote computer terminal during field checking of Landsat digital maps

USGS Publications Warehouse

Robinove, Charles J.; Hutchinson, C.F.

1978-01-01

Field checking of small-scale land classification maps made digitally from Landsat data is facilitated by use of a remote portable teletypewriter terminal linked by teleplume to the IDIMS (Interactive Digital Image Manipulation System) at the EDC (EROS Data Center), Sioux Falls, S. Dak. When field checking of maps 20 miles northeast of Baker, Calif., during the day showed that changes in classification were needed, the terminal was used at night to combine image statistical files, remap portions of images, and produce new alphanumeric maps for field checking during the next day. The alphanumeric maps can be used without serious difficulty in location in the field even though the scale is distorted, and statistical files created during the field check can be used for full image classification and map output at the EDC. This process makes field checking faster than normal, provides interaction with the statistical data while in the field, and reduces to a minimum the number of trips needed to work interactively with the IDIMS at the EDC, thus saving significant amounts of time and money. The only significant problem is using telephone lines which at times create spurious characters in the printout or prevent the line feed (paper advance) signal from reaching the terminal, thus overprinting lines which should be sequential. We recommend that maps for field checking be made with more spectral classes than are expected because in the field it is much easier to group classes than to reclassify or separate classes when only the remote terminal is available for display.

Evaluation of image deblurring methods via a classification metric

NASA Astrophysics Data System (ADS)

Perrone, Daniele; Humphreys, David; Lamb, Robert A.; Favaro, Paolo

2012-09-01

The performance of single image deblurring algorithms is typically evaluated via a certain discrepancy measure between the reconstructed image and the ideal sharp image. The choice of metric, however, has been a source of debate and has also led to alternative metrics based on human visual perception. While fixed metrics may fail to capture some small but visible artifacts, perception-based metrics may favor reconstructions with artifacts that are visually pleasant. To overcome these limitations, we propose to assess the quality of reconstructed images via a task-driven metric. In this paper we consider object classification as the task and therefore use the rate of classification as the metric to measure deblurring performance. In our evaluation we use data with different types of blur in two cases: Optical Character Recognition (OCR), where the goal is to recognise characters in a black and white image, and object classification with no restrictions on pose, illumination and orientation. Finally, we show how off-the-shelf classification algorithms benefit from working with deblurred images.

Recognition and characterization of networks of water bodies in the Arctic ice-wedge polygonal tundra using high-resolution satellite imagery

NASA Astrophysics Data System (ADS)

Skurikhin, A. N.; Gangodagamage, C.; Rowland, J. C.; Wilson, C. J.

2013-12-01

Arctic lowland landscapes underlain by permafrost are often characterized by polygon-like patterns such as ice-wedge polygons outlined by networks of ice wedges and complemented with polygon rims, troughs, shallow ponds and thermokarst lakes. Polygonal patterns and corresponding features are relatively easy to recognize in high spatial resolution satellite imagery by a human, but their automated recognition is challenging due to the variability in their spectral appearance, the irregularity of individual trough spacing and orientation within the patterns, and a lack of unique spectral response attributable to troughs with widths commonly between 1 m and 2 m. Accurate identification of fine scale elements of ice-wedge polygonal tundra is important as their imprecise recognition may bias estimates of water, heat and carbon fluxes in large-scale climate models. Our focus is on the problem of identification of Arctic polygonal tundra fine-scale landscape elements (as small as 1 m - 2 m width). The challenge of the considered problem is that while large water bodies (e.g. lakes and rivers) can be recognized based on spectral response, reliable recognition of troughs is more difficult. Troughs do not have unique spectral signature, their appearance is noisy (edges are not strong), their width is small, and they often form connected networks with ponds and lakes, and thus they have overlapping spectral response with other water bodies and surrounding non-water bodies. We present a semi-automated approach to identify and classify Arctic polygonal tundra landscape components across the range of spatial scales, such as troughs, ponds, river- and lake-like objects, using high spatial resolution satellite imagery. The novelty of the approach lies in: (1) the combined use of segmentation and shape-based classification to identify a broad range of water bodies, including troughs, and (2) the use of high-resolution WorldView-2 satellite imagery (with resolution of 0.6 m) for this identification. The approach starts by segmenting water bodies from an image, which are then categorized using shape-based classification. Segmentation uses combination of pan sharpened multispectral bands and is based on the active contours without edges technique. The segmentation is robust to noise and can detect objects with weak boundaries that is important for extraction of troughs. We then categorize the segmented regions via shape based classification. Because segmentation accuracy is the main factor impacting the quality of the shape-based classification, for segmentation accuracy assessment we created reference image using WorldView-2 satellite image of ice-wedge polygonal tundra. Reference image contained manually labelled image regions which cover components of drainage networks, such as troughs, ponds, rivers and lakes. The evaluation has shown that the approach provides a good accuracy of segmentation and reasonable classification results. The overall accuracy of the segmentation is approximately 95%, the segmentation user's and producer's accuracies are approximately 92% and 97% respectively.

Enhancing and Archiving the APS Catalog of the POSS I

NASA Technical Reports Server (NTRS)

Humphreys, Roberta M.

2003-01-01

We have worked on two different projects: 1) Archiving the APS Catalog of the POSS I for distribution to NASA's NED at IPAC, SIMBAD in France, and individual astronomers and 2) The automated morphological classification of galaxies. We have completed archiving the Catalog into easily readable binary files. The database together with the software to read it has been distributed on DVD's to the national and international data centers and to individual astronomers. The archived Catalog contains more than 89 million objects in 632 fields in the first epoch Palomar Observatory Sky Survey. Additional image parameters not available in the original on-line version are also included in the archived version. The archived Catalog is also available and can be queried at the APS web site (URL: http://aps.umn.edu) which has been improved with a much faster and more efficient querying system. The Catalog can be downloaded as binary datafiles with the source code for reading it. It is also being integrated into the SkyQuery system which includes the Sloan Digital Sky Survey, 2MASS, and the FIRST radio sky survey. We experimented with different classification algorithms to automate the morphological classification of galaxies. This is an especially difficult problem because there are not only a large number of attributes or parameters and measurement uncertainties, but also the added complication of human disagreement about the adopted types. To solve this problem we used 837 galaxy images from nine POSS I fields at the North Galactic Pole classified by two independent astronomers for which they agree on the morphological types. The initial goal was to separate the galaxies into the three broad classes relevant to issues of large scale structure and galaxy formation and evolution: early (ellipticals and lenticulars), spirals, and late (irregulars) with an accuracy or success rate that rivals the best astronomer classifiers. We also needed to identify a set of parameters derived from the digitized images that separate the galaxies by type. The human eye can easily recognize complicated patterns in images such as spiral arms which can be spotty, blotchy affairs that are difficult for automated techniques. A galaxy image can potentially be described by hundreds of parameters, all of which may have some relation to the morphological type. In the set of initial experiments we used 624 such parameters, in two colors, blue and red. These parameters include the surface brightness and color measured at different radii, ratios of these parameters at different radii, concentration indices, Fourier transforms and wavelet decomposition coefficients. We experimented with three different classes of classification algorithms; decision trees, k-nearest neighbors, and support vector machines (SVM). A range of experiments were conducted and we eventually narrowed the parameters to 23 selected parameters. SVM consistently outperformed the other algorithms with both sets of features. By combining the results from the different algorithms in a weighted scheme we achieved an overall classification success of 86%.

Semantic classification of business images

NASA Astrophysics Data System (ADS)

Erol, Berna; Hull, Jonathan J.

2006-01-01

Digital cameras are becoming increasingly common for capturing information in business settings. In this paper, we describe a novel method for classifying images into the following semantic classes: document, whiteboard, business card, slide, and regular images. Our method is based on combining low-level image features, such as text color, layout, and handwriting features with high-level OCR output analysis. Several Support Vector Machine Classifiers are combined for multi-class classification of input images. The system yields 95% accuracy in classification.

Development of a classification method for a crack on a pavement surface images using machine learning

NASA Astrophysics Data System (ADS)

Hizukuri, Akiyoshi; Nagata, Takeshi

2017-03-01

The purpose of this study is to develop a classification method for a crack on a pavement surface image using machine learning to reduce a maintenance fee. Our database consists of 3500 pavement surface images. This includes 800 crack and 2700 normal pavement surface images. The pavement surface images first are decomposed into several sub-images using a discrete wavelet transform (DWT) decomposition. We then calculate the wavelet sub-band histogram from each several sub-images at each level. The support vector machine (SVM) with computed wavelet sub-band histogram is employed for distinguishing between a crack and normal pavement surface images. The accuracies of the proposed classification method are 85.3% for crack and 84.4% for normal pavement images. The proposed classification method achieved high performance. Therefore, the proposed method would be useful in maintenance inspection.

A Classification of Remote Sensing Image Based on Improved Compound Kernels of Svm

NASA Astrophysics Data System (ADS)

Zhao, Jianing; Gao, Wanlin; Liu, Zili; Mou, Guifen; Lu, Lin; Yu, Lina

The accuracy of RS classification based on SVM which is developed from statistical learning theory is high under small number of train samples, which results in satisfaction of classification on RS using SVM methods. The traditional RS classification method combines visual interpretation with computer classification. The accuracy of the RS classification, however, is improved a lot based on SVM method, because it saves much labor and time which is used to interpret images and collect training samples. Kernel functions play an important part in the SVM algorithm. It uses improved compound kernel function and therefore has a higher accuracy of classification on RS images. Moreover, compound kernel improves the generalization and learning ability of the kernel.

Improved Hierarchical Optimization-Based Classification of Hyperspectral Images Using Shape Analysis

NASA Technical Reports Server (NTRS)

Tarabalka, Yuliya; Tilton, James C.

2012-01-01

A new spectral-spatial method for classification of hyperspectral images is proposed. The HSegClas method is based on the integration of probabilistic classification and shape analysis within the hierarchical step-wise optimization algorithm. First, probabilistic support vector machines classification is applied. Then, at each iteration two neighboring regions with the smallest Dissimilarity Criterion (DC) are merged, and classification probabilities are recomputed. The important contribution of this work consists in estimating a DC between regions as a function of statistical, classification and geometrical (area and rectangularity) features. Experimental results are presented on a 102-band ROSIS image of the Center of Pavia, Italy. The developed approach yields more accurate classification results when compared to previously proposed methods.

A Method of Face Detection with Bayesian Probability

NASA Astrophysics Data System (ADS)

Sarker, Goutam

2010-10-01

The objective of face detection is to identify all images which contain a face, irrespective of its orientation, illumination conditions etc. This is a hard problem, because the faces are highly variable in size, shape lighting conditions etc. Many methods have been designed and developed to detect faces in a single image. The present paper is based on one `Appearance Based Method' which relies on learning the facial and non facial features from image examples. This in its turn is based on statistical analysis of examples and counter examples of facial images and employs Bayesian Conditional Classification Rule to detect the probability of belongingness of a face (or non-face) within an image frame. The detection rate of the present system is very high and thereby the number of false positive and false negative detection is substantially low.

A multiple-point spatially weighted k-NN method for object-based classification

NASA Astrophysics Data System (ADS)

Tang, Yunwei; Jing, Linhai; Li, Hui; Atkinson, Peter M.

2016-10-01

Object-based classification, commonly referred to as object-based image analysis (OBIA), is now commonly regarded as able to produce more appealing classification maps, often of greater accuracy, than pixel-based classification and its application is now widespread. Therefore, improvement of OBIA using spatial techniques is of great interest. In this paper, multiple-point statistics (MPS) is proposed for object-based classification enhancement in the form of a new multiple-point k-nearest neighbour (k-NN) classification method (MPk-NN). The proposed method first utilises a training image derived from a pre-classified map to characterise the spatial correlation between multiple points of land cover classes. The MPS borrows spatial structures from other parts of the training image, and then incorporates this spatial information, in the form of multiple-point probabilities, into the k-NN classifier. Two satellite sensor images with a fine spatial resolution were selected to evaluate the new method. One is an IKONOS image of the Beijing urban area and the other is a WorldView-2 image of the Wolong mountainous area, in China. The images were object-based classified using the MPk-NN method and several alternatives, including the k-NN, the geostatistically weighted k-NN, the Bayesian method, the decision tree classifier (DTC), and the support vector machine classifier (SVM). It was demonstrated that the new spatial weighting based on MPS can achieve greater classification accuracy relative to the alternatives and it is, thus, recommended as appropriate for object-based classification.

A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features

NASA Astrophysics Data System (ADS)

Srinivasan, Yeshwanth; Hernes, Dana; Tulpule, Bhakti; Yang, Shuyu; Guo, Jiangling; Mitra, Sunanda; Yagneswaran, Sriraja; Nutter, Brian; Jeronimo, Jose; Phillips, Benny; Long, Rodney; Ferris, Daron

2005-04-01

Automated segmentation and classification of diagnostic markers in medical imagery are challenging tasks. Numerous algorithms for segmentation and classification based on statistical approaches of varying complexity are found in the literature. However, the design of an efficient and automated algorithm for precise classification of desired diagnostic markers is extremely image-specific. The National Library of Medicine (NLM), in collaboration with the National Cancer Institute (NCI), is creating an archive of 60,000 digitized color images of the uterine cervix. NLM is developing tools for the analysis and dissemination of these images over the Web for the study of visual features correlated with precancerous neoplasia and cancer. To enable indexing of images of the cervix, it is essential to develop algorithms for the segmentation of regions of interest, such as acetowhitened regions, and automatic identification and classification of regions exhibiting mosaicism and punctation. Success of such algorithms depends, primarily, on the selection of relevant features representing the region of interest. We present color and geometric features based statistical classification and segmentation algorithms yielding excellent identification of the regions of interest. The distinct classification of the mosaic regions from the non-mosaic ones has been obtained by clustering multiple geometric and color features of the segmented sections using various morphological and statistical approaches. Such automated classification methodologies will facilitate content-based image retrieval from the digital archive of uterine cervix and have the potential of developing an image based screening tool for cervical cancer.

Histological Image Feature Mining Reveals Emergent Diagnostic Properties for Renal Cancer

PubMed Central

Kothari, Sonal; Phan, John H.; Young, Andrew N.; Wang, May D.

2016-01-01

Computer-aided histological image classification systems are important for making objective and timely cancer diagnostic decisions. These systems use combinations of image features that quantify a variety of image properties. Because researchers tend to validate their diagnostic systems on specific cancer endpoints, it is difficult to predict which image features will perform well given a new cancer endpoint. In this paper, we define a comprehensive set of common image features (consisting of 12 distinct feature subsets) that quantify a variety of image properties. We use a data-mining approach to determine which feature subsets and image properties emerge as part of an “optimal” diagnostic model when applied to specific cancer endpoints. Our goal is to assess the performance of such comprehensive image feature sets for application to a wide variety of diagnostic problems. We perform this study on 12 endpoints including 6 renal tumor subtype endpoints and 6 renal cancer grade endpoints. Keywords-histology, image mining, computer-aided diagnosis PMID:28163980

A Comparative Study of Landsat TM and SPOT HRG Images for Vegetation Classification in the Brazilian Amazon.

PubMed

Lu, Dengsheng; Batistella, Mateus; de Miranda, Evaristo E; Moran, Emilio

2008-01-01

Complex forest structure and abundant tree species in the moist tropical regions often cause difficulties in classifying vegetation classes with remotely sensed data. This paper explores improvement in vegetation classification accuracies through a comparative study of different image combinations based on the integration of Landsat Thematic Mapper (TM) and SPOT High Resolution Geometric (HRG) instrument data, as well as the combination of spectral signatures and textures. A maximum likelihood classifier was used to classify the different image combinations into thematic maps. This research indicated that data fusion based on HRG multispectral and panchromatic data slightly improved vegetation classification accuracies: a 3.1 to 4.6 percent increase in the kappa coefficient compared with the classification results based on original HRG or TM multispectral images. A combination of HRG spectral signatures and two textural images improved the kappa coefficient by 6.3 percent compared with pure HRG multispectral images. The textural images based on entropy or second-moment texture measures with a window size of 9 pixels × 9 pixels played an important role in improving vegetation classification accuracy. Overall, optical remote-sensing data are still insufficient for accurate vegetation classifications in the Amazon basin.

A Comparative Study of Landsat TM and SPOT HRG Images for Vegetation Classification in the Brazilian Amazon

PubMed Central

Lu, Dengsheng; Batistella, Mateus; de Miranda, Evaristo E.; Moran, Emilio

2009-01-01

Complex forest structure and abundant tree species in the moist tropical regions often cause difficulties in classifying vegetation classes with remotely sensed data. This paper explores improvement in vegetation classification accuracies through a comparative study of different image combinations based on the integration of Landsat Thematic Mapper (TM) and SPOT High Resolution Geometric (HRG) instrument data, as well as the combination of spectral signatures and textures. A maximum likelihood classifier was used to classify the different image combinations into thematic maps. This research indicated that data fusion based on HRG multispectral and panchromatic data slightly improved vegetation classification accuracies: a 3.1 to 4.6 percent increase in the kappa coefficient compared with the classification results based on original HRG or TM multispectral images. A combination of HRG spectral signatures and two textural images improved the kappa coefficient by 6.3 percent compared with pure HRG multispectral images. The textural images based on entropy or second-moment texture measures with a window size of 9 pixels × 9 pixels played an important role in improving vegetation classification accuracy. Overall, optical remote-sensing data are still insufficient for accurate vegetation classifications in the Amazon basin. PMID:19789716

Roi Detection and Vessel Segmentation in Retinal Image

NASA Astrophysics Data System (ADS)

Sabaz, F.; Atila, U.

2017-11-01

Diabetes disrupts work by affecting the structure of the eye and afterwards leads to loss of vision. Depending on the stage of disease that called diabetic retinopathy, there are sudden loss of vision and blurred vision problems. Automated detection of vessels in retinal images is a useful study to diagnose eye diseases, disease classification and other clinical trials. The shape and structure of the vessels give information about the severity of the disease and the stage of the disease. Automatic and fast detection of vessels allows for a quick diagnosis of the disease and the treatment process to start shortly. ROI detection and vessel extraction methods for retinal image are mentioned in this study. It is shown that the Frangi filter used in image processing can be successfully used in detection and extraction of vessels.

A fast image retrieval method based on SVM and imbalanced samples in filtering multimedia message spam

NASA Astrophysics Data System (ADS)

Chen, Zhang; Peng, Zhenming; Peng, Lingbing; Liao, Dongyi; He, Xin

2011-11-01

With the swift and violent development of the Multimedia Messaging Service (MMS), it becomes an urgent task to filter the Multimedia Message (MM) spam effectively in real-time. For the fact that most MMs contain images or videos, a method based on retrieving images is given in this paper for filtering MM spam. The detection method used in this paper is a combination of skin-color detection, texture detection, and face detection, and the classifier for this imbalanced problem is a very fast multi-classification combining Support vector machine (SVM) with unilateral binary decision tree. The experiments on 3 test sets show that the proposed method is effective, with the interception rate up to 60% and the average detection time for each image less than 1 second.

MR imaging in sports-related glenohumeral instability

PubMed Central

Waldt, Simone

2006-01-01

Sports-related shoulder pain and injuries represent a common problem. In this context, glenohumeral instability is currently believed to play a central role either as a recognized or as an unrecognized condition. Shoulder instabilities can roughly be divided into traumatic, atraumatic, and microtraumatic glenohumeral instabilities. In athletes, atraumatic and microtraumatic instabilities can lead to secondary impingement syndromes and chronic damage to intraarticular structures. Magnetic resonance (MR) arthrography is superior to conventional MR imaging in the diagnosis of labro-ligamentous injuries, intrinsic impingement, and SLAP (superior labral anteroposterior) lesions, and thus represents the most informative imaging modality in the overall assessment of glenohumeral instability. This article reviews the imaging criteria for the detection and classification of instability-related injuries in athletes with special emphasis on the influence of MR findings on therapeutic decisions. PMID:16633790

Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.

PubMed

Choi, Joon Yul; Yoo, Tae Keun; Seo, Jeong Gi; Kwak, Jiyong; Um, Terry Taewoong; Rim, Tyler Hyungtaek

2017-01-01

Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen's kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.

Detection of Alzheimer's disease using group lasso SVM-based region selection

NASA Astrophysics Data System (ADS)

Sun, Zhuo; Fan, Yong; Lelieveldt, Boudewijn P. F.; van de Giessen, Martijn

2015-03-01

Alzheimer's disease (AD) is one of the most frequent forms of dementia and an increasing challenging public health problem. In the last two decades, structural magnetic resonance imaging (MRI) has shown potential in distinguishing patients with Alzheimer's disease and elderly controls (CN). To obtain AD-specific biomarkers, previous research used either statistical testing to find statistically significant different regions between the two clinical groups, or l1 sparse learning to select isolated features in the image domain. In this paper, we propose a new framework that uses structural MRI to simultaneously distinguish the two clinical groups and find the bio-markers of AD, using a group lasso support vector machine (SVM). The group lasso term (mixed l1- l2 norm) introduces anatomical information from the image domain into the feature domain, such that the resulting set of selected voxels are more meaningful than the l1 sparse SVM. Because of large inter-structure size variation, we introduce a group specific normalization factor to deal with the structure size bias. Experiments have been performed on a well-designed AD vs. CN dataset1 to validate our method. Comparing to the l1 sparse SVM approach, our method achieved better classification performance and a more meaningful biomarker selection. When we vary the training set, the selected regions by our method were more stable than the l1 sparse SVM. Classification experiments showed that our group normalization lead to higher classification accuracy with fewer selected regions than the non-normalized method. Comparing to the state-of-art AD vs. CN classification methods, our approach not only obtains a high accuracy with the same dataset, but more importantly, we simultaneously find the brain anatomies that are closely related to the disease.

Global and Local Features Based Classification for Bleed-Through Removal

NASA Astrophysics Data System (ADS)

Hu, Xiangyu; Lin, Hui; Li, Shutao; Sun, Bin

2016-12-01

The text on one side of historical documents often seeps through and appears on the other side, so the bleed-through is a common problem in historical document images. It makes the document images hard to read and the text difficult to recognize. To improve the image quality and readability, the bleed-through has to be removed. This paper proposes a global and local features extraction based bleed-through removal method. The Gaussian mixture model is used to get the global features of the images. Local features are extracted by the patch around each pixel. Then, the extreme learning machine classifier is utilized to classify the scanned images into the foreground text and the bleed-through component. Experimental results on real document image datasets show that the proposed method outperforms the state-of-the-art bleed-through removal methods and preserves the text strokes well.

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

PubMed Central

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-01-01

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images. PMID:28335510

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction.

PubMed

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-03-20

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

Image characterization by fractal descriptors in variational mode decomposition domain: Application to brain magnetic resonance

NASA Astrophysics Data System (ADS)

Lahmiri, Salim

2016-08-01

The main purpose of this work is to explore the usefulness of fractal descriptors estimated in multi-resolution domains to characterize biomedical digital image texture. In this regard, three multi-resolution techniques are considered: the well-known discrete wavelet transform (DWT) and the empirical mode decomposition (EMD), and; the newly introduced; variational mode decomposition mode (VMD). The original image is decomposed by the DWT, EMD, and VMD into different scales. Then, Fourier spectrum based fractal descriptors is estimated at specific scales and directions to characterize the image. The support vector machine (SVM) was used to perform supervised classification. The empirical study was applied to the problem of distinguishing between normal and abnormal brain magnetic resonance images (MRI) affected with Alzheimer disease (AD). Our results demonstrate that fractal descriptors estimated in VMD domain outperform those estimated in DWT and EMD domains; and also those directly estimated from the original image.

Towards a computer-aided diagnosis system for vocal cord diseases.

PubMed

Verikas, A; Gelzinis, A; Bacauskiene, M; Uloza, V

2006-01-01

The objective of this work is to investigate a possibility of creating a computer-aided decision support system for an automated analysis of vocal cord images aiming to categorize diseases of vocal cords. The problem is treated as a pattern recognition task. To obtain a concise and informative representation of a vocal cord image, colour, texture, and geometrical features are used. The representation is further analyzed by a pattern classifier categorizing the image into healthy, diffuse, and nodular classes. The approach developed was tested on 785 vocal cord images collected at the Department of Otolaryngology, Kaunas University of Medicine, Lithuania. A correct classification rate of over 87% was obtained when categorizing a set of unseen images into the aforementioned three classes. Bearing in mind the high similarity of the decision classes, the results obtained are rather encouraging and the developed tools could be very helpful for assuring objective analysis of the images of laryngeal diseases.

Implementation of Nearest Neighbor using HSV to Identify Skin Disease

NASA Astrophysics Data System (ADS)

Gerhana, Y. A.; Zulfikar, W. B.; Ramdani, A. H.; Ramdhani, M. A.

2018-01-01

Today, Android is one of the most widely used operating system in the world. Most of android device has a camera that could capture an image, this feature could be optimized to identify skin disease. The disease is one of health problem caused by bacterium, fungi, and virus. The symptoms of skin disease usually visible. In this work, the symptoms that captured as image contains HSV in every pixel of the image. HSV can extracted and then calculate to earn euclidean value. The value compared using nearest neighbor algorithm to discover closer value between image testing and image training to get highest value that decide class label or type of skin disease. The testing result show that 166 of 200 or about 80% is accurate. There are some reasons that influence the result of classification model like number of image training and quality of android device’s camera.

Local Subspace Classifier with Transform-Invariance for Image Classification

NASA Astrophysics Data System (ADS)

Hotta, Seiji

A family of linear subspace classifiers called local subspace classifier (LSC) outperforms the k-nearest neighbor rule (kNN) and conventional subspace classifiers in handwritten digit classification. However, LSC suffers very high sensitivity to image transformations because it uses projection and the Euclidean distances for classification. In this paper, I present a combination of a local subspace classifier (LSC) and a tangent distance (TD) for improving accuracy of handwritten digit recognition. In this classification rule, we can deal with transform-invariance easily because we are able to use tangent vectors for approximation of transformations. However, we cannot use tangent vectors in other type of images such as color images. Hence, kernel LSC (KLSC) is proposed for incorporating transform-invariance into LSC via kernel mapping. The performance of the proposed methods is verified with the experiments on handwritten digit and color image classification.

Polsar Land Cover Classification Based on Hidden Polarimetric Features in Rotation Domain and Svm Classifier

NASA Astrophysics Data System (ADS)

Tao, C.-S.; Chen, S.-W.; Li, Y.-Z.; Xiao, S.-P.

2017-09-01

Land cover classification is an important application for polarimetric synthetic aperture radar (PolSAR) data utilization. Rollinvariant polarimetric features such as H / Ani / α / Span are commonly adopted in PolSAR land cover classification. However, target orientation diversity effect makes PolSAR images understanding and interpretation difficult. Only using the roll-invariant polarimetric features may introduce ambiguity in the interpretation of targets' scattering mechanisms and limit the followed classification accuracy. To address this problem, this work firstly focuses on hidden polarimetric feature mining in the rotation domain along the radar line of sight using the recently reported uniform polarimetric matrix rotation theory and the visualization and characterization tool of polarimetric coherence pattern. The former rotates the acquired polarimetric matrix along the radar line of sight and fully describes the rotation characteristics of each entry of the matrix. Sets of new polarimetric features are derived to describe the hidden scattering information of the target in the rotation domain. The latter extends the traditional polarimetric coherence at a given rotation angle to the rotation domain for complete interpretation. A visualization and characterization tool is established to derive new polarimetric features for hidden information exploration. Then, a classification scheme is developed combing both the selected new hidden polarimetric features in rotation domain and the commonly used roll-invariant polarimetric features with a support vector machine (SVM) classifier. Comparison experiments based on AIRSAR and multi-temporal UAVSAR data demonstrate that compared with the conventional classification scheme which only uses the roll-invariant polarimetric features, the proposed classification scheme achieves both higher classification accuracy and better robustness. For AIRSAR data, the overall classification accuracy with the proposed classification scheme is 94.91 %, while that with the conventional classification scheme is 93.70 %. Moreover, for multi-temporal UAVSAR data, the averaged overall classification accuracy with the proposed classification scheme is up to 97.08 %, which is much higher than the 87.79 % from the conventional classification scheme. Furthermore, for multitemporal PolSAR data, the proposed classification scheme can achieve better robustness. The comparison studies also clearly demonstrate that mining and utilization of hidden polarimetric features and information in the rotation domain can gain the added benefits for PolSAR land cover classification and provide a new vision for PolSAR image interpretation and application.

Building and Solving Odd-One-Out Classification Problems: A Systematic Approach

ERIC Educational Resources Information Center

Ruiz, Philippe E.

2011-01-01

Classification problems ("find the odd-one-out") are frequently used as tests of inductive reasoning to evaluate human or animal intelligence. This paper introduces a systematic method for building the set of all possible classification problems, followed by a simple algorithm for solving the problems of the R-ASCM, a psychometric test derived…

Classification of skin cancer images using local binary pattern and SVM classifier

NASA Astrophysics Data System (ADS)

Adjed, Faouzi; Faye, Ibrahima; Ababsa, Fakhreddine; Gardezi, Syed Jamal; Dass, Sarat Chandra

2016-11-01

In this paper, a classification method for melanoma and non-melanoma skin cancer images has been presented using the local binary patterns (LBP). The LBP computes the local texture information from the skin cancer images, which is later used to compute some statistical features that have capability to discriminate the melanoma and non-melanoma skin tissues. Support vector machine (SVM) is applied on the feature matrix for classification into two skin image classes (malignant and benign). The method achieves good classification accuracy of 76.1% with sensitivity of 75.6% and specificity of 76.7%.

Seismic waveform classification using deep learning

NASA Astrophysics Data System (ADS)

Kong, Q.; Allen, R. M.

2017-12-01

MyShake is a global smartphone seismic network that harnesses the power of crowdsourcing. It has an Artificial Neural Network (ANN) algorithm running on the phone to distinguish earthquake motion from human activities recorded by the accelerometer on board. Once the ANN detects earthquake-like motion, it sends a 5-min chunk of acceleration data back to the server for further analysis. The time-series data collected contains both earthquake data and human activity data that the ANN confused. In this presentation, we will show the Convolutional Neural Network (CNN) we built under the umbrella of supervised learning to find out the earthquake waveform. The waveforms of the recorded motion could treat easily as images, and by taking the advantage of the power of CNN processing the images, we achieved very high successful rate to select the earthquake waveforms out. Since there are many non-earthquake waveforms than the earthquake waveforms, we also built an anomaly detection algorithm using the CNN. Both these two methods can be easily extended to other waveform classification problems.

Spectral Regression Discriminant Analysis for Hyperspectral Image Classification

NASA Astrophysics Data System (ADS)

Pan, Y.; Wu, J.; Huang, H.; Liu, J.

2012-08-01

Dimensionality reduction algorithms, which aim to select a small set of efficient and discriminant features, have attracted great attention for Hyperspectral Image Classification. The manifold learning methods are popular for dimensionality reduction, such as Locally Linear Embedding, Isomap, and Laplacian Eigenmap. However, a disadvantage of many manifold learning methods is that their computations usually involve eigen-decomposition of dense matrices which is expensive in both time and memory. In this paper, we introduce a new dimensionality reduction method, called Spectral Regression Discriminant Analysis (SRDA). SRDA casts the problem of learning an embedding function into a regression framework, which avoids eigen-decomposition of dense matrices. Also, with the regression based framework, different kinds of regularizes can be naturally incorporated into our algorithm which makes it more flexible. It can make efficient use of data points to discover the intrinsic discriminant structure in the data. Experimental results on Washington DC Mall and AVIRIS Indian Pines hyperspectral data sets demonstrate the effectiveness of the proposed method.

Emotional modelling and classification of a large-scale collection of scene images in a cluster environment

PubMed Central

Li, Yanfei; Tian, Yun

2018-01-01

The development of network technology and the popularization of image capturing devices have led to a rapid increase in the number of digital images available, and it is becoming increasingly difficult to identify a desired image from among the massive number of possible images. Images usually contain rich semantic information, and people usually understand images at a high semantic level. Therefore, achieving the ability to use advanced technology to identify the emotional semantics contained in images to enable emotional semantic image classification remains an urgent issue in various industries. To this end, this study proposes an improved OCC emotion model that integrates personality and mood factors for emotional modelling to describe the emotional semantic information contained in an image. The proposed classification system integrates the k-Nearest Neighbour (KNN) algorithm with the Support Vector Machine (SVM) algorithm. The MapReduce parallel programming model was used to adapt the KNN-SVM algorithm for parallel implementation in the Hadoop cluster environment, thereby achieving emotional semantic understanding for the classification of a massive collection of images. For training and testing, 70,000 scene images were randomly selected from the SUN Database. The experimental results indicate that users with different personalities show overall consistency in their emotional understanding of the same image. For a training sample size of 50,000, the classification accuracies for different emotional categories targeted at users with different personalities were approximately 95%, and the training time was only 1/5 of that required for the corresponding algorithm with a single-node architecture. Furthermore, the speedup of the system also showed a linearly increasing tendency. Thus, the experiments achieved a good classification effect and can lay a foundation for classification in terms of additional types of emotional image semantics, thereby demonstrating the practical significance of the proposed model. PMID:29320579

Emotional modelling and classification of a large-scale collection of scene images in a cluster environment.

PubMed

Cao, Jianfang; Li, Yanfei; Tian, Yun

2018-01-01

The development of network technology and the popularization of image capturing devices have led to a rapid increase in the number of digital images available, and it is becoming increasingly difficult to identify a desired image from among the massive number of possible images. Images usually contain rich semantic information, and people usually understand images at a high semantic level. Therefore, achieving the ability to use advanced technology to identify the emotional semantics contained in images to enable emotional semantic image classification remains an urgent issue in various industries. To this end, this study proposes an improved OCC emotion model that integrates personality and mood factors for emotional modelling to describe the emotional semantic information contained in an image. The proposed classification system integrates the k-Nearest Neighbour (KNN) algorithm with the Support Vector Machine (SVM) algorithm. The MapReduce parallel programming model was used to adapt the KNN-SVM algorithm for parallel implementation in the Hadoop cluster environment, thereby achieving emotional semantic understanding for the classification of a massive collection of images. For training and testing, 70,000 scene images were randomly selected from the SUN Database. The experimental results indicate that users with different personalities show overall consistency in their emotional understanding of the same image. For a training sample size of 50,000, the classification accuracies for different emotional categories targeted at users with different personalities were approximately 95%, and the training time was only 1/5 of that required for the corresponding algorithm with a single-node architecture. Furthermore, the speedup of the system also showed a linearly increasing tendency. Thus, the experiments achieved a good classification effect and can lay a foundation for classification in terms of additional types of emotional image semantics, thereby demonstrating the practical significance of the proposed model.

Hyperspectral image classification based on local binary patterns and PCANet

NASA Astrophysics Data System (ADS)

Yang, Huizhen; Gao, Feng; Dong, Junyu; Yang, Yang

2018-04-01

Hyperspectral image classification has been well acknowledged as one of the challenging tasks of hyperspectral data processing. In this paper, we propose a novel hyperspectral image classification framework based on local binary pattern (LBP) features and PCANet. In the proposed method, linear prediction error (LPE) is first employed to select a subset of informative bands, and LBP is utilized to extract texture features. Then, spectral and texture features are stacked into a high dimensional vectors. Next, the extracted features of a specified position are transformed to a 2-D image. The obtained images of all pixels are fed into PCANet for classification. Experimental results on real hyperspectral dataset demonstrate the effectiveness of the proposed method.

Sub-pixel mapping of hyperspectral imagery using super-resolution

NASA Astrophysics Data System (ADS)

Sharma, Shreya; Sharma, Shakti; Buddhiraju, Krishna M.

2016-04-01

With the development of remote sensing technologies, it has become possible to obtain an overview of landscape elements which helps in studying the changes on earth's surface due to climate, geological, geomorphological and human activities. Remote sensing measures the electromagnetic radiations from the earth's surface and match the spectral similarity between the observed signature and the known standard signatures of the various targets. However, problem lies when image classification techniques assume pixels to be pure. In hyperspectral imagery, images have high spectral resolution but poor spatial resolution. Therefore, the spectra obtained is often contaminated due to the presence of mixed pixels and causes misclassification. To utilise this high spectral information, spatial resolution has to be enhanced. Many factors make the spatial resolution one of the most expensive and hardest to improve in imaging systems. To solve this problem, post-processing of hyperspectral images is done to retrieve more information from the already acquired images. The algorithm to enhance spatial resolution of the images by dividing them into sub-pixels is known as super-resolution and several researches have been done in this domain.In this paper, we propose a new method for super-resolution based on ant colony optimization and review the popular methods of sub-pixel mapping of hyperspectral images along with their comparative analysis.

Hyperspectral imaging with wavelet transform for classification of colon tissue biopsy samples

NASA Astrophysics Data System (ADS)

Masood, Khalid

2008-08-01

Automatic classification of medical images is a part of our computerised medical imaging programme to support the pathologists in their diagnosis. Hyperspectral data has found its applications in medical imagery. Its usage is increasing significantly in biopsy analysis of medical images. In this paper, we present a histopathological analysis for the classification of colon biopsy samples into benign and malignant classes. The proposed study is based on comparison between 3D spectral/spatial analysis and 2D spatial analysis. Wavelet textural features in the wavelet domain are used in both these approaches for classification of colon biopsy samples. Experimental results indicate that the incorporation of wavelet textural features using a support vector machine, in 2D spatial analysis, achieve best classification accuracy.

Extending a field-based Sonoran desert vegetation classification to a regional scale using optical and microwave satellite imagery

NASA Astrophysics Data System (ADS)

Shupe, Scott Marshall

2000-10-01

Vegetation mapping in and regions facilitates ecological studies, land management, and provides a record to which future land changes can be compared. Accurate and representative mapping of desert vegetation requires a sound field sampling program and a methodology to transform the data collected into a representative classification system. Time and cost constraints require that a remote sensing approach be used if such a classification system is to be applied on a regional scale. However, desert vegetation may be sparse and thus difficult to sense at typical satellite resolutions, especially given the problem of soil reflectance. This study was designed to address these concerns by conducting vegetation mapping research using field and satellite data from the US Army Yuma Proving Ground (USYPG) in Southwest Arizona. Line and belt transect data from the Army's Land Condition Trend Analysis (LCTA) Program were transformed into relative cover and relative density classification schemes using cluster analysis. Ordination analysis of the same data produced two and three-dimensional graphs on which the homogeneity of each vegetation class could be examined. It was found that the use of correspondence analysis (CA), detrended correspondence analysis (DCA), and non-metric multidimensional scaling (NMS) ordination methods was superior to the use of any single ordination method for helping to clarify between-class and within-class relationships in vegetation composition. Analysis of these between-class and within-class relationships were of key importance in examining how well relative cover and relative density schemes characterize the USYPG vegetation. Using these two classification schemes as reference data, maximum likelihood and artificial neural net classifications were then performed on a coregistered dataset consisting of a summer Landsat Thematic Mapper (TM) image, one spring and one summer ERS-1 microwave image, and elevation, slope, and aspect layers. Classifications using a combination of ERS-1 imagery and elevation, slope, and aspect data were superior to classifications carried out using Landsat TM data alone. In all classification iterations it was consistently found that the highest classification accuracy was obtained by using a combination of Landsat TM, ERS-1, and elevation, slope, and aspect data. Maximum likelihood classification accuracy was found to be higher than artificial neural net classification in all cases.

Unsupervised feature learning for autonomous rock image classification

NASA Astrophysics Data System (ADS)

Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond

2017-09-01

Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

Aquifer Hydrogeologic Layer Zonation at the Hanford Site

DOE Office of Scientific and Technical Information (OSTI.GOV)

Savelieva-Trofimova, Elena A.; Kanevski, Mikhail; timonin, v.

2003-09-10

Sedimentary aquifer layers are characterized by spatial variability of hydraulic properties. Nevertheless, zones with similar values of hydraulic parameters (parameter zones) can be distinguished. This parameter zonation approach is an alternative to the analysis of spatial variation of the continuous hydraulic parameters. The parameter zonation approach is primarily motivated by the lack of measurements that would be needed for direct spatial modeling of the hydraulic properties. The current work is devoted to the problem of zonation of the Hanford formation, the uppermost sedimentary aquifer unit (U1) included in hydrogeologic models at the Hanford site. U1 is characterized by 5 zonesmore » with different hydraulic properties. Each sampled location is ascribed to a parameter zone by an expert. This initial classification is accompanied by a measure of quality (also indicated by an expert) that addresses the level of classification confidence. In the current study, the coneptual zonation map developed by an expert geologist was used as an a priori model. The parameter zonation problem was formulated as a multiclass classification task. Different geostatistical and machine learning algorithms were adapted and applied to solve this problem, including: indicator kriging, conditional simulations, neural networks of different architectures, and support vector machines. All methods were trained using additional soft information based on expert estimates. Regularization methods were used to overcome possible overfitting. The zonation problem was complicated because there were few samples for some zones (classes) and by the spatial non-stationarity of the data. Special approaches were developed to overcome these complications. The comparison of different methods was performed using qualitative and quantitative statistical methods and image analysis. We examined the correspondence of the results with the geologically based interpretation, including the reproduction of the spatial orientation of the different classes and the spatial correlation structure of the classes. The uncertainty of the classification task was examined using both probabilistic interpretation of the estimators and by examining the results of a set of stochastic realizations. Characterization of the classification uncertainty is the main advantage of the proposed methods.« less

The fusion of large scale classified side-scan sonar image mosaics.

PubMed

Reed, Scott; Tena, Ruiz Ioseba; Capus, Chris; Petillot, Yvan

2006-07-01

This paper presents a unified framework for the creation of classified maps of the seafloor from sonar imagery. Significant challenges in photometric correction, classification, navigation and registration, and image fusion are addressed. The techniques described are directly applicable to a range of remote sensing problems. Recent advances in side-scan data correction are incorporated to compensate for the sonar beam pattern and motion of the acquisition platform. The corrected images are segmented using pixel-based textural features and standard classifiers. In parallel, the navigation of the sonar device is processed using Kalman filtering techniques. A simultaneous localization and mapping framework is adopted to improve the navigation accuracy and produce georeferenced mosaics of the segmented side-scan data. These are fused within a Markovian framework and two fusion models are presented. The first uses a voting scheme regularized by an isotropic Markov random field and is applicable when the reliability of each information source is unknown. The Markov model is also used to inpaint regions where no final classification decision can be reached using pixel level fusion. The second model formally introduces the reliability of each information source into a probabilistic model. Evaluation of the two models using both synthetic images and real data from a large scale survey shows significant quantitative and qualitative improvement using the fusion approach.

Ensemble methods with simple features for document zone classification

NASA Astrophysics Data System (ADS)

Obafemi-Ajayi, Tayo; Agam, Gady; Xie, Bingqing

2012-01-01

Document layout analysis is of fundamental importance for document image understanding and information retrieval. It requires the identification of blocks extracted from a document image via features extraction and block classification. In this paper, we focus on the classification of the extracted blocks into five classes: text (machine printed), handwriting, graphics, images, and noise. We propose a new set of features for efficient classifications of these blocks. We present a comparative evaluation of three ensemble based classification algorithms (boosting, bagging, and combined model trees) in addition to other known learning algorithms. Experimental results are demonstrated for a set of 36503 zones extracted from 416 document images which were randomly selected from the tobacco legacy document collection. The results obtained verify the robustness and effectiveness of the proposed set of features in comparison to the commonly used Ocropus recognition features. When used in conjunction with the Ocropus feature set, we further improve the performance of the block classification system to obtain a classification accuracy of 99.21%.

An evolution of image source camera attribution approaches.

PubMed

Jahanirad, Mehdi; Wahab, Ainuddin Wahid Abdul; Anuar, Nor Badrul

2016-05-01

Camera attribution plays an important role in digital image forensics by providing the evidence and distinguishing characteristics of the origin of the digital image. It allows the forensic analyser to find the possible source camera which captured the image under investigation. However, in real-world applications, these approaches have faced many challenges due to the large set of multimedia data publicly available through photo sharing and social network sites, captured with uncontrolled conditions and undergone variety of hardware and software post-processing operations. Moreover, the legal system only accepts the forensic analysis of the digital image evidence if the applied camera attribution techniques are unbiased, reliable, nondestructive and widely accepted by the experts in the field. The aim of this paper is to investigate the evolutionary trend of image source camera attribution approaches from fundamental to practice, in particular, with the application of image processing and data mining techniques. Extracting implicit knowledge from images using intrinsic image artifacts for source camera attribution requires a structured image mining process. In this paper, we attempt to provide an introductory tutorial on the image processing pipeline, to determine the general classification of the features corresponding to different components for source camera attribution. The article also reviews techniques of the source camera attribution more comprehensively in the domain of the image forensics in conjunction with the presentation of classifying ongoing developments within the specified area. The classification of the existing source camera attribution approaches is presented based on the specific parameters, such as colour image processing pipeline, hardware- and software-related artifacts and the methods to extract such artifacts. The more recent source camera attribution approaches, which have not yet gained sufficient attention among image forensics researchers, are also critically analysed and further categorised into four different classes, namely, optical aberrations based, sensor camera fingerprints based, processing statistics based and processing regularities based, to present a classification. Furthermore, this paper aims to investigate the challenging problems, and the proposed strategies of such schemes based on the suggested taxonomy to plot an evolution of the source camera attribution approaches with respect to the subjective optimisation criteria over the last decade. The optimisation criteria were determined based on the strategies proposed to increase the detection accuracy, robustness and computational efficiency of source camera brand, model or device attribution. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Time-reversal imaging for classification of submerged elastic targets via Gibbs sampling and the Relevance Vector Machine.

PubMed

Dasgupta, Nilanjan; Carin, Lawrence

2005-04-01

Time-reversal imaging (TRI) is analogous to matched-field processing, although TRI is typically very wideband and is appropriate for subsequent target classification (in addition to localization). Time-reversal techniques, as applied to acoustic target classification, are highly sensitive to channel mismatch. Hence, it is crucial to estimate the channel parameters before time-reversal imaging is performed. The channel-parameter statistics are estimated here by applying a geoacoustic inversion technique based on Gibbs sampling. The maximum a posteriori (MAP) estimate of the channel parameters are then used to perform time-reversal imaging. Time-reversal implementation requires a fast forward model, implemented here by a normal-mode framework. In addition to imaging, extraction of features from the time-reversed images is explored, with these applied to subsequent target classification. The classification of time-reversed signatures is performed by the relevance vector machine (RVM). The efficacy of the technique is analyzed on simulated in-channel data generated by a free-field finite element method (FEM) code, in conjunction with a channel propagation model, wherein the final classification performance is demonstrated to be relatively insensitive to the associated channel parameters. The underlying theory of Gibbs sampling and TRI are presented along with the feature extraction and target classification via the RVM.

Automatic Modulation Classification Based on Deep Learning for Unmanned Aerial Vehicles.

PubMed

Zhang, Duona; Ding, Wenrui; Zhang, Baochang; Xie, Chunyu; Li, Hongguang; Liu, Chunhui; Han, Jungong

2018-03-20

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition and remains challenging for traditional methods due to complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include the following: (1) a convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; (2) a large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and (3) experimental results demonstrate that HDMF is very capable of coping with the AMC problem, and achieves much better performance when compared with the independent network.

Automatic Modulation Classification Based on Deep Learning for Unmanned Aerial Vehicles

PubMed Central

Ding, Wenrui; Zhang, Baochang; Xie, Chunyu; Li, Hongguang; Liu, Chunhui; Han, Jungong

2018-01-01

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition and remains challenging for traditional methods due to complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include the following: (1) a convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; (2) a large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and (3) experimental results demonstrate that HDMF is very capable of coping with the AMC problem, and achieves much better performance when compared with the independent network. PMID:29558434

Multi-Pixel Simultaneous Classification of PolSAR Image Using Convolutional Neural Networks

PubMed Central

Xu, Xin; Gui, Rong; Pu, Fangling

2018-01-01

Convolutional neural networks (CNN) have achieved great success in the optical image processing field. Because of the excellent performance of CNN, more and more methods based on CNN are applied to polarimetric synthetic aperture radar (PolSAR) image classification. Most CNN-based PolSAR image classification methods can only classify one pixel each time. Because all the pixels of a PolSAR image are classified independently, the inherent interrelation of different land covers is ignored. We use a fixed-feature-size CNN (FFS-CNN) to classify all pixels in a patch simultaneously. The proposed method has several advantages. First, FFS-CNN can classify all the pixels in a small patch simultaneously. When classifying a whole PolSAR image, it is faster than common CNNs. Second, FFS-CNN is trained to learn the interrelation of different land covers in a patch, so it can use the interrelation of land covers to improve the classification results. The experiments of FFS-CNN are evaluated on a Chinese Gaofen-3 PolSAR image and other two real PolSAR images. Experiment results show that FFS-CNN is comparable with the state-of-the-art PolSAR image classification methods. PMID:29510499

Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries

PubMed Central

Md Noor, Siti Salwa; Michael, Kaleena; Marshall, Stephen; Ren, Jinchang

2017-01-01

In our preliminary study, the reflectance signatures obtained from hyperspectral imaging (HSI) of normal and abnormal corneal epithelium tissues of porcine show similar morphology with subtle differences. Here we present image enhancement algorithms that can be used to improve the interpretability of data into clinically relevant information to facilitate diagnostics. A total of 25 corneal epithelium images without the application of eye staining were used. Three image feature extraction approaches were applied for image classification: (i) image feature classification from histogram using a support vector machine with a Gaussian radial basis function (SVM-GRBF); (ii) physical image feature classification using deep-learning Convolutional Neural Networks (CNNs) only; and (iii) the combined classification of CNNs and SVM-Linear. The performance results indicate that our chosen image features from the histogram and length-scale parameter were able to classify with up to 100% accuracy; particularly, at CNNs and CNNs-SVM, by employing 80% of the data sample for training and 20% for testing. Thus, in the assessment of corneal epithelium injuries, HSI has high potential as a method that could surpass current technologies regarding speed, objectivity, and reliability. PMID:29144388

Multi-Pixel Simultaneous Classification of PolSAR Image Using Convolutional Neural Networks.

PubMed

Wang, Lei; Xu, Xin; Dong, Hao; Gui, Rong; Pu, Fangling

2018-03-03

Convolutional neural networks (CNN) have achieved great success in the optical image processing field. Because of the excellent performance of CNN, more and more methods based on CNN are applied to polarimetric synthetic aperture radar (PolSAR) image classification. Most CNN-based PolSAR image classification methods can only classify one pixel each time. Because all the pixels of a PolSAR image are classified independently, the inherent interrelation of different land covers is ignored. We use a fixed-feature-size CNN (FFS-CNN) to classify all pixels in a patch simultaneously. The proposed method has several advantages. First, FFS-CNN can classify all the pixels in a small patch simultaneously. When classifying a whole PolSAR image, it is faster than common CNNs. Second, FFS-CNN is trained to learn the interrelation of different land covers in a patch, so it can use the interrelation of land covers to improve the classification results. The experiments of FFS-CNN are evaluated on a Chinese Gaofen-3 PolSAR image and other two real PolSAR images. Experiment results show that FFS-CNN is comparable with the state-of-the-art PolSAR image classification methods.

Two-tier tissue decomposition for histopathological image representation and classification.

PubMed

Gultekin, Tunc; Koyuncu, Can Fahrettin; Sokmensuer, Cenk; Gunduz-Demir, Cigdem

2015-01-01

In digital pathology, devising effective image representations is crucial to design robust automated diagnosis systems. To this end, many studies have proposed to develop object-based representations, instead of directly using image pixels, since a histopathological image may contain a considerable amount of noise typically at the pixel-level. These previous studies mostly employ color information to define their objects, which approximately represent histological tissue components in an image, and then use the spatial distribution of these objects for image representation and classification. Thus, object definition has a direct effect on the way of representing the image, which in turn affects classification accuracies. In this paper, our aim is to design a classification system for histopathological images. Towards this end, we present a new model for effective representation of these images that will be used by the classification system. The contributions of this model are twofold. First, it introduces a new two-tier tissue decomposition method for defining a set of multityped objects in an image. Different than the previous studies, these objects are defined combining texture, shape, and size information and they may correspond to individual histological tissue components as well as local tissue subregions of different characteristics. As its second contribution, it defines a new metric, which we call dominant blob scale, to characterize the shape and size of an object with a single scalar value. Our experiments on colon tissue images reveal that this new object definition and characterization provides distinguishing representation of normal and cancerous histopathological images, which is effective to obtain more accurate classification results compared to its counterparts.

High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks.

PubMed

Rajkomar, Alvin; Lingam, Sneha; Taylor, Andrew G; Blum, Michael; Mongan, John

2017-02-01

The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73-100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation.

Unsupervised universal steganalyzer for high-dimensional steganalytic features

NASA Astrophysics Data System (ADS)

Hou, Xiaodan; Zhang, Tao

2016-11-01

The research in developing steganalytic features has been highly successful. These features are extremely powerful when applied to supervised binary classification problems. However, they are incompatible with unsupervised universal steganalysis because the unsupervised method cannot distinguish embedding distortion from varying levels of noises caused by cover variation. This study attempts to alleviate the problem by introducing similarity retrieval of image statistical properties (SRISP), with the specific aim of mitigating the effect of cover variation on the existing steganalytic features. First, cover images with some statistical properties similar to those of a given test image are searched from a retrieval cover database to establish an aided sample set. Then, unsupervised outlier detection is performed on a test set composed of the given test image and its aided sample set to determine the type (cover or stego) of the given test image. Our proposed framework, called SRISP-aided unsupervised outlier detection, requires no training. Thus, it does not suffer from model mismatch mess. Compared with prior unsupervised outlier detectors that do not consider SRISP, the proposed framework not only retains the universality but also exhibits superior performance when applied to high-dimensional steganalytic features.

Semi-supervised classification tool for DubaiSat-2 multispectral imagery

NASA Astrophysics Data System (ADS)

Al-Mansoori, Saeed

2015-10-01

This paper addresses a semi-supervised classification tool based on a pixel-based approach of the multi-spectral satellite imagery. There are not many studies demonstrating such algorithm for the multispectral images, especially when the image consists of 4 bands (Red, Green, Blue and Near Infrared) as in DubaiSat-2 satellite images. The proposed approach utilizes both unsupervised and supervised classification schemes sequentially to identify four classes in the image, namely, water bodies, vegetation, land (developed and undeveloped areas) and paved areas (i.e. roads). The unsupervised classification concept is applied to identify two classes; water bodies and vegetation, based on a well-known index that uses the distinct wavelengths of visible and near-infrared sunlight that is absorbed and reflected by the plants to identify the classes; this index parameter is called "Normalized Difference Vegetation Index (NDVI)". Afterward, the supervised classification is performed by selecting training homogenous samples for roads and land areas. Here, a precise selection of training samples plays a vital role in the classification accuracy. Post classification is finally performed to enhance the classification accuracy, where the classified image is sieved, clumped and filtered before producing final output. Overall, the supervised classification approach produced higher accuracy than the unsupervised method. This paper shows some current preliminary research results which point out the effectiveness of the proposed technique in a virtual perspective.

A minimum spanning forest based classification method for dedicated breast CT images

DOE Office of Scientific and Technical Information (OSTI.GOV)

Pike, Robert; Sechopoulos, Ioannis; Fei, Baowei, E-mail: bfei@emory.edu

Purpose: To develop and test an automated algorithm to classify different types of tissue in dedicated breast CT images. Methods: Images of a single breast of five different patients were acquired with a dedicated breast CT clinical prototype. The breast CT images were processed by a multiscale bilateral filter to reduce noise while keeping edge information and were corrected to overcome cupping artifacts. As skin and glandular tissue have similar CT values on breast CT images, morphologic processing is used to identify the skin based on its position information. A support vector machine (SVM) is trained and the resulting modelmore » used to create a pixelwise classification map of fat and glandular tissue. By combining the results of the skin mask with the SVM results, the breast tissue is classified as skin, fat, and glandular tissue. This map is then used to identify markers for a minimum spanning forest that is grown to segment the image using spatial and intensity information. To evaluate the authors’ classification method, they use DICE overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on five patient images. Results: Comparison between the automatic and the manual segmentation shows that the minimum spanning forest based classification method was able to successfully classify dedicated breast CT image with average DICE ratios of 96.9%, 89.8%, and 89.5% for fat, glandular, and skin tissue, respectively. Conclusions: A 2D minimum spanning forest based classification method was proposed and evaluated for classifying the fat, skin, and glandular tissue in dedicated breast CT images. The classification method can be used for dense breast tissue quantification, radiation dose assessment, and other applications in breast imaging.« less

A Wavelet Polarization Decomposition Net Model for Polarimetric SAR Image Classification

NASA Astrophysics Data System (ADS)

He, Chu; Ou, Dan; Yang, Teng; Wu, Kun; Liao, Mingsheng; Chen, Erxue

2014-11-01

In this paper, a deep model based on wavelet texture has been proposed for Polarimetric Synthetic Aperture Radar (PolSAR) image classification inspired by recent successful deep learning method. Our model is supposed to learn powerful and informative representations to improve the generalization ability for the complex scene classification tasks. Given the influence of speckle noise in Polarimetric SAR image, wavelet polarization decomposition is applied first to obtain basic and discriminative texture features which are then embedded into a Deep Neural Network (DNN) in order to compose multi-layer higher representations. We demonstrate that the model can produce a powerful representation which can capture some untraceable information from Polarimetric SAR images and show a promising achievement in comparison with other traditional SAR image classification methods for the SAR image dataset.

A comparative study for chest radiograph image retrieval using binary texture and deep learning classification.

PubMed

Anavi, Yaron; Kogan, Ilya; Gelbart, Elad; Geva, Ofer; Greenspan, Hayit

2015-08-01

In this work various approaches are investigated for X-ray image retrieval and specifically chest pathology retrieval. Given a query image taken from a data set of 443 images, the objective is to rank images according to similarity. Different features, including binary features, texture features, and deep learning (CNN) features are examined. In addition, two approaches are investigated for the retrieval task. One approach is based on the distance of image descriptors using the above features (hereon termed the "descriptor"-based approach); the second approach ("classification"-based approach) is based on a probability descriptor, generated by a pair-wise classification of each two classes (pathologies) and their decision values using an SVM classifier. Best results are achieved using deep learning features in a classification scheme.

Restoration of Wavelet-Compressed Images and Motion Imagery

DTIC Science & Technology

2004-01-01

SECURITY CLASSIFICATION OF REPORT UNCLASSIFIED 18. SECURITY CLASSIFICATION OF THIS PAGE UNCLASSIFIED 19. SECURITY CLASSIFICATION...images is that they are global translates of each other, where 29 the global motion parameters are known. In a very simple sense , these five images form...Image Proc., vol. 1, Oct. 2001, pp. 185–188. [2] J. W. Woods and T. Naveen, “A filter based bit allocation scheme for subband compresion of HDTV,” IEEE

AVHRR channel selection for land cover classification

USGS Publications Warehouse

Maxwell, S.K.; Hoffer, R.M.; Chapman, P.L.

2002-01-01

Mapping land cover of large regions often requires processing of satellite images collected from several time periods at many spectral wavelength channels. However, manipulating and processing large amounts of image data increases the complexity and time, and hence the cost, that it takes to produce a land cover map. Very few studies have evaluated the importance of individual Advanced Very High Resolution Radiometer (AVHRR) channels for discriminating cover types, especially the thermal channels (channels 3, 4 and 5). Studies rarely perform a multi-year analysis to determine the impact of inter-annual variability on the classification results. We evaluated 5 years of AVHRR data using combinations of the original AVHRR spectral channels (1-5) to determine which channels are most important for cover type discrimination, yet stabilize inter-annual variability. Particular attention was placed on the channels in the thermal portion of the spectrum. Fourteen cover types over the entire state of Colorado were evaluated using a supervised classification approach on all two-, three-, four- and five-channel combinations for seven AVHRR biweekly composite datasets covering the entire growing season for each of 5 years. Results show that all three of the major portions of the electromagnetic spectrum represented by the AVHRR sensor are required to discriminate cover types effectively and stabilize inter-annual variability. Of the two-channel combinations, channels 1 (red visible) and 2 (near-infrared) had, by far, the highest average overall accuracy (72.2%), yet the inter-annual classification accuracies were highly variable. Including a thermal channel (channel 4) significantly increased the average overall classification accuracy by 5.5% and stabilized interannual variability. Each of the thermal channels gave similar classification accuracies; however, because of the problems in consistently interpreting channel 3 data, either channel 4 or 5 was found to be a more appropriate choice. Substituting the thermal channel with a single elevation layer resulted in equivalent classification accuracies and inter-annual variability.

A Marker-Based Approach for the Automated Selection of a Single Segmentation from a Hierarchical Set of Image Segmentations

NASA Technical Reports Server (NTRS)

Tarabalka, Y.; Tilton, J. C.; Benediktsson, J. A.; Chanussot, J.

2012-01-01

The Hierarchical SEGmentation (HSEG) algorithm, which combines region object finding with region object clustering, has given good performances for multi- and hyperspectral image analysis. This technique produces at its output a hierarchical set of image segmentations. The automated selection of a single segmentation level is often necessary. We propose and investigate the use of automatically selected markers for this purpose. In this paper, a novel Marker-based HSEG (M-HSEG) method for spectral-spatial classification of hyperspectral images is proposed. Two classification-based approaches for automatic marker selection are adapted and compared for this purpose. Then, a novel constrained marker-based HSEG algorithm is applied, resulting in a spectral-spatial classification map. Three different implementations of the M-HSEG method are proposed and their performances in terms of classification accuracies are compared. The experimental results, presented for three hyperspectral airborne images, demonstrate that the proposed approach yields accurate segmentation and classification maps, and thus is attractive for remote sensing image analysis.

A contour-based shape descriptor for biomedical image classification and retrieval

NASA Astrophysics Data System (ADS)

You, Daekeun; Antani, Sameer; Demner-Fushman, Dina; Thoma, George R.

2013-12-01

Contours, object blobs, and specific feature points are utilized to represent object shapes and extract shape descriptors that can then be used for object detection or image classification. In this research we develop a shape descriptor for biomedical image type (or, modality) classification. We adapt a feature extraction method used in optical character recognition (OCR) for character shape representation, and apply various image preprocessing methods to successfully adapt the method to our application. The proposed shape descriptor is applied to radiology images (e.g., MRI, CT, ultrasound, X-ray, etc.) to assess its usefulness for modality classification. In our experiment we compare our method with other visual descriptors such as CEDD, CLD, Tamura, and PHOG that extract color, texture, or shape information from images. The proposed method achieved the highest classification accuracy of 74.1% among all other individual descriptors in the test, and when combined with CSD (color structure descriptor) showed better performance (78.9%) than using the shape descriptor alone.

Histogram Curve Matching Approaches for Object-based Image Classification of Land Cover and Land Use

PubMed Central

Toure, Sory I.; Stow, Douglas A.; Weeks, John R.; Kumar, Sunil

2013-01-01

The classification of image-objects is usually done using parametric statistical measures of central tendency and/or dispersion (e.g., mean or standard deviation). The objectives of this study were to analyze digital number histograms of image objects and evaluate classifications measures exploiting characteristic signatures of such histograms. Two histograms matching classifiers were evaluated and compared to the standard nearest neighbor to mean classifier. An ADS40 airborne multispectral image of San Diego, California was used for assessing the utility of curve matching classifiers in a geographic object-based image analysis (GEOBIA) approach. The classifications were performed with data sets having 0.5 m, 2.5 m, and 5 m spatial resolutions. Results show that histograms are reliable features for characterizing classes. Also, both histogram matching classifiers consistently performed better than the one based on the standard nearest neighbor to mean rule. The highest classification accuracies were produced with images having 2.5 m spatial resolution. PMID:24403648

Improving mass candidate detection in mammograms via feature maxima propagation and local feature selection.

PubMed

Melendez, Jaime; Sánchez, Clara I; van Ginneken, Bram; Karssemeijer, Nico

2014-08-01

Mass candidate detection is a crucial component of multistep computer-aided detection (CAD) systems. It is usually performed by combining several local features by means of a classifier. When these features are processed on a per-image-location basis (e.g., for each pixel), mismatching problems may arise while constructing feature vectors for classification, which is especially true when the behavior expected from the evaluated features is a peaked response due to the presence of a mass. In this study, two of these problems, consisting of maxima misalignment and differences of maxima spread, are identified and two solutions are proposed. The first proposed method, feature maxima propagation, reproduces feature maxima through their neighboring locations. The second method, local feature selection, combines different subsets of features for different feature vectors associated with image locations. Both methods are applied independently and together. The proposed methods are included in a mammogram-based CAD system intended for mass detection in screening. Experiments are carried out with a database of 382 digital cases. Sensitivity is assessed at two sets of operating points. The first one is the interval of 3.5-15 false positives per image (FPs/image), which is typical for mass candidate detection. The second one is 1 FP/image, which allows to estimate the quality of the mass candidate detector's output for use in subsequent steps of the CAD system. The best results are obtained when the proposed methods are applied together. In that case, the mean sensitivity in the interval of 3.5-15 FPs/image significantly increases from 0.926 to 0.958 (p < 0.0002). At the lower rate of 1 FP/image, the mean sensitivity improves from 0.628 to 0.734 (p < 0.0002). Given the improved detection performance, the authors believe that the strategies proposed in this paper can render mass candidate detection approaches based on image location classification more robust to feature discrepancies and prove advantageous not only at the candidate detection level, but also at subsequent steps of a CAD system.