Performance improvement of multi-class detection using greedy algorithm for Viola-Jones cascade selection

NASA Astrophysics Data System (ADS)

Tereshin, Alexander A.; Usilin, Sergey A.; Arlazarov, Vladimir V.

2018-04-01

This paper aims to study the problem of multi-class object detection in video stream with Viola-Jones cascades. An adaptive algorithm for selecting Viola-Jones cascade based on greedy choice strategy in solution of the N-armed bandit problem is proposed. The efficiency of the algorithm on the problem of detection and recognition of the bank card logos in the video stream is shown. The proposed algorithm can be effectively used in documents localization and identification, recognition of road scene elements, localization and tracking of the lengthy objects , and for solving other problems of rigid object detection in a heterogeneous data flows. The computational efficiency of the algorithm makes it possible to use it both on personal computers and on mobile devices based on processors with low power consumption.

Complex scenes and situations visualization in hierarchical learning algorithm with dynamic 3D NeoAxis engine

NASA Astrophysics Data System (ADS)

Graham, James; Ternovskiy, Igor V.

2013-06-01

We applied a two stage unsupervised hierarchical learning system to model complex dynamic surveillance and cyber space monitoring systems using a non-commercial version of the NeoAxis visualization software. The hierarchical scene learning and recognition approach is based on hierarchical expectation maximization, and was linked to a 3D graphics engine for validation of learning and classification results and understanding the human - autonomous system relationship. Scene recognition is performed by taking synthetically generated data and feeding it to a dynamic logic algorithm. The algorithm performs hierarchical recognition of the scene by first examining the features of the objects to determine which objects are present, and then determines the scene based on the objects present. This paper presents a framework within which low level data linked to higher-level visualization can provide support to a human operator and be evaluated in a detailed and systematic way.

Image registration under translation and rotation in two-dimensional planes using Fourier slice theorem.

PubMed

Pohit, M; Sharma, J

2015-05-10

Image recognition in the presence of both rotation and translation is a longstanding problem in correlation pattern recognition. Use of log polar transform gives a solution to this problem, but at a cost of losing the vital phase information from the image. The main objective of this paper is to develop an algorithm based on Fourier slice theorem for measuring the simultaneous rotation and translation of an object in a 2D plane. The algorithm is applicable for any arbitrary object shift for full 180° rotation.

Demonstration of a 3D vision algorithm for space applications

NASA Technical Reports Server (NTRS)

Defigueiredo, Rui J. P. (Editor)

1987-01-01

This paper reports an extension of the MIAG algorithm for recognition and motion parameter determination of general 3-D polyhedral objects based on model matching techniques and using movement invariants as features of object representation. Results of tests conducted on the algorithm under conditions simulating space conditions are presented.

Hybrid simulated annealing and its application to optimization of hidden Markov models for visual speech recognition.

PubMed

Lee, Jong-Seok; Park, Cheol Hoon

2010-08-01

We propose a novel stochastic optimization algorithm, hybrid simulated annealing (SA), to train hidden Markov models (HMMs) for visual speech recognition. In our algorithm, SA is combined with a local optimization operator that substitutes a better solution for the current one to improve the convergence speed and the quality of solutions. We mathematically prove that the sequence of the objective values converges in probability to the global optimum in the algorithm. The algorithm is applied to train HMMs that are used as visual speech recognizers. While the popular training method of HMMs, the expectation-maximization algorithm, achieves only local optima in the parameter space, the proposed method can perform global optimization of the parameters of HMMs and thereby obtain solutions yielding improved recognition performance. The superiority of the proposed algorithm to the conventional ones is demonstrated via isolated word recognition experiments.

Sensor agnostic object recognition using a map seeking circuit

NASA Astrophysics Data System (ADS)

Overman, Timothy L.; Hart, Michael

2012-05-01

Automatic object recognition capabilities are traditionally tuned to exploit the specific sensing modality they were designed to. Their successes (and shortcomings) are tied to object segmentation from the background, they typically require highly skilled personnel to train them, and they become cumbersome with the introduction of new objects. In this paper we describe a sensor independent algorithm based on the biologically inspired technology of map seeking circuits (MSC) which overcomes many of these obstacles. In particular, the MSC concept offers transparency in object recognition from a common interface to all sensor types, analogous to a USB device. It also provides a common core framework that is independent of the sensor and expandable to support high dimensionality decision spaces. Ease in training is assured by using commercially available 3D models from the video game community. The search time remains linear no matter how many objects are introduced, ensuring rapid object recognition. Here, we report results of an MSC algorithm applied to object recognition and pose estimation from high range resolution radar (1D), electrooptical imagery (2D), and LIDAR point clouds (3D) separately. By abstracting the sensor phenomenology from the underlying a prior knowledge base, MSC shows promise as an easily adaptable tool for incorporating additional sensor inputs.

Generation, recognition, and consistent fusion of partial boundary representations from range images

NASA Astrophysics Data System (ADS)

Kohlhepp, Peter; Hanczak, Andrzej M.; Li, Gang

1994-10-01

This paper presents SOMBRERO, a new system for recognizing and locating 3D, rigid, non- moving objects from range data. The objects may be polyhedral or curved, partially occluding, touching or lying flush with each other. For data collection, we employ 2D time- of-flight laser scanners mounted to a moving gantry robot. By combining sensor and robot coordinates, we obtain 3D cartesian coordinates. Boundary representations (Brep's) provide view independent geometry models that are both efficiently recognizable and derivable automatically from sensor data. SOMBRERO's methods for generating, matching and fusing Brep's are highly synergetic. A split-and-merge segmentation algorithm with dynamic triangular builds a partial (21/2D) Brep from scattered data. The recognition module matches this scene description with a model database and outputs recognized objects, their positions and orientations, and possibly surfaces corresponding to unknown objects. We present preliminary results in scene segmentation and recognition. Partial Brep's corresponding to different range sensors or viewpoints can be merged into a consistent, complete and irredundant 3D object or scene model. This fusion algorithm itself uses the recognition and segmentation methods.

Object recognition in images via a factor graph model

NASA Astrophysics Data System (ADS)

He, Yong; Wang, Long; Wu, Zhaolin; Zhang, Haisu

2018-04-01

Object recognition in images suffered from huge search space and uncertain object profile. Recently, the Bag-of- Words methods are utilized to solve these problems, especially the 2-dimension CRF(Conditional Random Field) model. In this paper we suggest the method based on a general and flexible fact graph model, which can catch the long-range correlation in Bag-of-Words by constructing a network learning framework contrasted from lattice in CRF. Furthermore, we explore a parameter learning algorithm based on the gradient descent and Loopy Sum-Product algorithms for the factor graph model. Experimental results on Graz 02 dataset show that, the recognition performance of our method in precision and recall is better than a state-of-art method and the original CRF model, demonstrating the effectiveness of the proposed method.

Automatic anatomy recognition via multiobject oriented active shape models.

PubMed

Chen, Xinjian; Udupa, Jayaram K; Alavi, Abass; Torigian, Drew A

2010-12-01

This paper studies the feasibility of developing an automatic anatomy recognition (AAR) system in clinical radiology and demonstrates its operation on clinical 2D images. The anatomy recognition method described here consists of two main components: (a) multiobject generalization of OASM and (b) object recognition strategies. The OASM algorithm is generalized to multiple objects by including a model for each object and assigning a cost structure specific to each object in the spirit of live wire. The delineation of multiobject boundaries is done in MOASM via a three level dynamic programming algorithm, wherein the first level is at pixel level which aims to find optimal oriented boundary segments between successive landmarks, the second level is at landmark level which aims to find optimal location for the landmarks, and the third level is at the object level which aims to find optimal arrangement of object boundaries over all objects. The object recognition strategy attempts to find that pose vector (consisting of translation, rotation, and scale component) for the multiobject model that yields the smallest total boundary cost for all objects. The delineation and recognition accuracies were evaluated separately utilizing routine clinical chest CT, abdominal CT, and foot MRI data sets. The delineation accuracy was evaluated in terms of true and false positive volume fractions (TPVF and FPVF). The recognition accuracy was assessed (1) in terms of the size of the space of the pose vectors for the model assembly that yielded high delineation accuracy, (2) as a function of the number of objects and objects' distribution and size in the model, (3) in terms of the interdependence between delineation and recognition, and (4) in terms of the closeness of the optimum recognition result to the global optimum. When multiple objects are included in the model, the delineation accuracy in terms of TPVF can be improved to 97%-98% with a low FPVF of 0.1%-0.2%. Typically, a recognition accuracy of > or = 90% yielded a TPVF > or = 95% and FPVF < or = 0.5%. Over the three data sets and over all tested objects, in 97% of the cases, the optimal solutions found by the proposed method constituted the true global optimum. The experimental results showed the feasibility and efficacy of the proposed automatic anatomy recognition system. Increasing the number of objects in the model can significantly improve both recognition and delineation accuracy. More spread out arrangement of objects in the model can lead to improved recognition and delineation accuracy. Including larger objects in the model also improved recognition and delineation. The proposed method almost always finds globally optimum solutions.

OPTICAL INFORMATION PROCESSING: Synthesis of an object recognition system based on the profile of the envelope of a laser pulse in pulsed lidars

NASA Astrophysics Data System (ADS)

Buryi, E. V.

1998-05-01

The main problems in the synthesis of an object recognition system, based on the principles of operation of neuron networks, are considered. Advantages are demonstrated of a hierarchical structure of the recognition algorithm. The use of reading of the amplitude spectrum of signals as information tags is justified and a method is developed for determination of the dimensionality of the tag space. Methods are suggested for ensuring the stability of object recognition in the optical range. It is concluded that it should be possible to recognise perspectives of complex objects.

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar

PubMed Central

Shin, Young Hoon; Seo, Jiwon

2016-01-01

People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker’s vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing. PMID:27801867

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar.

PubMed

Shin, Young Hoon; Seo, Jiwon

2016-10-29

People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker's vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing.

Object recognition and localization from 3D point clouds by maximum-likelihood estimation

NASA Astrophysics Data System (ADS)

Dantanarayana, Harshana G.; Huntley, Jonathan M.

2017-08-01

We present an algorithm based on maximum-likelihood analysis for the automated recognition of objects, and estimation of their pose, from 3D point clouds. Surfaces segmented from depth images are used as the features, unlike `interest point'-based algorithms which normally discard such data. Compared to the 6D Hough transform, it has negligible memory requirements, and is computationally efficient compared to iterative closest point algorithms. The same method is applicable to both the initial recognition/pose estimation problem as well as subsequent pose refinement through appropriate choice of the dispersion of the probability density functions. This single unified approach therefore avoids the usual requirement for different algorithms for these two tasks. In addition to the theoretical description, a simple 2 degrees of freedom (d.f.) example is given, followed by a full 6 d.f. analysis of 3D point cloud data from a cluttered scene acquired by a projected fringe-based scanner, which demonstrated an RMS alignment error as low as 0.3 mm.

How does the brain solve visual object recognition?

PubMed Central

Zoccolan, Davide; Rust, Nicole C.

2012-01-01

Mounting evidence suggests that “core object recognition,” the ability to rapidly recognize objects despite substantial appearance variation, is solved in the brain via a cascade of reflexive, largely feedforward computations that culminate in a powerful neuronal representation in the inferior temporal cortex. However, the algorithm that produces this solution remains little-understood. Here we review evidence ranging from individual neurons, to neuronal populations, to behavior, to computational models. We propose that understanding this algorithm will require using neuronal and psychophysical data to sift through many computational models, each based on building blocks of small, canonical sub-networks with a common functional goal. PMID:22325196

Development of a two wheeled self balancing robot with speech recognition and navigation algorithm

NASA Astrophysics Data System (ADS)

Rahman, Md. Muhaimin; Ashik-E-Rasul, Haq, Nowab. Md. Aminul; Hassan, Mehedi; Hasib, Irfan Mohammad Al; Hassan, K. M. Rafidh

2016-07-01

This paper is aimed to discuss modeling, construction and development of navigation algorithm of a two wheeled self balancing mobile robot in an enclosure. In this paper, we have discussed the design of two of the main controller algorithms, namely PID algorithms, on the robot model. Simulation is performed in the SIMULINK environment. The controller is developed primarily for self-balancing of the robot and also it's positioning. As for the navigation in an enclosure, template matching algorithm is proposed for precise measurement of the robot position. The navigation system needs to be calibrated before navigation process starts. Almost all of the earlier template matching algorithms that can be found in the open literature can only trace the robot. But the proposed algorithm here can also locate the position of other objects in an enclosure, like furniture, tables etc. This will enable the robot to know the exact location of every stationary object in the enclosure. Moreover, some additional features, such as Speech Recognition and Object Detection, are added. For Object Detection, the single board Computer Raspberry Pi is used. The system is programmed to analyze images captured via the camera, which are then processed through background subtraction, followed by active noise reduction.

Selection of Norway spruce somatic embryos by computer vision

NASA Astrophysics Data System (ADS)

Hamalainen, Jari J.; Jokinen, Kari J.

1993-05-01

A computer vision system was developed for the classification of plant somatic embryos. The embryos are in a Petri dish that is transferred with constant speed and they are recognized as they pass a line scan camera. A classification algorithm needs to be installed for every plant species. This paper describes an algorithm for the recognition of Norway spruce (Picea abies) embryos. A short review of conifer micropropagation by somatic embryogenesis is also given. The recognition algorithm is based on features calculated from the boundary of the object. Only part of the boundary corresponding to the developing cotyledons (2 - 15) and the straight sides of the embryo are used for recognition. An index of the length of the cotyledons describes the developmental stage of the embryo. The testing set for classifier performance consisted of 118 embryos and 478 nonembryos. With the classification tolerances chosen 69% of the objects classified as embryos by a human classifier were selected and 31$% rejected. Less than 1% of the nonembryos were classified as embryos. The basic features developed can probably be easily adapted for the recognition of other conifer somatic embryos.

A method for the evaluation of image quality according to the recognition effectiveness of objects in the optical remote sensing image using machine learning algorithm.

PubMed

Yuan, Tao; Zheng, Xinqi; Hu, Xuan; Zhou, Wei; Wang, Wei

2014-01-01

Objective and effective image quality assessment (IQA) is directly related to the application of optical remote sensing images (ORSI). In this study, a new IQA method of standardizing the target object recognition rate (ORR) is presented to reflect quality. First, several quality degradation treatments with high-resolution ORSIs are implemented to model the ORSIs obtained in different imaging conditions; then, a machine learning algorithm is adopted for recognition experiments on a chosen target object to obtain ORRs; finally, a comparison with commonly used IQA indicators was performed to reveal their applicability and limitations. The results showed that the ORR of the original ORSI was calculated to be up to 81.95%, whereas the ORR ratios of the quality-degraded images to the original images were 65.52%, 64.58%, 71.21%, and 73.11%. The results show that these data can more accurately reflect the advantages and disadvantages of different images in object identification and information extraction when compared with conventional digital image assessment indexes. By recognizing the difference in image quality from the application effect perspective, using a machine learning algorithm to extract regional gray scale features of typical objects in the image for analysis, and quantitatively assessing quality of ORSI according to the difference, this method provides a new approach for objective ORSI assessment.

Data-driven indexing mechanism for the recognition of polyhedral objects

NASA Astrophysics Data System (ADS)

McLean, Stewart; Horan, Peter; Caelli, Terry M.

1992-02-01

This paper is concerned with the problem of searching large model databases. To date, most object recognition systems have concentrated on the problem of matching using simple searching algorithms. This is quite acceptable when the number of object models is small. However, in the future, general purpose computer vision systems will be required to recognize hundreds or perhaps thousands of objects and, in such circumstances, efficient searching algorithms will be needed. The problem of searching a large model database is one which must be addressed if future computer vision systems are to be at all effective. In this paper we present a method we call data-driven feature-indexed hypothesis generation as one solution to the problem of searching large model databases.

Stochastic resonance investigation of object detection in images

NASA Astrophysics Data System (ADS)

Repperger, Daniel W.; Pinkus, Alan R.; Skipper, Julie A.; Schrider, Christina D.

2007-02-01

Object detection in images was conducted using a nonlinear means of improving signal to noise ratio termed "stochastic resonance" (SR). In a recent United States patent application, it was shown that arbitrarily large signal to noise ratio gains could be realized when a signal detection problem is cast within the context of a SR filter. Signal-to-noise ratio measures were investigated. For a binary object recognition task (friendly versus hostile), the method was implemented by perturbing the recognition algorithm and subsequently thresholding via a computer simulation. To fairly test the efficacy of the proposed algorithm, a unique database of images has been constructed by modifying two sample library objects by adjusting their brightness, contrast and relative size via commercial software to gradually compromise their saliency to identification. The key to the use of the SR method is to produce a small perturbation in the identification algorithm and then to threshold the results, thus improving the overall system's ability to discern objects. A background discussion of the SR method is presented. A standard test is proposed in which object identification algorithms could be fairly compared against each other with respect to their relative performance.

Extraction of edge-based and region-based features for object recognition

NASA Astrophysics Data System (ADS)

Coutts, Benjamin; Ravi, Srinivas; Hu, Gongzhu; Shrikhande, Neelima

1993-08-01

One of the central problems of computer vision is object recognition. A catalogue of model objects is described as a set of features such as edges and surfaces. The same features are extracted from the scene and matched against the models for object recognition. Edges and surfaces extracted from the scenes are often noisy and imperfect. In this paper algorithms are described for improving low level edge and surface features. Existing edge extraction algorithms are applied to the intensity image to obtain edge features. Initial edges are traced by following directions of the current contour. These are improved by using corresponding depth and intensity information for decision making at branch points. Surface fitting routines are applied to the range image to obtain planar surface patches. An algorithm of region growing is developed that starts with a coarse segmentation and uses quadric surface fitting to iteratively merge adjacent regions into quadric surfaces based on approximate orthogonal distance regression. Surface information obtained is returned to the edge extraction routine to detect and remove fake edges. This process repeats until no more merging or edge improvement can take place. Both synthetic (with Gaussian noise) and real images containing multiple object scenes have been tested using the merging criteria. Results appeared quite encouraging.

Feature extraction for face recognition via Active Shape Model (ASM) and Active Appearance Model (AAM)

NASA Astrophysics Data System (ADS)

Iqtait, M.; Mohamad, F. S.; Mamat, M.

2018-03-01

Biometric is a pattern recognition system which is used for automatic recognition of persons based on characteristics and features of an individual. Face recognition with high recognition rate is still a challenging task and usually accomplished in three phases consisting of face detection, feature extraction, and expression classification. Precise and strong location of trait point is a complicated and difficult issue in face recognition. Cootes proposed a Multi Resolution Active Shape Models (ASM) algorithm, which could extract specified shape accurately and efficiently. Furthermore, as the improvement of ASM, Active Appearance Models algorithm (AAM) is proposed to extracts both shape and texture of specified object simultaneously. In this paper we give more details about the two algorithms and give the results of experiments, testing their performance on one dataset of faces. We found that the ASM is faster and gains more accurate trait point location than the AAM, but the AAM gains a better match to the texture.

Online graphic symbol recognition using neural network and ARG matching

NASA Astrophysics Data System (ADS)

Yang, Bing; Li, Changhua; Xie, Weixing

2001-09-01

This paper proposes a novel method for on-line recognition of line-based graphic symbol. The input strokes are usually warped into a cursive form due to the sundry drawing style, and classifying them is very difficult. To deal with this, an ART-2 neural network is used to classify the input strokes. It has the advantages of high recognition rate, less recognition time and forming classes in a self-organized manner. The symbol recognition is achieved by an Attribute Relational Graph (ARG) matching algorithm. The ARG is very efficient for representing complex objects, but computation cost is very high. To over come this, we suggest a fast graph matching algorithm using symbol structure information. The experimental results show that the proposed method is effective for recognition of symbols with hierarchical structure.

Image-algebraic design of multispectral target recognition algorithms

NASA Astrophysics Data System (ADS)

Schmalz, Mark S.; Ritter, Gerhard X.

1994-06-01

In this paper, we discuss methods for multispectral ATR (Automated Target Recognition) of small targets that are sensed under suboptimal conditions, such as haze, smoke, and low light levels. In particular, we discuss our ongoing development of algorithms and software that effect intelligent object recognition by selecting ATR filter parameters according to ambient conditions. Our algorithms are expressed in terms of IA (image algebra), a concise, rigorous notation that unifies linear and nonlinear mathematics in the image processing domain. IA has been implemented on a variety of parallel computers, with preprocessors available for the Ada and FORTRAN languages. An image algebra C++ class library has recently been made available. Thus, our algorithms are both feasible implementationally and portable to numerous machines. Analyses emphasize the aspects of image algebra that aid the design of multispectral vision algorithms, such as parameterized templates that facilitate the flexible specification of ATR filters.

Digital and optical shape representation and pattern recognition; Proceedings of the Meeting, Orlando, FL, Apr. 4-6, 1988

NASA Technical Reports Server (NTRS)

Juday, Richard D. (Editor)

1988-01-01

The present conference discusses topics in pattern-recognition correlator architectures, digital stereo systems, geometric image transformations and their applications, topics in pattern recognition, filter algorithms, object detection and classification, shape representation techniques, and model-based object recognition methods. Attention is given to edge-enhancement preprocessing using liquid crystal TVs, massively-parallel optical data base management, three-dimensional sensing with polar exponential sensor arrays, the optical processing of imaging spectrometer data, hybrid associative memories and metric data models, the representation of shape primitives in neural networks, and the Monte Carlo estimation of moment invariants for pattern recognition.

Creating objects and object categories for studying perception and perceptual learning.

PubMed

Hauffen, Karin; Bart, Eugene; Brady, Mark; Kersten, Daniel; Hegdé, Jay

2012-11-02

In order to quantitatively study object perception, be it perception by biological systems or by machines, one needs to create objects and object categories with precisely definable, preferably naturalistic, properties. Furthermore, for studies on perceptual learning, it is useful to create novel objects and object categories (or object classes) with such properties. Many innovative and useful methods currently exist for creating novel objects and object categories (also see refs. 7,8). However, generally speaking, the existing methods have three broad types of shortcomings. First, shape variations are generally imposed by the experimenter, and may therefore be different from the variability in natural categories, and optimized for a particular recognition algorithm. It would be desirable to have the variations arise independently of the externally imposed constraints. Second, the existing methods have difficulty capturing the shape complexity of natural objects. If the goal is to study natural object perception, it is desirable for objects and object categories to be naturalistic, so as to avoid possible confounds and special cases. Third, it is generally hard to quantitatively measure the available information in the stimuli created by conventional methods. It would be desirable to create objects and object categories where the available information can be precisely measured and, where necessary, systematically manipulated (or 'tuned'). This allows one to formulate the underlying object recognition tasks in quantitative terms. Here we describe a set of algorithms, or methods, that meet all three of the above criteria. Virtual morphogenesis (VM) creates novel, naturalistic virtual 3-D objects called 'digital embryos' by simulating the biological process of embryogenesis. Virtual phylogenesis (VP) creates novel, naturalistic object categories by simulating the evolutionary process of natural selection. Objects and object categories created by these simulations can be further manipulated by various morphing methods to generate systematic variations of shape characteristics. The VP and morphing methods can also be applied, in principle, to novel virtual objects other than digital embryos, or to virtual versions of real-world objects. Virtual objects created in this fashion can be rendered as visual images using a conventional graphical toolkit, with desired manipulations of surface texture, illumination, size, viewpoint and background. The virtual objects can also be 'printed' as haptic objects using a conventional 3-D prototyper. We also describe some implementations of these computational algorithms to help illustrate the potential utility of the algorithms. It is important to distinguish the algorithms from their implementations. The implementations are demonstrations offered solely as a 'proof of principle' of the underlying algorithms. It is important to note that, in general, an implementation of a computational algorithm often has limitations that the algorithm itself does not have. Together, these methods represent a set of powerful and flexible tools for studying object recognition and perceptual learning by biological and computational systems alike. With appropriate extensions, these methods may also prove useful in the study of morphogenesis and phylogenesis.

A biologically inspired neural network model to transformation invariant object recognition

NASA Astrophysics Data System (ADS)

Iftekharuddin, Khan M.; Li, Yaqin; Siddiqui, Faraz

2007-09-01

Transformation invariant image recognition has been an active research area due to its widespread applications in a variety of fields such as military operations, robotics, medical practices, geographic scene analysis, and many others. The primary goal for this research is detection of objects in the presence of image transformations such as changes in resolution, rotation, translation, scale and occlusion. We investigate a biologically-inspired neural network (NN) model for such transformation-invariant object recognition. In a classical training-testing setup for NN, the performance is largely dependent on the range of transformation or orientation involved in training. However, an even more serious dilemma is that there may not be enough training data available for successful learning or even no training data at all. To alleviate this problem, a biologically inspired reinforcement learning (RL) approach is proposed. In this paper, the RL approach is explored for object recognition with different types of transformations such as changes in scale, size, resolution and rotation. The RL is implemented in an adaptive critic design (ACD) framework, which approximates the neuro-dynamic programming of an action network and a critic network, respectively. Two ACD algorithms such as Heuristic Dynamic Programming (HDP) and Dual Heuristic dynamic Programming (DHP) are investigated to obtain transformation invariant object recognition. The two learning algorithms are evaluated statistically using simulated transformations in images as well as with a large-scale UMIST face database with pose variations. In the face database authentication case, the 90° out-of-plane rotation of faces from 20 different subjects in the UMIST database is used. Our simulations show promising results for both designs for transformation-invariant object recognition and authentication of faces. Comparing the two algorithms, DHP outperforms HDP in learning capability, as DHP takes fewer steps to perform a successful recognition task in general. Further, the residual critic error in DHP is generally smaller than that of HDP, and DHP achieves a 100% success rate more frequently than HDP for individual objects/subjects. On the other hand, HDP is more robust than the DHP as far as success rate across the database is concerned when applied in a stochastic and uncertain environment, and the computational time involved in DHP is more.

Stereo vision with distance and gradient recognition

NASA Astrophysics Data System (ADS)

Kim, Soo-Hyun; Kang, Suk-Bum; Yang, Tae-Kyu

2007-12-01

Robot vision technology is needed for the stable walking, object recognition and the movement to the target spot. By some sensors which use infrared rays and ultrasonic, robot can overcome the urgent state or dangerous time. But stereo vision of three dimensional space would make robot have powerful artificial intelligence. In this paper we consider about the stereo vision for stable and correct movement of a biped robot. When a robot confront with an inclination plane or steps, particular algorithms are needed to go on without failure. This study developed the recognition algorithm of distance and gradient of environment by stereo matching process.

Label consistent K-SVD: learning a discriminative dictionary for recognition.

PubMed

Jiang, Zhuolin; Lin, Zhe; Davis, Larry S

2013-11-01

A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse codes during the dictionary learning process. More specifically, we introduce a new label consistency constraint called "discriminative sparse-code error" and combine it with the reconstruction error and the classification error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. Our algorithm learns a single overcomplete dictionary and an optimal linear classifier jointly. The incremental dictionary learning algorithm is presented for the situation of limited memory resources. It yields dictionaries so that feature points with the same class labels have similar sparse codes. Experimental results demonstrate that our algorithm outperforms many recently proposed sparse-coding techniques for face, action, scene, and object category recognition under the same learning conditions.

Integrated approach for automatic target recognition using a network of collaborative sensors.

PubMed

Mahalanobis, Abhijit; Van Nevel, Alan

2006-10-01

We introduce what is believed to be a novel concept by which several sensors with automatic target recognition (ATR) capability collaborate to recognize objects. Such an approach would be suitable for netted systems in which the sensors and platforms can coordinate to optimize end-to-end performance. We use correlation filtering techniques to facilitate the development of the concept, although other ATR algorithms may be easily substituted. Essentially, a self-configuring geometry of netted platforms is proposed that positions the sensors optimally with respect to each other, and takes into account the interactions among the sensor, the recognition algorithms, and the classes of the objects to be recognized. We show how such a paradigm optimizes overall performance, and illustrate the collaborative ATR scheme for recognizing targets in synthetic aperture radar imagery by using viewing position as a sensor parameter.

Three-dimensional model-based object recognition and segmentation in cluttered scenes.

PubMed

Mian, Ajmal S; Bennamoun, Mohammed; Owens, Robyn

2006-10-01

Viewpoint independent recognition of free-form objects and their segmentation in the presence of clutter and occlusions is a challenging task. We present a novel 3D model-based algorithm which performs this task automatically and efficiently. A 3D model of an object is automatically constructed offline from its multiple unordered range images (views). These views are converted into multidimensional table representations (which we refer to as tensors). Correspondences are automatically established between these views by simultaneously matching the tensors of a view with those of the remaining views using a hash table-based voting scheme. This results in a graph of relative transformations used to register the views before they are integrated into a seamless 3D model. These models and their tensor representations constitute the model library. During online recognition, a tensor from the scene is simultaneously matched with those in the library by casting votes. Similarity measures are calculated for the model tensors which receive the most votes. The model with the highest similarity is transformed to the scene and, if it aligns accurately with an object in the scene, that object is declared as recognized and is segmented. This process is repeated until the scene is completely segmented. Experiments were performed on real and synthetic data comprised of 55 models and 610 scenes and an overall recognition rate of 95 percent was achieved. Comparison with the spin images revealed that our algorithm is superior in terms of recognition rate and efficiency.

A hybrid flower pollination algorithm based modified randomized location for multi-threshold medical image segmentation.

PubMed

Wang, Rui; Zhou, Yongquan; Zhao, Chengyan; Wu, Haizhou

2015-01-01

Multi-threshold image segmentation is a powerful image processing technique that is used for the preprocessing of pattern recognition and computer vision. However, traditional multilevel thresholding methods are computationally expensive because they involve exhaustively searching the optimal thresholds to optimize the objective functions. To overcome this drawback, this paper proposes a flower pollination algorithm with a randomized location modification. The proposed algorithm is used to find optimal threshold values for maximizing Otsu's objective functions with regard to eight medical grayscale images. When benchmarked against other state-of-the-art evolutionary algorithms, the new algorithm proves itself to be robust and effective through numerical experimental results including Otsu's objective values and standard deviations.

A 2D range Hausdorff approach to 3D facial recognition.

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

Koch, Mark William; Russ, Trina Denise; Little, Charles Quentin

2004-11-01

This paper presents a 3D facial recognition algorithm based on the Hausdorff distance metric. The standard 3D formulation of the Hausdorff matching algorithm has been modified to operate on a 2D range image, enabling a reduction in computation from O(N2) to O(N) without large storage requirements. The Hausdorff distance is known for its robustness to data outliers and inconsistent data between two data sets, making it a suitable choice for dealing with the inherent problems in many 3D datasets due to sensor noise and object self-occlusion. For optimal performance, the algorithm assumes a good initial alignment between probe and templatemore » datasets. However, to minimize the error between two faces, the alignment can be iteratively refined. Results from the algorithm are presented using 3D face images from the Face Recognition Grand Challenge database version 1.0.« less

A new method of edge detection for object recognition

USGS Publications Warehouse

Maddox, Brian G.; Rhew, Benjamin

2004-01-01

Traditional edge detection systems function by returning every edge in an input image. This can result in a large amount of clutter and make certain vectorization algorithms less accurate. Accuracy problems can then have a large impact on automated object recognition systems that depend on edge information. A new method of directed edge detection can be used to limit the number of edges returned based on a particular feature. This results in a cleaner image that is easier for vectorization. Vectorized edges from this process could then feed an object recognition system where the edge data would also contain information as to what type of feature it bordered.

Dilated contour extraction and component labeling algorithm for object vector representation

NASA Astrophysics Data System (ADS)

Skourikhine, Alexei N.

2005-08-01

Object boundary extraction from binary images is important for many applications, e.g., image vectorization, automatic interpretation of images containing segmentation results, printed and handwritten documents and drawings, maps, and AutoCAD drawings. Efficient and reliable contour extraction is also important for pattern recognition due to its impact on shape-based object characterization and recognition. The presented contour tracing and component labeling algorithm produces dilated (sub-pixel) contours associated with corresponding regions. The algorithm has the following features: (1) it always produces non-intersecting, non-degenerate contours, including the case of one-pixel wide objects; (2) it associates the outer and inner (i.e., around hole) contours with the corresponding regions during the process of contour tracing in a single pass over the image; (3) it maintains desired connectivity of object regions as specified by 8-neighbor or 4-neighbor connectivity of adjacent pixels; (4) it avoids degenerate regions in both background and foreground; (5) it allows an easy augmentation that will provide information about the containment relations among regions; (6) it has a time complexity that is dominantly linear in the number of contour points. This early component labeling (contour-region association) enables subsequent efficient object-based processing of the image information.

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

PubMed Central

Hauffen, Karin; Bart, Eugene; Brady, Mark; Kersten, Daniel; Hegdé, Jay

2012-01-01

In order to quantitatively study object perception, be it perception by biological systems or by machines, one needs to create objects and object categories with precisely definable, preferably naturalistic, properties1. Furthermore, for studies on perceptual learning, it is useful to create novel objects and object categories (or object classes) with such properties2. Many innovative and useful methods currently exist for creating novel objects and object categories3-6 (also see refs. 7,8). However, generally speaking, the existing methods have three broad types of shortcomings. First, shape variations are generally imposed by the experimenter5,9,10, and may therefore be different from the variability in natural categories, and optimized for a particular recognition algorithm. It would be desirable to have the variations arise independently of the externally imposed constraints. Second, the existing methods have difficulty capturing the shape complexity of natural objects11-13. If the goal is to study natural object perception, it is desirable for objects and object categories to be naturalistic, so as to avoid possible confounds and special cases. Third, it is generally hard to quantitatively measure the available information in the stimuli created by conventional methods. It would be desirable to create objects and object categories where the available information can be precisely measured and, where necessary, systematically manipulated (or 'tuned'). This allows one to formulate the underlying object recognition tasks in quantitative terms. Here we describe a set of algorithms, or methods, that meet all three of the above criteria. Virtual morphogenesis (VM) creates novel, naturalistic virtual 3-D objects called 'digital embryos' by simulating the biological process of embryogenesis14. Virtual phylogenesis (VP) creates novel, naturalistic object categories by simulating the evolutionary process of natural selection9,12,13. Objects and object categories created by these simulations can be further manipulated by various morphing methods to generate systematic variations of shape characteristics15,16. The VP and morphing methods can also be applied, in principle, to novel virtual objects other than digital embryos, or to virtual versions of real-world objects9,13. Virtual objects created in this fashion can be rendered as visual images using a conventional graphical toolkit, with desired manipulations of surface texture, illumination, size, viewpoint and background. The virtual objects can also be 'printed' as haptic objects using a conventional 3-D prototyper. We also describe some implementations of these computational algorithms to help illustrate the potential utility of the algorithms. It is important to distinguish the algorithms from their implementations. The implementations are demonstrations offered solely as a 'proof of principle' of the underlying algorithms. It is important to note that, in general, an implementation of a computational algorithm often has limitations that the algorithm itself does not have. Together, these methods represent a set of powerful and flexible tools for studying object recognition and perceptual learning by biological and computational systems alike. With appropriate extensions, these methods may also prove useful in the study of morphogenesis and phylogenesis. PMID:23149420

Constrained Metric Learning by Permutation Inducing Isometries.

PubMed

Bosveld, Joel; Mahmood, Arif; Huynh, Du Q; Noakes, Lyle

2016-01-01

The choice of metric critically affects the performance of classification and clustering algorithms. Metric learning algorithms attempt to improve performance, by learning a more appropriate metric. Unfortunately, most of the current algorithms learn a distance function which is not invariant to rigid transformations of images. Therefore, the distances between two images and their rigidly transformed pair may differ, leading to inconsistent classification or clustering results. We propose to constrain the learned metric to be invariant to the geometry preserving transformations of images that induce permutations in the feature space. The constraint that these transformations are isometries of the metric ensures consistent results and improves accuracy. Our second contribution is a dimension reduction technique that is consistent with the isometry constraints. Our third contribution is the formulation of the isometry constrained logistic discriminant metric learning (IC-LDML) algorithm, by incorporating the isometry constraints within the objective function of the LDML algorithm. The proposed algorithm is compared with the existing techniques on the publicly available labeled faces in the wild, viewpoint-invariant pedestrian recognition, and Toy Cars data sets. The IC-LDML algorithm has outperformed existing techniques for the tasks of face recognition, person identification, and object classification by a significant margin.

Automatic voice recognition using traditional and artificial neural network approaches

NASA Technical Reports Server (NTRS)

Botros, Nazeih M.

1989-01-01

The main objective of this research is to develop an algorithm for isolated-word recognition. This research is focused on digital signal analysis rather than linguistic analysis of speech. Features extraction is carried out by applying a Linear Predictive Coding (LPC) algorithm with order of 10. Continuous-word and speaker independent recognition will be considered in future study after accomplishing this isolated word research. To examine the similarity between the reference and the training sets, two approaches are explored. The first is implementing traditional pattern recognition techniques where a dynamic time warping algorithm is applied to align the two sets and calculate the probability of matching by measuring the Euclidean distance between the two sets. The second is implementing a backpropagation artificial neural net model with three layers as the pattern classifier. The adaptation rule implemented in this network is the generalized least mean square (LMS) rule. The first approach has been accomplished. A vocabulary of 50 words was selected and tested. The accuracy of the algorithm was found to be around 85 percent. The second approach is in progress at the present time.

Toward open set recognition.

PubMed

Scheirer, Walter J; de Rezende Rocha, Anderson; Sapkota, Archana; Boult, Terrance E

2013-07-01

To date, almost all experimental evaluations of machine learning-based recognition algorithms in computer vision have taken the form of "closed set" recognition, whereby all testing classes are known at training time. A more realistic scenario for vision applications is "open set" recognition, where incomplete knowledge of the world is present at training time, and unknown classes can be submitted to an algorithm during testing. This paper explores the nature of open set recognition and formalizes its definition as a constrained minimization problem. The open set recognition problem is not well addressed by existing algorithms because it requires strong generalization. As a step toward a solution, we introduce a novel "1-vs-set machine," which sculpts a decision space from the marginal distances of a 1-class or binary SVM with a linear kernel. This methodology applies to several different applications in computer vision where open set recognition is a challenging problem, including object recognition and face verification. We consider both in this work, with large scale cross-dataset experiments performed over the Caltech 256 and ImageNet sets, as well as face matching experiments performed over the Labeled Faces in the Wild set. The experiments highlight the effectiveness of machines adapted for open set evaluation compared to existing 1-class and binary SVMs for the same tasks.

Image-based automatic recognition of larvae

NASA Astrophysics Data System (ADS)

Sang, Ru; Yu, Guiying; Fan, Weijun; Guo, Tiantai

2010-08-01

As the main objects, imagoes have been researched in quarantine pest recognition in these days. However, pests in their larval stage are latent, and the larvae spread abroad much easily with the circulation of agricultural and forest products. It is presented in this paper that, as the new research objects, larvae are recognized by means of machine vision, image processing and pattern recognition. More visional information is reserved and the recognition rate is improved as color image segmentation is applied to images of larvae. Along with the characteristics of affine invariance, perspective invariance and brightness invariance, scale invariant feature transform (SIFT) is adopted for the feature extraction. The neural network algorithm is utilized for pattern recognition, and the automatic identification of larvae images is successfully achieved with satisfactory results.

Body-wide hierarchical fuzzy modeling, recognition, and delineation of anatomy in medical images.

PubMed

Udupa, Jayaram K; Odhner, Dewey; Zhao, Liming; Tong, Yubing; Matsumoto, Monica M S; Ciesielski, Krzysztof C; Falcao, Alexandre X; Vaideeswaran, Pavithra; Ciesielski, Victoria; Saboury, Babak; Mohammadianrasanani, Syedmehrdad; Sin, Sanghun; Arens, Raanan; Torigian, Drew A

2014-07-01

To make Quantitative Radiology (QR) a reality in radiological practice, computerized body-wide Automatic Anatomy Recognition (AAR) becomes essential. With the goal of building a general AAR system that is not tied to any specific organ system, body region, or image modality, this paper presents an AAR methodology for localizing and delineating all major organs in different body regions based on fuzzy modeling ideas and a tight integration of fuzzy models with an Iterative Relative Fuzzy Connectedness (IRFC) delineation algorithm. The methodology consists of five main steps: (a) gathering image data for both building models and testing the AAR algorithms from patient image sets existing in our health system; (b) formulating precise definitions of each body region and organ and delineating them following these definitions; (c) building hierarchical fuzzy anatomy models of organs for each body region; (d) recognizing and locating organs in given images by employing the hierarchical models; and (e) delineating the organs following the hierarchy. In Step (c), we explicitly encode object size and positional relationships into the hierarchy and subsequently exploit this information in object recognition in Step (d) and delineation in Step (e). Modality-independent and dependent aspects are carefully separated in model encoding. At the model building stage, a learning process is carried out for rehearsing an optimal threshold-based object recognition method. The recognition process in Step (d) starts from large, well-defined objects and proceeds down the hierarchy in a global to local manner. A fuzzy model-based version of the IRFC algorithm is created by naturally integrating the fuzzy model constraints into the delineation algorithm. The AAR system is tested on three body regions - thorax (on CT), abdomen (on CT and MRI), and neck (on MRI and CT) - involving a total of over 35 organs and 130 data sets (the total used for model building and testing). The training and testing data sets are divided into equal size in all cases except for the neck. Overall the AAR method achieves a mean accuracy of about 2 voxels in localizing non-sparse blob-like objects and most sparse tubular objects. The delineation accuracy in terms of mean false positive and negative volume fractions is 2% and 8%, respectively, for non-sparse objects, and 5% and 15%, respectively, for sparse objects. The two object groups achieve mean boundary distance relative to ground truth of 0.9 and 1.5 voxels, respectively. Some sparse objects - venous system (in the thorax on CT), inferior vena cava (in the abdomen on CT), and mandible and naso-pharynx (in neck on MRI, but not on CT) - pose challenges at all levels, leading to poor recognition and/or delineation results. The AAR method fares quite favorably when compared with methods from the recent literature for liver, kidneys, and spleen on CT images. We conclude that separation of modality-independent from dependent aspects, organization of objects in a hierarchy, encoding of object relationship information explicitly into the hierarchy, optimal threshold-based recognition learning, and fuzzy model-based IRFC are effective concepts which allowed us to demonstrate the feasibility of a general AAR system that works in different body regions on a variety of organs and on different modalities. Copyright © 2014 Elsevier B.V. All rights reserved.

Target recognition based on convolutional neural network

NASA Astrophysics Data System (ADS)

Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

2017-11-01

One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

Indonesian Sign Language Number Recognition using SIFT Algorithm

NASA Astrophysics Data System (ADS)

Mahfudi, Isa; Sarosa, Moechammad; Andrie Asmara, Rosa; Azrino Gustalika, M.

2018-04-01

Indonesian sign language (ISL) is generally used for deaf individuals and poor people communication in communicating. They use sign language as their primary language which consists of 2 types of action: sign and finger spelling. However, not all people understand their sign language so that this becomes a problem for them to communicate with normal people. this problem also becomes a factor they are isolated feel from the social life. It needs a solution that can help them to be able to interacting with normal people. Many research that offers a variety of methods in solving the problem of sign language recognition based on image processing. SIFT (Scale Invariant Feature Transform) algorithm is one of the methods that can be used to identify an object. SIFT is claimed very resistant to scaling, rotation, illumination and noise. Using SIFT algorithm for Indonesian sign language recognition number result rate recognition to 82% with the use of a total of 100 samples image dataset consisting 50 sample for training data and 50 sample images for testing data. Change threshold value get affect the result of the recognition. The best value threshold is 0.45 with rate recognition of 94%.

Object-oriented recognition of high-resolution remote sensing image

NASA Astrophysics Data System (ADS)

Wang, Yongyan; Li, Haitao; Chen, Hong; Xu, Yuannan

2016-01-01

With the development of remote sensing imaging technology and the improvement of multi-source image's resolution in satellite visible light, multi-spectral and hyper spectral , the high resolution remote sensing image has been widely used in various fields, for example military field, surveying and mapping, geophysical prospecting, environment and so forth. In remote sensing image, the segmentation of ground targets, feature extraction and the technology of automatic recognition are the hotspot and difficulty in the research of modern information technology. This paper also presents an object-oriented remote sensing image scene classification method. The method is consist of vehicles typical objects classification generation, nonparametric density estimation theory, mean shift segmentation theory, multi-scale corner detection algorithm, local shape matching algorithm based on template. Remote sensing vehicles image classification software system is designed and implemented to meet the requirements .

A novel rotational invariants target recognition method for rotating motion blurred images

NASA Astrophysics Data System (ADS)

Lan, Jinhui; Gong, Meiling; Dong, Mingwei; Zeng, Yiliang; Zhang, Yuzhen

2017-11-01

The imaging of the image sensor is blurred due to the rotational motion of the carrier and reducing the target recognition rate greatly. Although the traditional mode that restores the image first and then identifies the target can improve the recognition rate, it takes a long time to recognize. In order to solve this problem, a rotating fuzzy invariants extracted model was constructed that recognizes target directly. The model includes three metric layers. The object description capability of metric algorithms that contain gray value statistical algorithm, improved round projection transformation algorithm and rotation-convolution moment invariants in the three metric layers ranges from low to high, and the metric layer with the lowest description ability among them is as the input which can eliminate non pixel points of target region from degenerate image gradually. Experimental results show that the proposed model can improve the correct target recognition rate of blurred image and optimum allocation between the computational complexity and function of region.

Electro-Optic Identification (EOID) Research Program

DTIC Science & Technology

2002-09-30

The goal of this research is to provide computer-assisted identification of underwater mines in electro - optic imagery. Identification algorithms will...greatly reduce the time and risk to reacquire mine-like-objects for positive classification and identification. The objectives are to collect electro ... optic data under a wide range of operating and environmental conditions and develop precise algorithms that can provide accurate target recognition on this data for all possible conditions.

Motion-seeded object-based attention for dynamic visual imagery

NASA Astrophysics Data System (ADS)

Huber, David J.; Khosla, Deepak; Kim, Kyungnam

2017-05-01

This paper† describes a novel system that finds and segments "objects of interest" from dynamic imagery (video) that (1) processes each frame using an advanced motion algorithm that pulls out regions that exhibit anomalous motion, and (2) extracts the boundary of each object of interest using a biologically-inspired segmentation algorithm based on feature contours. The system uses a series of modular, parallel algorithms, which allows many complicated operations to be carried out by the system in a very short time, and can be used as a front-end to a larger system that includes object recognition and scene understanding modules. Using this method, we show 90% accuracy with fewer than 0.1 false positives per frame of video, which represents a significant improvement over detection using a baseline attention algorithm.

Two-dimensional shape recognition using oriented-polar representation

NASA Astrophysics Data System (ADS)

Hu, Neng-Chung; Yu, Kuo-Kan; Hsu, Yung-Li

1997-10-01

To deal with such a problem as object recognition of position, scale, and rotation invariance (PSRI), we utilize some PSRI properties of images obtained from objects, for example, the centroid of the image. The corresponding position of the centroid to the boundary of the image is invariant in spite of rotation, scale, and translation of the image. To obtain the information of the image, we use the technique similar to Radon transform, called the oriented-polar representation of a 2D image. In this representation, two specific points, the centroid and the weighted mean point, are selected to form an initial ray, then the image is sampled with N angularly equispaced rays departing from the initial rays. Each ray contains a number of intersections and the distance information obtained from the centroid to the intersections. The shape recognition algorithm is based on the least total error of these two items of information. Together with a simple noise removal and a typical backpropagation neural network, this algorithm is simple, but the PSRI is achieved with a high recognition rate.

Classifying performance impairment in response to sleep loss using pattern recognition algorithms on single session testing

PubMed Central

St. Hilaire, Melissa A.; Sullivan, Jason P.; Anderson, Clare; Cohen, Daniel A.; Barger, Laura K.; Lockley, Steven W.; Klerman, Elizabeth B.

2012-01-01

There is currently no “gold standard” marker of cognitive performance impairment resulting from sleep loss. We utilized pattern recognition algorithms to determine which features of data collected under controlled laboratory conditions could most reliably identify cognitive performance impairment in response to sleep loss using data from only one testing session, such as would occur in the “real world” or field conditions. A training set for testing the pattern recognition algorithms was developed using objective Psychomotor Vigilance Task (PVT) and subjective Karolinska Sleepiness Scale (KSS) data collected from laboratory studies during which subjects were sleep deprived for 26 – 52 hours. The algorithm was then tested in data from both laboratory and field experiments. The pattern recognition algorithm was able to identify performance impairment with a single testing session in individuals studied under laboratory conditions using PVT, KSS, length of time awake and time of day information with sensitivity and specificity as high as 82%. When this algorithm was tested on data collected under real-world conditions from individuals whose data were not in the training set, accuracy of predictions for individuals categorized with low performance impairment were as high as 98%. Predictions for medium and severe performance impairment were less accurate. We conclude that pattern recognition algorithms may be a promising method for identifying performance impairment in individuals using only current information about the individual’s behavior. Single testing features (e.g., number of PVT lapses) with high correlation with performance impairment in the laboratory setting may not be the best indicators of performance impairment under real-world conditions. Pattern recognition algorithms should be further tested for their ability to be used in conjunction with other assessments of sleepiness in real-world conditions to quantify performance impairment in response to sleep loss. PMID:22959616

Wheezing recognition algorithm using recordings of respiratory sounds at the mouth in a pediatric population.

PubMed

Bokov, Plamen; Mahut, Bruno; Flaud, Patrice; Delclaux, Christophe

2016-03-01

Respiratory diseases in children are a common reason for physician visits. A diagnostic difficulty arises when parents hear wheezing that is no longer present during the medical consultation. Thus, an outpatient objective tool for recognition of wheezing is of clinical value. We developed a wheezing recognition algorithm from recorded respiratory sounds with a Smartphone placed near the mouth. A total of 186 recordings were obtained in a pediatric emergency department, mostly in toddlers (mean age 20 months). After exclusion of recordings with artefacts and those with a single clinical operator auscultation, 95 recordings with the agreement of two operators on auscultation diagnosis (27 with wheezing and 68 without) were subjected to a two phase algorithm (signal analysis and pattern classifier using machine learning algorithms) to classify records. The best performance (71.4% sensitivity and 88.9% specificity) was observed with a Support Vector Machine-based algorithm. We further tested the algorithm over a set of 39 recordings having a single operator and found a fair agreement (kappa=0.28, CI95% [0.12, 0.45]) between the algorithm and the operator. The main advantage of such an algorithm is its use in contact-free sound recording, thus valuable in the pediatric population. Copyright © 2016 Elsevier Ltd. All rights reserved.

Using pattern recognition to automatically localize reflection hyperbolas in data from ground penetrating radar

NASA Astrophysics Data System (ADS)

Maas, Christian; Schmalzl, Jörg

2013-08-01

Ground Penetrating Radar (GPR) is used for the localization of supply lines, land mines, pipes and many other buried objects. These objects can be recognized in the recorded data as reflection hyperbolas with a typical shape depending on depth and material of the object and the surrounding material. To obtain the parameters, the shape of the hyperbola has to be fitted. In the last years several methods were developed to automate this task during post-processing. In this paper we show another approach for the automated localization of reflection hyperbolas in GPR data by solving a pattern recognition problem in grayscale images. In contrast to other methods our detection program is also able to immediately mark potential objects in real-time. For this task we use a version of the Viola-Jones learning algorithm, which is part of the open source library "OpenCV". This algorithm was initially developed for face recognition, but can be adapted to any other simple shape. In our program it is used to narrow down the location of reflection hyperbolas to certain areas in the GPR data. In order to extract the exact location and the velocity of the hyperbolas we apply a simple Hough Transform for hyperbolas. Because the Viola-Jones Algorithm reduces the input for the computational expensive Hough Transform dramatically the detection system can also be implemented on normal field computers, so on-site application is possible. The developed detection system shows promising results and detection rates in unprocessed radargrams. In order to improve the detection results and apply the program to noisy radar images more data of different GPR systems as input for the learning algorithm is necessary.

Component Pin Recognition Using Algorithms Based on Machine Learning

NASA Astrophysics Data System (ADS)

Xiao, Yang; Hu, Hong; Liu, Ze; Xu, Jiangchang

2018-04-01

The purpose of machine vision for a plug-in machine is to improve the machine’s stability and accuracy, and recognition of the component pin is an important part of the vision. This paper focuses on component pin recognition using three different techniques. The first technique involves traditional image processing using the core algorithm for binary large object (BLOB) analysis. The second technique uses the histogram of oriented gradients (HOG), to experimentally compare the effect of the support vector machine (SVM) and the adaptive boosting machine (AdaBoost) learning meta-algorithm classifiers. The third technique is the use of an in-depth learning method known as convolution neural network (CNN), which involves identifying the pin by comparing a sample to its training. The main purpose of the research presented in this paper is to increase the knowledge of learning methods used in the plug-in machine industry in order to achieve better results.

Object recognition and pose estimation of planar objects from range data

NASA Technical Reports Server (NTRS)

Pendleton, Thomas W.; Chien, Chiun Hong; Littlefield, Mark L.; Magee, Michael

1994-01-01

The Extravehicular Activity Helper/Retriever (EVAHR) is a robotic device currently under development at the NASA Johnson Space Center that is designed to fetch objects or to assist in retrieving an astronaut who may have become inadvertently de-tethered. The EVAHR will be required to exhibit a high degree of intelligent autonomous operation and will base much of its reasoning upon information obtained from one or more three-dimensional sensors that it will carry and control. At the highest level of visual cognition and reasoning, the EVAHR will be required to detect objects, recognize them, and estimate their spatial orientation and location. The recognition phase and estimation of spatial pose will depend on the ability of the vision system to reliably extract geometric features of the objects such as whether the surface topologies observed are planar or curved and the spatial relationships between the component surfaces. In order to achieve these tasks, three-dimensional sensing of the operational environment and objects in the environment will therefore be essential. One of the sensors being considered to provide image data for object recognition and pose estimation is a phase-shift laser scanner. The characteristics of the data provided by this scanner have been studied and algorithms have been developed for segmenting range images into planar surfaces, extracting basic features such as surface area, and recognizing the object based on the characteristics of extracted features. Also, an approach has been developed for estimating the spatial orientation and location of the recognized object based on orientations of extracted planes and their intersection points. This paper presents some of the algorithms that have been developed for the purpose of recognizing and estimating the pose of objects as viewed by the laser scanner, and characterizes the desirability and utility of these algorithms within the context of the scanner itself, considering data quality and noise.

Recognition of 3-D Scene with Partially Occluded Objects

NASA Astrophysics Data System (ADS)

Lu, Siwei; Wong, Andrew K. C...

1987-03-01

This paper presents a robot vision system which is capable of recognizing objects in a 3-D scene and interpreting their spatial relation even though some objects in the scene may be partially occluded by other objects. An algorithm is developed to transform the geometric information from the range data into an attributed hypergraph representation (AHR). A hypergraph monomorphism algorithm is then used to compare the AHR of objects in the scene with a set of complete AHR's of prototypes. The capability of identifying connected components and interpreting various types of edges in the 3-D scene enables us to distinguish objects which are partially blocking each other in the scene. Using structural information stored in the primitive area graph, a heuristic hypergraph monomorphism algorithm provides an effective way for recognizing, locating, and interpreting partially occluded objects in the range image.

Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments.

PubMed

Tian, Yingli; Yang, Xiaodong; Yi, Chucai; Arditi, Aries

2013-04-01

Independent travel is a well known challenge for blind and visually impaired persons. In this paper, we propose a proof-of-concept computer vision-based wayfinding aid for blind people to independently access unfamiliar indoor environments. In order to find different rooms (e.g. an office, a lab, or a bathroom) and other building amenities (e.g. an exit or an elevator), we incorporate object detection with text recognition. First we develop a robust and efficient algorithm to detect doors, elevators, and cabinets based on their general geometric shape, by combining edges and corners. The algorithm is general enough to handle large intra-class variations of objects with different appearances among different indoor environments, as well as small inter-class differences between different objects such as doors and door-like cabinets. Next, in order to distinguish intra-class objects (e.g. an office door from a bathroom door), we extract and recognize text information associated with the detected objects. For text recognition, we first extract text regions from signs with multiple colors and possibly complex backgrounds, and then apply character localization and topological analysis to filter out background interference. The extracted text is recognized using off-the-shelf optical character recognition (OCR) software products. The object type, orientation, location, and text information are presented to the blind traveler as speech.

Toward a Computer Vision-based Wayfinding Aid for Blind Persons to Access Unfamiliar Indoor Environments

PubMed Central

Tian, YingLi; Yang, Xiaodong; Yi, Chucai; Arditi, Aries

2012-01-01

Independent travel is a well known challenge for blind and visually impaired persons. In this paper, we propose a proof-of-concept computer vision-based wayfinding aid for blind people to independently access unfamiliar indoor environments. In order to find different rooms (e.g. an office, a lab, or a bathroom) and other building amenities (e.g. an exit or an elevator), we incorporate object detection with text recognition. First we develop a robust and efficient algorithm to detect doors, elevators, and cabinets based on their general geometric shape, by combining edges and corners. The algorithm is general enough to handle large intra-class variations of objects with different appearances among different indoor environments, as well as small inter-class differences between different objects such as doors and door-like cabinets. Next, in order to distinguish intra-class objects (e.g. an office door from a bathroom door), we extract and recognize text information associated with the detected objects. For text recognition, we first extract text regions from signs with multiple colors and possibly complex backgrounds, and then apply character localization and topological analysis to filter out background interference. The extracted text is recognized using off-the-shelf optical character recognition (OCR) software products. The object type, orientation, location, and text information are presented to the blind traveler as speech. PMID:23630409

The impact of privacy protection filters on gender recognition

NASA Astrophysics Data System (ADS)

Ruchaud, Natacha; Antipov, Grigory; Korshunov, Pavel; Dugelay, Jean-Luc; Ebrahimi, Touradj; Berrani, Sid-Ahmed

2015-09-01

Deep learning-based algorithms have become increasingly efficient in recognition and detection tasks, especially when they are trained on large-scale datasets. Such recent success has led to a speculation that deep learning methods are comparable to or even outperform human visual system in its ability to detect and recognize objects and their features. In this paper, we focus on the specific task of gender recognition in images when they have been processed by privacy protection filters (e.g., blurring, masking, and pixelization) applied at different strengths. Assuming a privacy protection scenario, we compare the performance of state of the art deep learning algorithms with a subjective evaluation obtained via crowdsourcing to understand how privacy protection filters affect both machine and human vision.

Object recognition of real targets using modelled SAR images

NASA Astrophysics Data System (ADS)

Zherdev, D. A.

2017-12-01

In this work the problem of recognition is studied using SAR images. The algorithm of recognition is based on the computation of conjugation indices with vectors of class. The support subspaces for each class are constructed by exception of the most and the less correlated vectors in a class. In the study we examine the ability of a significant feature vector size reduce that leads to recognition time decrease. The images of targets form the feature vectors that are transformed using pre-trained convolutional neural network (CNN).

Identification and location of catenary insulator in complex background based on machine vision

NASA Astrophysics Data System (ADS)

Yao, Xiaotong; Pan, Yingli; Liu, Li; Cheng, Xiao

2018-04-01

It is an important premise to locate insulator precisely for fault detection. Current location algorithms for insulator under catenary checking images are not accurate, a target recognition and localization method based on binocular vision combined with SURF features is proposed. First of all, because of the location of the insulator in complex environment, using SURF features to achieve the coarse positioning of target recognition; then Using binocular vision principle to calculate the 3D coordinates of the object which has been coarsely located, realization of target object recognition and fine location; Finally, Finally, the key is to preserve the 3D coordinate of the object's center of mass, transfer to the inspection robot to control the detection position of the robot. Experimental results demonstrate that the proposed method has better recognition efficiency and accuracy, can successfully identify the target and has a define application value.

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence

PubMed Central

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-01-01

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain. PMID:27282108

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence.

PubMed

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-06-10

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.

Automated target recognition and tracking using an optical pattern recognition neural network

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin

1991-01-01

The on-going development of an automatic target recognition and tracking system at the Jet Propulsion Laboratory is presented. This system is an optical pattern recognition neural network (OPRNN) that is an integration of an innovative optical parallel processor and a feature extraction based neural net training algorithm. The parallel optical processor provides high speed and vast parallelism as well as full shift invariance. The neural network algorithm enables simultaneous discrimination of multiple noisy targets in spite of their scales, rotations, perspectives, and various deformations. This fully developed OPRNN system can be effectively utilized for the automated spacecraft recognition and tracking that will lead to success in the Automated Rendezvous and Capture (AR&C) of the unmanned Cargo Transfer Vehicle (CTV). One of the most powerful optical parallel processors for automatic target recognition is the multichannel correlator. With the inherent advantages of parallel processing capability and shift invariance, multiple objects can be simultaneously recognized and tracked using this multichannel correlator. This target tracking capability can be greatly enhanced by utilizing a powerful feature extraction based neural network training algorithm such as the neocognitron. The OPRNN, currently under investigation at JPL, is constructed with an optical multichannel correlator where holographic filters have been prepared using the neocognitron training algorithm. The computation speed of the neocognitron-type OPRNN is up to 10(exp 14) analog connections/sec that enabling the OPRNN to outperform its state-of-the-art electronics counterpart by at least two orders of magnitude.

Man-Made Object Extraction from Remote Sensing Imagery by Graph-Based Manifold Ranking

NASA Astrophysics Data System (ADS)

He, Y.; Wang, X.; Hu, X. Y.; Liu, S. H.

2018-04-01

The automatic extraction of man-made objects from remote sensing imagery is useful in many applications. This paper proposes an algorithm for extracting man-made objects automatically by integrating a graph model with the manifold ranking algorithm. Initially, we estimate a priori value of the man-made objects with the use of symmetric and contrast features. The graph model is established to represent the spatial relationships among pre-segmented superpixels, which are used as the graph nodes. Multiple characteristics, namely colour, texture and main direction, are used to compute the weights of the adjacent nodes. Manifold ranking effectively explores the relationships among all the nodes in the feature space as well as initial query assignment; thus, it is applied to generate a ranking map, which indicates the scores of the man-made objects. The man-made objects are then segmented on the basis of the ranking map. Two typical segmentation algorithms are compared with the proposed algorithm. Experimental results show that the proposed algorithm can extract man-made objects with high recognition rate and low omission rate.

Vision-based object detection and recognition system for intelligent vehicles

NASA Astrophysics Data System (ADS)

Ran, Bin; Liu, Henry X.; Martono, Wilfung

1999-01-01

Recently, a proactive crash mitigation system is proposed to enhance the crash avoidance and survivability of the Intelligent Vehicles. Accurate object detection and recognition system is a prerequisite for a proactive crash mitigation system, as system component deployment algorithms rely on accurate hazard detection, recognition, and tracking information. In this paper, we present a vision-based approach to detect and recognize vehicles and traffic signs, obtain their information, and track multiple objects by using a sequence of color images taken from a moving vehicle. The entire system consist of two sub-systems, the vehicle detection and recognition sub-system and traffic sign detection and recognition sub-system. Both of the sub- systems consist of four models: object detection model, object recognition model, object information model, and object tracking model. In order to detect potential objects on the road, several features of the objects are investigated, which include symmetrical shape and aspect ratio of a vehicle and color and shape information of the signs. A two-layer neural network is trained to recognize different types of vehicles and a parameterized traffic sign model is established in the process of recognizing a sign. Tracking is accomplished by combining the analysis of single image frame with the analysis of consecutive image frames. The analysis of the single image frame is performed every ten full-size images. The information model will obtain the information related to the object, such as time to collision for the object vehicle and relative distance from the traffic sings. Experimental results demonstrated a robust and accurate system in real time object detection and recognition over thousands of image frames.

Tactile recognition and localization using object models: the case of polyhedra on a plane.

PubMed

Gaston, P C; Lozano-Perez, T

1984-03-01

This paper discusses how data from multiple tactile sensors may be used to identify and locate one object, from among a set of known objects. We use only local information from sensors: 1) the position of contact points and 2) ranges of surface normals at the contact points. The recognition and localization process is structured as the development and pruning of a tree of consistent hypotheses about pairings between contact points and object surfaces. In this paper, we deal with polyhedral objects constrained to lie on a known plane, i.e., having three degrees of positioning freedom relative to the sensors. We illustrate the performance of the algorithm by simulation.

Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition.

PubMed

Wong, Sebastien C; Stamatescu, Victor; Gatt, Adam; Kearney, David; Lee, Ivan; McDonnell, Mark D

2017-10-01

This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or user-based track initialization. We then classify the tracked objects with a fast-learning image classifier, that is based on a shallow convolutional neural network architecture and demonstrate that object recognition improves when this is combined with object state information from the tracking algorithm. We argue that by transferring the use of prior knowledge from the detection and tracking stages to the classification stage, we can design a robust, general purpose object recognition system with the ability to detect and track a variety of object types. We describe our biologically inspired implementation, which adaptively learns the shape and motion of tracked objects, and apply it to the Neovision2 Tower benchmark data set, which contains multiple object types. An experimental evaluation demonstrates that our approach is competitive with the state-of-the-art video object recognition systems that do make use of object-specific prior knowledge in detection and tracking, while providing additional practical advantages by virtue of its generality.

Single-pixel non-imaging object recognition by means of Fourier spectrum acquisition

NASA Astrophysics Data System (ADS)

Chen, Huichao; Shi, Jianhong; Liu, Xialin; Niu, Zhouzhou; Zeng, Guihua

2018-04-01

Single-pixel imaging has emerged over recent years as a novel imaging technique, which has significant application prospects. In this paper, we propose and experimentally demonstrate a scheme that can achieve single-pixel non-imaging object recognition by acquiring the Fourier spectrum. In an experiment, a four-step phase-shifting sinusoid illumination light is used to irradiate the object image, the value of the light intensity is measured with a single-pixel detection unit, and the Fourier coefficients of the object image are obtained by a differential measurement. The Fourier coefficients are first cast into binary numbers to obtain the hash value. We propose a new method of perceptual hashing algorithm, which is combined with a discrete Fourier transform to calculate the hash value. The hash distance is obtained by calculating the difference of the hash value between the object image and the contrast images. By setting an appropriate threshold, the object image can be quickly and accurately recognized. The proposed scheme realizes single-pixel non-imaging perceptual hashing object recognition by using fewer measurements. Our result might open a new path for realizing object recognition with non-imaging.

Fuzzy support vector machines for adaptive Morse code recognition.

PubMed

Yang, Cheng-Hong; Jin, Li-Cheng; Chuang, Li-Yeh

2006-11-01

Morse code is now being harnessed for use in rehabilitation applications of augmentative-alternative communication and assistive technology, facilitating mobility, environmental control and adapted worksite access. In this paper, Morse code is selected as a communication adaptive device for persons who suffer from muscle atrophy, cerebral palsy or other severe handicaps. A stable typing rate is strictly required for Morse code to be effective as a communication tool. Therefore, an adaptive automatic recognition method with a high recognition rate is needed. The proposed system uses both fuzzy support vector machines and the variable-degree variable-step-size least-mean-square algorithm to achieve these objectives. We apply fuzzy memberships to each point, and provide different contributions to the decision learning function for support vector machines. Statistical analyses demonstrated that the proposed method elicited a higher recognition rate than other algorithms in the literature.

Activity and function recognition for moving and static objects in urban environments from wide-area persistent surveillance inputs

NASA Astrophysics Data System (ADS)

Levchuk, Georgiy; Bobick, Aaron; Jones, Eric

2010-04-01

In this paper, we describe results from experimental analysis of a model designed to recognize activities and functions of moving and static objects from low-resolution wide-area video inputs. Our model is based on representing the activities and functions using three variables: (i) time; (ii) space; and (iii) structures. The activity and function recognition is achieved by imposing lexical, syntactic, and semantic constraints on the lower-level event sequences. In the reported research, we have evaluated the utility and sensitivity of several algorithms derived from natural language processing and pattern recognition domains. We achieved high recognition accuracy for a wide range of activity and function types in the experiments using Electro-Optical (EO) imagery collected by Wide Area Airborne Surveillance (WAAS) platform.

Human recognition based on head-shoulder contour extraction and BP neural network

NASA Astrophysics Data System (ADS)

Kong, Xiao-fang; Wang, Xiu-qin; Gu, Guohua; Chen, Qian; Qian, Wei-xian

2014-11-01

In practical application scenarios like video surveillance and human-computer interaction, human body movements are uncertain because the human body is a non-rigid object. Based on the fact that the head-shoulder part of human body can be less affected by the movement, and will seldom be obscured by other objects, in human detection and recognition, a head-shoulder model with its stable characteristics can be applied as a detection feature to describe the human body. In order to extract the head-shoulder contour accurately, a head-shoulder model establish method with combination of edge detection and the mean-shift algorithm in image clustering has been proposed in this paper. First, an adaptive method of mixture Gaussian background update has been used to extract targets from the video sequence. Second, edge detection has been used to extract the contour of moving objects, and the mean-shift algorithm has been combined to cluster parts of target's contour. Third, the head-shoulder model can be established, according to the width and height ratio of human head-shoulder combined with the projection histogram of the binary image, and the eigenvectors of the head-shoulder contour can be acquired. Finally, the relationship between head-shoulder contour eigenvectors and the moving objects will be formed by the training of back-propagation (BP) neural network classifier, and the human head-shoulder model can be clustered for human detection and recognition. Experiments have shown that the method combined with edge detection and mean-shift algorithm proposed in this paper can extract the complete head-shoulder contour, with low calculating complexity and high efficiency.

A Novel Optical/digital Processing System for Pattern Recognition

NASA Technical Reports Server (NTRS)

Boone, Bradley G.; Shukla, Oodaye B.

1993-01-01

This paper describes two processing algorithms that can be implemented optically: the Radon transform and angular correlation. These two algorithms can be combined in one optical processor to extract all the basic geometric and amplitude features from objects embedded in video imagery. We show that the internal amplitude structure of objects is recovered by the Radon transform, which is a well-known result, but, in addition, we show simulation results that calculate angular correlation, a simple but unique algorithm that extracts object boundaries from suitably threshold images from which length, width, area, aspect ratio, and orientation can be derived. In addition to circumventing scale and rotation distortions, these simulations indicate that the features derived from the angular correlation algorithm are relatively insensitive to tracking shifts and image noise. Some optical architecture concepts, including one based on micro-optical lenslet arrays, have been developed to implement these algorithms. Simulation test and evaluation using simple synthetic object data will be described, including results of a study that uses object boundaries (derivable from angular correlation) to classify simple objects using a neural network.

Document localization algorithms based on feature points and straight lines

NASA Astrophysics Data System (ADS)

Skoryukina, Natalya; Shemiakina, Julia; Arlazarov, Vladimir L.; Faradjev, Igor

2018-04-01

The important part of the system of a planar rectangular object analysis is the localization: the estimation of projective transform from template image of an object to its photograph. The system also includes such subsystems as the selection and recognition of text fields, the usage of contexts etc. In this paper three localization algorithms are described. All algorithms use feature points and two of them also analyze near-horizontal and near- vertical lines on the photograph. The algorithms and their combinations are tested on a dataset of real document photographs. Also the method of localization quality estimation is proposed that allows configuring the localization subsystem independently of the other subsystems quality.

Parallel Architectures and Parallel Algorithms for Integrated Vision Systems. Ph.D. Thesis

NASA Technical Reports Server (NTRS)

Choudhary, Alok Nidhi

1989-01-01

Computer vision is regarded as one of the most complex and computationally intensive problems. An integrated vision system (IVS) is a system that uses vision algorithms from all levels of processing to perform for a high level application (e.g., object recognition). An IVS normally involves algorithms from low level, intermediate level, and high level vision. Designing parallel architectures for vision systems is of tremendous interest to researchers. Several issues are addressed in parallel architectures and parallel algorithms for integrated vision systems.

Increasing the object recognition distance of compact open air on board vision system

NASA Astrophysics Data System (ADS)

Kirillov, Sergey; Kostkin, Ivan; Strotov, Valery; Dmitriev, Vladimir; Berdnikov, Vadim; Akopov, Eduard; Elyutin, Aleksey

2016-10-01

The aim of this work was developing an algorithm eliminating the atmospheric distortion and improves image quality. The proposed algorithm is entirely software without using additional hardware photographic equipment. . This algorithm does not required preliminary calibration. It can work equally effectively with the images obtained at a distances from 1 to 500 meters. An algorithm for the open air images improve designed for Raspberry Pi model B on-board vision systems is proposed. The results of experimental examination are given.

Objective Prediction of Hearing Aid Benefit Across Listener Groups Using Machine Learning: Speech Recognition Performance With Binaural Noise-Reduction Algorithms.

PubMed

Schädler, Marc R; Warzybok, Anna; Kollmeier, Birger

2018-01-01

The simulation framework for auditory discrimination experiments (FADE) was adopted and validated to predict the individual speech-in-noise recognition performance of listeners with normal and impaired hearing with and without a given hearing-aid algorithm. FADE uses a simple automatic speech recognizer (ASR) to estimate the lowest achievable speech reception thresholds (SRTs) from simulated speech recognition experiments in an objective way, independent from any empirical reference data. Empirical data from the literature were used to evaluate the model in terms of predicted SRTs and benefits in SRT with the German matrix sentence recognition test when using eight single- and multichannel binaural noise-reduction algorithms. To allow individual predictions of SRTs in binaural conditions, the model was extended with a simple better ear approach and individualized by taking audiograms into account. In a realistic binaural cafeteria condition, FADE explained about 90% of the variance of the empirical SRTs for a group of normal-hearing listeners and predicted the corresponding benefits with a root-mean-square prediction error of 0.6 dB. This highlights the potential of the approach for the objective assessment of benefits in SRT without prior knowledge about the empirical data. The predictions for the group of listeners with impaired hearing explained 75% of the empirical variance, while the individual predictions explained less than 25%. Possibly, additional individual factors should be considered for more accurate predictions with impaired hearing. A competing talker condition clearly showed one limitation of current ASR technology, as the empirical performance with SRTs lower than -20 dB could not be predicted.

Objective Prediction of Hearing Aid Benefit Across Listener Groups Using Machine Learning: Speech Recognition Performance With Binaural Noise-Reduction Algorithms

PubMed Central

Schädler, Marc R.; Warzybok, Anna; Kollmeier, Birger

2018-01-01

The simulation framework for auditory discrimination experiments (FADE) was adopted and validated to predict the individual speech-in-noise recognition performance of listeners with normal and impaired hearing with and without a given hearing-aid algorithm. FADE uses a simple automatic speech recognizer (ASR) to estimate the lowest achievable speech reception thresholds (SRTs) from simulated speech recognition experiments in an objective way, independent from any empirical reference data. Empirical data from the literature were used to evaluate the model in terms of predicted SRTs and benefits in SRT with the German matrix sentence recognition test when using eight single- and multichannel binaural noise-reduction algorithms. To allow individual predictions of SRTs in binaural conditions, the model was extended with a simple better ear approach and individualized by taking audiograms into account. In a realistic binaural cafeteria condition, FADE explained about 90% of the variance of the empirical SRTs for a group of normal-hearing listeners and predicted the corresponding benefits with a root-mean-square prediction error of 0.6 dB. This highlights the potential of the approach for the objective assessment of benefits in SRT without prior knowledge about the empirical data. The predictions for the group of listeners with impaired hearing explained 75% of the empirical variance, while the individual predictions explained less than 25%. Possibly, additional individual factors should be considered for more accurate predictions with impaired hearing. A competing talker condition clearly showed one limitation of current ASR technology, as the empirical performance with SRTs lower than −20 dB could not be predicted. PMID:29692200

Key features for ATA / ATR database design in missile systems

NASA Astrophysics Data System (ADS)

Özertem, Kemal Arda

2017-05-01

Automatic target acquisition (ATA) and automatic target recognition (ATR) are two vital tasks for missile systems, and having a robust detection and recognition algorithm is crucial for overall system performance. In order to have a robust target detection and recognition algorithm, an extensive image database is required. Automatic target recognition algorithms use the database of images in training and testing steps of algorithm. This directly affects the recognition performance, since the training accuracy is driven by the quality of the image database. In addition, the performance of an automatic target detection algorithm can be measured effectively by using an image database. There are two main ways for designing an ATA / ATR database. The first and easy way is by using a scene generator. A scene generator can model the objects by considering its material information, the atmospheric conditions, detector type and the territory. Designing image database by using a scene generator is inexpensive and it allows creating many different scenarios quickly and easily. However the major drawback of using a scene generator is its low fidelity, since the images are created virtually. The second and difficult way is designing it using real-world images. Designing image database with real-world images is a lot more costly and time consuming; however it offers high fidelity, which is critical for missile algorithms. In this paper, critical concepts in ATA / ATR database design with real-world images are discussed. Each concept is discussed in the perspective of ATA and ATR separately. For the implementation stage, some possible solutions and trade-offs for creating the database are proposed, and all proposed approaches are compared to each other with regards to their pros and cons.

Liquid lens: advances in adaptive optics

NASA Astrophysics Data System (ADS)

Casey, Shawn Patrick

2010-12-01

'Liquid lens' technologies promise significant advancements in machine vision and optical communications systems. Adaptations for machine vision, human vision correction, and optical communications are used to exemplify the versatile nature of this technology. Utilization of liquid lens elements allows the cost effective implementation of optical velocity measurement. The project consists of a custom image processor, camera, and interface. The images are passed into customized pattern recognition and optical character recognition algorithms. A single camera would be used for both speed detection and object recognition.

A knowledge-based object recognition system for applications in the space station

NASA Technical Reports Server (NTRS)

Dhawan, Atam P.

1988-01-01

A knowledge-based three-dimensional (3D) object recognition system is being developed. The system uses primitive-based hierarchical relational and structural matching for the recognition of 3D objects in the two-dimensional (2D) image for interpretation of the 3D scene. At present, the pre-processing, low-level preliminary segmentation, rule-based segmentation, and the feature extraction are completed. The data structure of the primitive viewing knowledge-base (PVKB) is also completed. Algorithms and programs based on attribute-trees matching for decomposing the segmented data into valid primitives were developed. The frame-based structural and relational descriptions of some objects were created and stored in a knowledge-base. This knowledge-base of the frame-based descriptions were developed on the MICROVAX-AI microcomputer in LISP environment. The simulated 3D scene of simple non-overlapping objects as well as real camera data of images of 3D objects of low-complexity have been successfully interpreted.

Novel Blind Recognition Algorithm of Frame Synchronization Words Based on Soft-Decision in Digital Communication Systems.

PubMed

Qin, Jiangyi; Huang, Zhiping; Liu, Chunwu; Su, Shaojing; Zhou, Jing

2015-01-01

A novel blind recognition algorithm of frame synchronization words is proposed to recognize the frame synchronization words parameters in digital communication systems. In this paper, a blind recognition method of frame synchronization words based on the hard-decision is deduced in detail. And the standards of parameter recognition are given. Comparing with the blind recognition based on the hard-decision, utilizing the soft-decision can improve the accuracy of blind recognition. Therefore, combining with the characteristics of Quadrature Phase Shift Keying (QPSK) signal, an improved blind recognition algorithm based on the soft-decision is proposed. Meanwhile, the improved algorithm can be extended to other signal modulation forms. Then, the complete blind recognition steps of the hard-decision algorithm and the soft-decision algorithm are given in detail. Finally, the simulation results show that both the hard-decision algorithm and the soft-decision algorithm can recognize the parameters of frame synchronization words blindly. What's more, the improved algorithm can enhance the accuracy of blind recognition obviously.

An Energy-Efficient and Scalable Deep Learning/Inference Processor With Tetra-Parallel MIMD Architecture for Big Data Applications.

PubMed

Park, Seong-Wook; Park, Junyoung; Bong, Kyeongryeol; Shin, Dongjoo; Lee, Jinmook; Choi, Sungpill; Yoo, Hoi-Jun

2015-12-01

Deep Learning algorithm is widely used for various pattern recognition applications such as text recognition, object recognition and action recognition because of its best-in-class recognition accuracy compared to hand-crafted algorithm and shallow learning based algorithms. Long learning time caused by its complex structure, however, limits its usage only in high-cost servers or many-core GPU platforms so far. On the other hand, the demand on customized pattern recognition within personal devices will grow gradually as more deep learning applications will be developed. This paper presents a SoC implementation to enable deep learning applications to run with low cost platforms such as mobile or portable devices. Different from conventional works which have adopted massively-parallel architecture, this work adopts task-flexible architecture and exploits multiple parallelism to cover complex functions of convolutional deep belief network which is one of popular deep learning/inference algorithms. In this paper, we implement the most energy-efficient deep learning and inference processor for wearable system. The implemented 2.5 mm × 4.0 mm deep learning/inference processor is fabricated using 65 nm 8-metal CMOS technology for a battery-powered platform with real-time deep inference and deep learning operation. It consumes 185 mW average power, and 213.1 mW peak power at 200 MHz operating frequency and 1.2 V supply voltage. It achieves 411.3 GOPS peak performance and 1.93 TOPS/W energy efficiency, which is 2.07× higher than the state-of-the-art.

State-Estimation Algorithm Based on Computer Vision

NASA Technical Reports Server (NTRS)

Bayard, David; Brugarolas, Paul

2007-01-01

An algorithm and software to implement the algorithm are being developed as means to estimate the state (that is, the position and velocity) of an autonomous vehicle, relative to a visible nearby target object, to provide guidance for maneuvering the vehicle. In the original intended application, the autonomous vehicle would be a spacecraft and the nearby object would be a small astronomical body (typically, a comet or asteroid) to be explored by the spacecraft. The algorithm could also be used on Earth in analogous applications -- for example, for guiding underwater robots near such objects of interest as sunken ships, mineral deposits, or submerged mines. It is assumed that the robot would be equipped with a vision system that would include one or more electronic cameras, image-digitizing circuitry, and an imagedata- processing computer that would generate feature-recognition data products.

Automatic recognition of ship types from infrared images using superstructure moment invariants

NASA Astrophysics Data System (ADS)

Li, Heng; Wang, Xinyu

2007-11-01

Automatic object recognition is an active area of interest for military and commercial applications. In this paper, a system addressing autonomous recognition of ship types in infrared images is proposed. Firstly, an approach of segmentation based on detection of salient features of the target with subsequent shadow removing is proposed, as is the base of the subsequent object recognition. Considering the differences between the shapes of various ships mainly lie in their superstructures, we then use superstructure moment functions invariant to translation, rotation and scale differences in input patterns and develop a robust algorithm of obtaining ship superstructure. Subsequently a back-propagation neural network is used as a classifier in the recognition stage and projection images of simulated three-dimensional ship models are used as the training sets. Our recognition model was implemented and experimentally validated using both simulated three-dimensional ship model images and real images derived from video of an AN/AAS-44V Forward Looking Infrared(FLIR) sensor.

Behavior analysis of video object in complicated background

NASA Astrophysics Data System (ADS)

Zhao, Wenting; Wang, Shigang; Liang, Chao; Wu, Wei; Lu, Yang

2016-10-01

This paper aims to achieve robust behavior recognition of video object in complicated background. Features of the video object are described and modeled according to the depth information of three-dimensional video. Multi-dimensional eigen vector are constructed and used to process high-dimensional data. Stable object tracing in complex scenes can be achieved with multi-feature based behavior analysis, so as to obtain the motion trail. Subsequently, effective behavior recognition of video object is obtained according to the decision criteria. What's more, the real-time of algorithms and accuracy of analysis are both improved greatly. The theory and method on the behavior analysis of video object in reality scenes put forward by this project have broad application prospect and important practical significance in the security, terrorism, military and many other fields.

Advanced optical correlation and digital methods for pattern matching—50th anniversary of Vander Lugt matched filter

NASA Astrophysics Data System (ADS)

Millán, María S.

2012-10-01

On the verge of the 50th anniversary of Vander Lugt’s formulation for pattern matching based on matched filtering and optical correlation, we acknowledge the very intense research activity developed in the field of correlation-based pattern recognition during this period of time. The paper reviews some domains that appeared as emerging fields in the last years of the 20th century and have been developed later on in the 21st century. Such is the case of three-dimensional (3D) object recognition, biometric pattern matching, optical security and hybrid optical-digital processors. 3D object recognition is a challenging case of multidimensional image recognition because of its implications in the recognition of real-world objects independent of their perspective. Biometric recognition is essentially pattern recognition for which the personal identification is based on the authentication of a specific physiological characteristic possessed by the subject (e.g. fingerprint, face, iris, retina, and multifactor combinations). Biometric recognition often appears combined with encryption-decryption processes to secure information. The optical implementations of correlation-based pattern recognition processes still rely on the 4f-correlator, the joint transform correlator, or some of their variants. But the many applications developed in the field have been pushing the systems for a continuous improvement of their architectures and algorithms, thus leading towards merged optical-digital solutions.

Fast and flexible 3D object recognition solutions for machine vision applications

NASA Astrophysics Data System (ADS)

Effenberger, Ira; Kühnle, Jens; Verl, Alexander

2013-03-01

In automation and handling engineering, supplying work pieces between different stages along the production process chain is of special interest. Often the parts are stored unordered in bins or lattice boxes and hence have to be separated and ordered for feeding purposes. An alternative to complex and spacious mechanical systems such as bowl feeders or conveyor belts, which are typically adapted to the parts' geometry, is using a robot to grip the work pieces out of a bin or from a belt. Such applications are in need of reliable and precise computer-aided object detection and localization systems. For a restricted range of parts, there exists a variety of 2D image processing algorithms that solve the recognition problem. However, these methods are often not well suited for the localization of randomly stored parts. In this paper we present a fast and flexible 3D object recognizer that localizes objects by identifying primitive features within the objects. Since technical work pieces typically consist to a substantial degree of geometric primitives such as planes, cylinders and cones, such features usually carry enough information in order to determine the position of the entire object. Our algorithms use 3D best-fitting combined with an intelligent data pre-processing step. The capability and performance of this approach is shown by applying the algorithms to real data sets of different industrial test parts in a prototypical bin picking demonstration system.

Fuzzy Set Methods for Object Recognition in Space Applications

NASA Technical Reports Server (NTRS)

Keller, James M. (Editor)

1992-01-01

Progress on the following four tasks is described: (1) fuzzy set based decision methodologies; (2) membership calculation; (3) clustering methods (including derivation of pose estimation parameters), and (4) acquisition of images and testing of algorithms.

Creating ensembles of oblique decision trees with evolutionary algorithms and sampling

DOEpatents

Cantu-Paz, Erick [Oakland, CA; Kamath, Chandrika [Tracy, CA

2006-06-13

A decision tree system that is part of a parallel object-oriented pattern recognition system, which in turn is part of an object oriented data mining system. A decision tree process includes the step of reading the data. If necessary, the data is sorted. A potential split of the data is evaluated according to some criterion. An initial split of the data is determined. The final split of the data is determined using evolutionary algorithms and statistical sampling techniques. The data is split. Multiple decision trees are combined in ensembles.

Pattern recognition of the targets with help of polarization properties of the signal

NASA Astrophysics Data System (ADS)

Ponomaryov, Volodymyr I.; de Rivera, Luis N.; Castellanos, Aldo B.; Popov, Anatoly V.

1999-10-01

We proposed to use the possibility of recognition of the targets on background of the scattering from the surface, weather objects with the help of polarimetric 3-cm radar. It has been investigated such polarization characteristics: the amplitudes of the polarization matrix elements; an anisotropy coefficient; depolarization coefficient; asymmetry coefficient; the energy section was less than 1 dB at ranges up to 15 km and less than 1.5 dB at ranges up to 100 km. During the experiments urban objects and 6 various ships of small displacement having the closest values of the backscattering cross-section were used. The analysis has shown: the factor of the polarization selection for anisotropy objects and weather objects had the values about 0.02-0.08 Isotropy had the values of polarimetric correlation factor for hydrometers about 0.7-0.8, for earth surface about 0.8-0.9, for sea surface - from 0.33 to 0.7. The results of the work of recognition algorithm of a class 'concrete objects', and 'metal objects' are submitted as example in the paper. The result of experiments have shown that the probability of correct recognition of the identified objects was in the limits from 0.93 to 0.97.

Position estimation and driving of an autonomous vehicle by monocular vision

NASA Astrophysics Data System (ADS)

Hanan, Jay C.; Kayathi, Pavan; Hughlett, Casey L.

2007-04-01

Automatic adaptive tracking in real-time for target recognition provided autonomous control of a scale model electric truck. The two-wheel drive truck was modified as an autonomous rover test-bed for vision based guidance and navigation. Methods were implemented to monitor tracking error and ensure a safe, accurate arrival at the intended science target. Some methods are situation independent relying only on the confidence error of the target recognition algorithm. Other methods take advantage of the scenario of combined motion and tracking to filter out anomalies. In either case, only a single calibrated camera was needed for position estimation. Results from real-time autonomous driving tests on the JPL simulated Mars yard are presented. Recognition error was often situation dependent. For the rover case, the background was in motion and may be characterized to provide visual cues on rover travel such as rate, pitch, roll, and distance to objects of interest or hazards. Objects in the scene may be used as landmarks, or waypoints, for such estimations. As objects are approached, their scale increases and their orientation may change. In addition, particularly on rough terrain, these orientation and scale changes may be unpredictable. Feature extraction combined with the neural network algorithm was successful in providing visual odometry in the simulated Mars environment.

Multi-objects recognition for distributed intelligent sensor networks

NASA Astrophysics Data System (ADS)

He, Haibo; Chen, Sheng; Cao, Yuan; Desai, Sachi; Hohil, Myron E.

2008-04-01

This paper proposes an innovative approach for multi-objects recognition for homeland security and defense based intelligent sensor networks. Unlike the conventional way of information analysis, data mining in such networks is typically characterized with high information ambiguity/uncertainty, data redundancy, high dimensionality and real-time constrains. Furthermore, since a typical military based network normally includes multiple mobile sensor platforms, ground forces, fortified tanks, combat flights, and other resources, it is critical to develop intelligent data mining approaches to fuse different information resources to understand dynamic environments, to support decision making processes, and finally to achieve the goals. This paper aims to address these issues with a focus on multi-objects recognition. Instead of classifying a single object as in the traditional image classification problems, the proposed method can automatically learn multiple objectives simultaneously. Image segmentation techniques are used to identify the interesting regions in the field, which correspond to multiple objects such as soldiers or tanks. Since different objects will come with different feature sizes, we propose a feature scaling method to represent each object in the same number of dimensions. This is achieved by linear/nonlinear scaling and sampling techniques. Finally, support vector machine (SVM) based learning algorithms are developed to learn and build the associations for different objects, and such knowledge will be adaptively accumulated for objects recognition in the testing stage. We test the effectiveness of proposed method in different simulated military environments.

Ball-scale based hierarchical multi-object recognition in 3D medical images

NASA Astrophysics Data System (ADS)

Bağci, Ulas; Udupa, Jayaram K.; Chen, Xinjian

2010-03-01

This paper investigates, using prior shape models and the concept of ball scale (b-scale), ways of automatically recognizing objects in 3D images without performing elaborate searches or optimization. That is, the goal is to place the model in a single shot close to the right pose (position, orientation, and scale) in a given image so that the model boundaries fall in the close vicinity of object boundaries in the image. This is achieved via the following set of key ideas: (a) A semi-automatic way of constructing a multi-object shape model assembly. (b) A novel strategy of encoding, via b-scale, the pose relationship between objects in the training images and their intensity patterns captured in b-scale images. (c) A hierarchical mechanism of positioning the model, in a one-shot way, in a given image from a knowledge of the learnt pose relationship and the b-scale image of the given image to be segmented. The evaluation results on a set of 20 routine clinical abdominal female and male CT data sets indicate the following: (1) Incorporating a large number of objects improves the recognition accuracy dramatically. (2) The recognition algorithm can be thought as a hierarchical framework such that quick replacement of the model assembly is defined as coarse recognition and delineation itself is known as finest recognition. (3) Scale yields useful information about the relationship between the model assembly and any given image such that the recognition results in a placement of the model close to the actual pose without doing any elaborate searches or optimization. (4) Effective object recognition can make delineation most accurate.

Classification of motor activities through derivative dynamic time warping applied on accelerometer data.

PubMed

Muscillo, Rossana; Conforto, Silvia; Schmid, Maurizio; Caselli, Paolo; D'Alessio, Tommaso

2007-01-01

In the context of tele-monitoring, great interest is presently devoted to physical activity, mainly of elderly or people with disabilities. In this context, many researchers studied the recognition of activities of daily living by using accelerometers. The present work proposes a novel algorithm for activity recognition that considers the variability in movement speed, by using dynamic programming. This objective is realized by means of a matching and recognition technique that determines the distance between the signal input and a set of previously defined templates. Two different approaches are here presented, one based on Dynamic Time Warping (DTW) and the other based on the Derivative Dynamic Time Warping (DDTW). The algorithm was applied to the recognition of gait, climbing and descending stairs, using a biaxial accelerometer placed on the shin. The results on DDTW, obtained by using only one sensor channel on the shin showed an average recognition score of 95%, higher than the values obtained with DTW (around 85%). Both DTW and DDTW consistently show higher classification rate than classical Linear Time Warping (LTW).

Marginal Fisher analysis and its variants for human gait recognition and content- based image retrieval.

PubMed

Xu, Dong; Yan, Shuicheng; Tao, Dacheng; Lin, Stephen; Zhang, Hong-Jiang

2007-11-01

Dimensionality reduction algorithms, which aim to select a small set of efficient and discriminant features, have attracted great attention for human gait recognition and content-based image retrieval (CBIR). In this paper, we present extensions of our recently proposed marginal Fisher analysis (MFA) to address these problems. For human gait recognition, we first present a direct application of MFA, then inspired by recent advances in matrix and tensor-based dimensionality reduction algorithms, we present matrix-based MFA for directly handling 2-D input in the form of gray-level averaged images. For CBIR, we deal with the relevance feedback problem by extending MFA to marginal biased analysis, in which within-class compactness is characterized only by the distances between each positive sample and its neighboring positive samples. In addition, we present a new technique to acquire a direct optimal solution for MFA without resorting to objective function modification as done in many previous algorithms. We conduct comprehensive experiments on the USF HumanID gait database and the Corel image retrieval database. Experimental results demonstrate that MFA and its extensions outperform related algorithms in both applications.

Optical and digital pattern recognition; Proceedings of the Meeting, Los Angeles, CA, Jan. 13-15, 1987

NASA Technical Reports Server (NTRS)

Liu, Hua-Kuang (Editor); Schenker, Paul (Editor)

1987-01-01

The papers presented in this volume provide an overview of current research in both optical and digital pattern recognition, with a theme of identifying overlapping research problems and methodologies. Topics discussed include image analysis and low-level vision, optical system design, object analysis and recognition, real-time hybrid architectures and algorithms, high-level image understanding, and optical matched filter design. Papers are presented on synthetic estimation filters for a control system; white-light correlator character recognition; optical AI architectures for intelligent sensors; interpreting aerial photographs by segmentation and search; and optical information processing using a new photopolymer.

Use of iris recognition camera technology for the quantification of corneal opacification in mucopolysaccharidoses.

PubMed

Aslam, Tariq Mehmood; Shakir, Savana; Wong, James; Au, Leon; Ashworth, Jane

2012-12-01

Mucopolysaccharidoses (MPS) can cause corneal opacification that is currently difficult to objectively quantify. With newer treatments for MPS comes an increased need for a more objective, valid and reliable index of disease severity for clinical and research use. Clinical evaluation by slit lamp is very subjective and techniques based on colour photography are difficult to standardise. In this article the authors present evidence for the utility of dedicated image analysis algorithms applied to images obtained by a highly sophisticated iris recognition camera that is small, manoeuvrable and adapted to achieve rapid, reliable and standardised objective imaging in a wide variety of patients while minimising artefactual interference in image quality.

Recognition of disturbances with specified morphology in time series. Part 1: Spikes on magnetograms of the worldwide INTERMAGNET network

NASA Astrophysics Data System (ADS)

Bogoutdinov, Sh. R.; Gvishiani, A. D.; Agayan, S. M.; Solovyev, A. A.; Kin, E.

2010-11-01

The International Real-time Magnetic Observatory Network (INTERMAGNET) is the world's biggest international network of ground-based observatories, providing geomagnetic data almost in real time (within 72 hours of collection) [Kerridge, 2001]. The observation data are rapidly transferred by the observatories participating in the program to regional Geomagnetic Information Nodes (GINs), which carry out a global exchange of data and process the results. The observations of the main (core) magnetic field of the Earth and its study are one of the key problems of geophysics. The INTERMAGNET system is the basis of monitoring the state of the Earth's magnetic field; therefore, the information provided by the system is required to be very reliable. Despite the rigid high-quality standard of the recording devices, they are subject to external effects that affect the quality of the records. Therefore, an objective and formalized recognition with the subsequent remedy of the anomalies (artifacts) that occur on the records is an important task. Expanding on the ideas of Agayan [Agayan et al., 2005] and Gvishiani [Gvishiani et al., 2008a; 2008b], this paper suggests a new algorithm of automatic recognition of anomalies with specified morphology, capable of identifying both physically- and anthropogenically-derived spikes on the magnetograms. The algorithm is constructed using fuzzy logic and, as such, is highly adaptive and universal. The developed algorithmic system formalizes the work of the expert-interpreter in terms of artificial intelligence. This ensures identical processing of large data arrays, almost unattainable manually. Besides the algorithm, the paper also reports on the application of the developed algorithmic system for identifying spikes at the INTERMAGNET observatories. The main achievement of the work is the creation of an algorithm permitting the almost unmanned extraction of spike-free (definitive) magnetograms from preliminary records. This automated system is developed for the first time with the application of fuzzy logic system for geomagnetic measurements. It is important to note that the recognition of time disturbances is formalized and identical. The algorithm presented here appreciably increases the reliability of spike-free INTERMAGNET magnetograms, thus increasing the objectivity of our knowledge of the Earth's magnetic field. At the same time, the created system can accomplish identical, formalized, and retrospective analysis of large archives of digital and digitized magnetograms, accumulated in the system of Worldwide Data Centers. The relevant project has already been initiated as a collaborative initiative of the Worldwide Data Center at Geophysical Center (Russian Academy of Sciences) and the NOAA National Geophysical Data Center (Unite States). Thus, by improving and adding objectivity to both new and historical initial data, the developed algorithmic system may contribute appreciably to improving our understanding of the Earth's magnetic field.

Visual recognition and inference using dynamic overcomplete sparse learning.

PubMed

Murray, Joseph F; Kreutz-Delgado, Kenneth

2007-09-01

We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and expectation-driven segmentation. Using properties of biological vision for guidance, we posit a stochastic generative world model and from it develop a simplified world model (SWM) based on a tractable variational approximation that is designed to enforce sparse coding. Recent developments in computational methods for learning overcomplete representations (Lewicki & Sejnowski, 2000; Teh, Welling, Osindero, & Hinton, 2003) suggest that overcompleteness can be useful for visual tasks, and we use an overcomplete dictionary learning algorithm (Kreutz-Delgado, et al., 2003) as a preprocessing stage to produce accurate, sparse codings of images. Inference is performed by constructing a dynamic multilayer network with feedforward, feedback, and lateral connections, which is trained to approximate the SWM. Learning is done with a variant of the back-propagation-through-time algorithm, which encourages convergence to desired states within a fixed number of iterations. Vision tasks require large networks, and to make learning efficient, we take advantage of the sparsity of each layer to update only a small subset of elements in a large weight matrix at each iteration. Experiments on a set of rotated objects demonstrate various types of visual inference and show that increasing the degree of overcompleteness improves recognition performance in difficult scenes with occluded objects in clutter.

Digital signal processing algorithms for automatic voice recognition

NASA Technical Reports Server (NTRS)

Botros, Nazeih M.

1987-01-01

The current digital signal analysis algorithms are investigated that are implemented in automatic voice recognition algorithms. Automatic voice recognition means, the capability of a computer to recognize and interact with verbal commands. The digital signal is focused on, rather than the linguistic, analysis of speech signal. Several digital signal processing algorithms are available for voice recognition. Some of these algorithms are: Linear Predictive Coding (LPC), Short-time Fourier Analysis, and Cepstrum Analysis. Among these algorithms, the LPC is the most widely used. This algorithm has short execution time and do not require large memory storage. However, it has several limitations due to the assumptions used to develop it. The other 2 algorithms are frequency domain algorithms with not many assumptions, but they are not widely implemented or investigated. However, with the recent advances in the digital technology, namely signal processors, these 2 frequency domain algorithms may be investigated in order to implement them in voice recognition. This research is concerned with real time, microprocessor based recognition algorithms.

New technique for real-time distortion-invariant multiobject recognition and classification

NASA Astrophysics Data System (ADS)

Hong, Rutong; Li, Xiaoshun; Hong, En; Wang, Zuyi; Wei, Hongan

2001-04-01

A real-time hybrid distortion-invariant OPR system was established to make 3D multiobject distortion-invariant automatic pattern recognition. Wavelet transform technique was used to make digital preprocessing of the input scene, to depress the noisy background and enhance the recognized object. A three-layer backpropagation artificial neural network was used in correlation signal post-processing to perform multiobject distortion-invariant recognition and classification. The C-80 and NOA real-time processing ability and the multithread programming technology were used to perform high speed parallel multitask processing and speed up the post processing rate to ROIs. The reference filter library was constructed for the distortion version of 3D object model images based on the distortion parameter tolerance measuring as rotation, azimuth and scale. The real-time optical correlation recognition testing of this OPR system demonstrates that using the preprocessing, post- processing, the nonlinear algorithm os optimum filtering, RFL construction technique and the multithread programming technology, a high possibility of recognition and recognition rate ere obtained for the real-time multiobject distortion-invariant OPR system. The recognition reliability and rate was improved greatly. These techniques are very useful to automatic target recognition.

a Fully Automated Pipeline for Classification Tasks with AN Application to Remote Sensing

NASA Astrophysics Data System (ADS)

Suzuki, K.; Claesen, M.; Takeda, H.; De Moor, B.

2016-06-01

Nowadays deep learning has been intensively in spotlight owing to its great victories at major competitions, which undeservedly pushed `shallow' machine learning methods, relatively naive/handy algorithms commonly used by industrial engineers, to the background in spite of their facilities such as small requisite amount of time/dataset for training. We, with a practical point of view, utilized shallow learning algorithms to construct a learning pipeline such that operators can utilize machine learning without any special knowledge, expensive computation environment, and a large amount of labelled data. The proposed pipeline automates a whole classification process, namely feature-selection, weighting features and the selection of the most suitable classifier with optimized hyperparameters. The configuration facilitates particle swarm optimization, one of well-known metaheuristic algorithms for the sake of generally fast and fine optimization, which enables us not only to optimize (hyper)parameters but also to determine appropriate features/classifier to the problem, which has conventionally been a priori based on domain knowledge and remained untouched or dealt with naïve algorithms such as grid search. Through experiments with the MNIST and CIFAR-10 datasets, common datasets in computer vision field for character recognition and object recognition problems respectively, our automated learning approach provides high performance considering its simple setting (i.e. non-specialized setting depending on dataset), small amount of training data, and practical learning time. Moreover, compared to deep learning the performance stays robust without almost any modification even with a remote sensing object recognition problem, which in turn indicates that there is a high possibility that our approach contributes to general classification problems.

Spatiotemporal information during unsupervised learning enhances viewpoint invariant object recognition

PubMed Central

Tian, Moqian; Grill-Spector, Kalanit

2015-01-01

Recognizing objects is difficult because it requires both linking views of an object that can be different and distinguishing objects with similar appearance. Interestingly, people can learn to recognize objects across views in an unsupervised way, without feedback, just from the natural viewing statistics. However, there is intense debate regarding what information during unsupervised learning is used to link among object views. Specifically, researchers argue whether temporal proximity, motion, or spatiotemporal continuity among object views during unsupervised learning is beneficial. Here, we untangled the role of each of these factors in unsupervised learning of novel three-dimensional (3-D) objects. We found that after unsupervised training with 24 object views spanning a 180° view space, participants showed significant improvement in their ability to recognize 3-D objects across rotation. Surprisingly, there was no advantage to unsupervised learning with spatiotemporal continuity or motion information than training with temporal proximity. However, we discovered that when participants were trained with just a third of the views spanning the same view space, unsupervised learning via spatiotemporal continuity yielded significantly better recognition performance on novel views than learning via temporal proximity. These results suggest that while it is possible to obtain view-invariant recognition just from observing many views of an object presented in temporal proximity, spatiotemporal information enhances performance by producing representations with broader view tuning than learning via temporal association. Our findings have important implications for theories of object recognition and for the development of computational algorithms that learn from examples. PMID:26024454

Scene text recognition in mobile applications by character descriptor and structure configuration.

PubMed

Yi, Chucai; Tian, Yingli

2014-07-01

Text characters and strings in natural scene can provide valuable information for many applications. Extracting text directly from natural scene images or videos is a challenging task because of diverse text patterns and variant background interferences. This paper proposes a method of scene text recognition from detected text regions. In text detection, our previously proposed algorithms are applied to obtain text regions from scene image. First, we design a discriminative character descriptor by combining several state-of-the-art feature detectors and descriptors. Second, we model character structure at each character class by designing stroke configuration maps. Our algorithm design is compatible with the application of scene text extraction in smart mobile devices. An Android-based demo system is developed to show the effectiveness of our proposed method on scene text information extraction from nearby objects. The demo system also provides us some insight into algorithm design and performance improvement of scene text extraction. The evaluation results on benchmark data sets demonstrate that our proposed scheme of text recognition is comparable with the best existing methods.

A bio-inspired method and system for visual object-based attention and segmentation

NASA Astrophysics Data System (ADS)

Huber, David J.; Khosla, Deepak

2010-04-01

This paper describes a method and system of human-like attention and object segmentation in visual scenes that (1) attends to regions in a scene in their rank of saliency in the image, (2) extracts the boundary of an attended proto-object based on feature contours, and (3) can be biased to boost the attention paid to specific features in a scene, such as those of a desired target object in static and video imagery. The purpose of the system is to identify regions of a scene of potential importance and extract the region data for processing by an object recognition and classification algorithm. The attention process can be performed in a default, bottom-up manner or a directed, top-down manner which will assign a preference to certain features over others. One can apply this system to any static scene, whether that is a still photograph or imagery captured from video. We employ algorithms that are motivated by findings in neuroscience, psychology, and cognitive science to construct a system that is novel in its modular and stepwise approach to the problems of attention and region extraction, its application of a flooding algorithm to break apart an image into smaller proto-objects based on feature density, and its ability to join smaller regions of similar features into larger proto-objects. This approach allows many complicated operations to be carried out by the system in a very short time, approaching real-time. A researcher can use this system as a robust front-end to a larger system that includes object recognition and scene understanding modules; it is engineered to function over a broad range of situations and can be applied to any scene with minimal tuning from the user.

Using LabView for real-time monitoring and tracking of multiple biological objects

NASA Astrophysics Data System (ADS)

Nikolskyy, Aleksandr I.; Krasilenko, Vladimir G.; Bilynsky, Yosyp Y.; Starovier, Anzhelika

2017-04-01

Today real-time studying and tracking of movement dynamics of various biological objects is important and widely researched. Features of objects, conditions of their visualization and model parameters strongly influence the choice of optimal methods and algorithms for a specific task. Therefore, to automate the processes of adaptation of recognition tracking algorithms, several Labview project trackers are considered in the article. Projects allow changing templates for training and retraining the system quickly. They adapt to the speed of objects and statistical characteristics of noise in images. New functions of comparison of images or their features, descriptors and pre-processing methods will be discussed. The experiments carried out to test the trackers on real video files will be presented and analyzed.

Recognition of military-specific physical activities with body-fixed sensors.

PubMed

Wyss, Thomas; Mäder, Urs

2010-11-01

The purpose of this study was to develop and validate an algorithm for recognizing military-specific, physically demanding activities using body-fixed sensors. To develop the algorithm, the first group of study participants (n = 15) wore body-fixed sensors capable of measuring acceleration, step frequency, and heart rate while completing six military-specific activities: walking, marching with backpack, lifting and lowering loads, lifting and carrying loads, digging, and running. The accuracy of the algorithm was tested in these isolated activities in a laboratory setting (n = 18) and in the context of daily military training routine (n = 24). The overall recognition rates during isolated activities and during daily military routine activities were 87.5% and 85.5%, respectively. We conclude that the algorithm adequately recognized six military-specific physical activities based on sensor data alone both in a laboratory setting and in the military training environment. By recognizing type of physical activities this objective method provides additional information on military-job descriptions.

A method of 3D object recognition and localization in a cloud of points

NASA Astrophysics Data System (ADS)

Bielicki, Jerzy; Sitnik, Robert

2013-12-01

The proposed method given in this article is prepared for analysis of data in the form of cloud of points directly from 3D measurements. It is designed for use in the end-user applications that can directly be integrated with 3D scanning software. The method utilizes locally calculated feature vectors (FVs) in point cloud data. Recognition is based on comparison of the analyzed scene with reference object library. A global descriptor in the form of a set of spatially distributed FVs is created for each reference model. During the detection process, correlation of subsets of reference FVs with FVs calculated in the scene is computed. Features utilized in the algorithm are based on parameters, which qualitatively estimate mean and Gaussian curvatures. Replacement of differentiation with averaging in the curvatures estimation makes the algorithm more resistant to discontinuities and poor quality of the input data. Utilization of the FV subsets allows to detect partially occluded and cluttered objects in the scene, while additional spatial information maintains false positive rate at a reasonably low level.

Search algorithm complexity modeling with application to image alignment and matching

NASA Astrophysics Data System (ADS)

DelMarco, Stephen

2014-05-01

Search algorithm complexity modeling, in the form of penetration rate estimation, provides a useful way to estimate search efficiency in application domains which involve searching over a hypothesis space of reference templates or models, as in model-based object recognition, automatic target recognition, and biometric recognition. The penetration rate quantifies the expected portion of the database that must be searched, and is useful for estimating search algorithm computational requirements. In this paper we perform mathematical modeling to derive general equations for penetration rate estimates that are applicable to a wide range of recognition problems. We extend previous penetration rate analyses to use more general probabilistic modeling assumptions. In particular we provide penetration rate equations within the framework of a model-based image alignment application domain in which a prioritized hierarchical grid search is used to rank subspace bins based on matching probability. We derive general equations, and provide special cases based on simplifying assumptions. We show how previously-derived penetration rate equations are special cases of the general formulation. We apply the analysis to model-based logo image alignment in which a hierarchical grid search is used over a geometric misalignment transform hypothesis space. We present numerical results validating the modeling assumptions and derived formulation.

Towards discrete wavelet transform-based human activity recognition

NASA Astrophysics Data System (ADS)

Khare, Manish; Jeon, Moongu

2017-06-01

Providing accurate recognition of human activities is a challenging problem for visual surveillance applications. In this paper, we present a simple and efficient algorithm for human activity recognition based on a wavelet transform. We adopt discrete wavelet transform (DWT) coefficients as a feature of human objects to obtain advantages of its multiresolution approach. The proposed method is tested on multiple levels of DWT. Experiments are carried out on different standard action datasets including KTH and i3D Post. The proposed method is compared with other state-of-the-art methods in terms of different quantitative performance measures. The proposed method is found to have better recognition accuracy in comparison to the state-of-the-art methods.

Online adaptive neural control of a robotic lower limb prosthesis

NASA Astrophysics Data System (ADS)

Spanias, J. A.; Simon, A. M.; Finucane, S. B.; Perreault, E. J.; Hargrove, L. J.

2018-02-01

Objective. The purpose of this study was to develop and evaluate an adaptive intent recognition algorithm that continuously learns to incorporate a lower limb amputee’s neural information (acquired via electromyography (EMG)) as they ambulate with a robotic leg prosthesis. Approach. We present a powered lower limb prosthesis that was configured to acquire the user’s neural information and kinetic/kinematic information from embedded mechanical sensors, and identify and respond to the user’s intent. We conducted an experiment with eight transfemoral amputees over multiple days. EMG and mechanical sensor data were collected while subjects using a powered knee/ankle prosthesis completed various ambulation activities such as walking on level ground, stairs, and ramps. Our adaptive intent recognition algorithm automatically transitioned the prosthesis into the different locomotion modes and continuously updated the user’s model of neural data during ambulation. Main results. Our proposed algorithm accurately and consistently identified the user’s intent over multiple days, despite changing neural signals. The algorithm incorporated 96.31% [0.91%] (mean, [standard error]) of neural information across multiple experimental sessions, and outperformed non-adaptive versions of our algorithm—with a 6.66% [3.16%] relative decrease in error rate. Significance. This study demonstrates that our adaptive intent recognition algorithm enables incorporation of neural information over long periods of use, allowing assistive robotic devices to accurately respond to the user’s intent with low error rates.

Stress reaction process-based hierarchical recognition algorithm for continuous intrusion events in optical fiber prewarning system

NASA Astrophysics Data System (ADS)

Qu, Hongquan; Yuan, Shijiao; Wang, Yanping; Yang, Dan

2018-04-01

To improve the recognition performance of optical fiber prewarning system (OFPS), this study proposed a hierarchical recognition algorithm (HRA). Compared with traditional methods, which employ only a complex algorithm that includes multiple extracted features and complex classifiers to increase the recognition rate with a considerable decrease in recognition speed, HRA takes advantage of the continuity of intrusion events, thereby creating a staged recognition flow inspired by stress reaction. HRA is expected to achieve high-level recognition accuracy with less time consumption. First, this work analyzed the continuity of intrusion events and then presented the algorithm based on the mechanism of stress reaction. Finally, it verified the time consumption through theoretical analysis and experiments, and the recognition accuracy was obtained through experiments. Experiment results show that the processing speed of HRA is 3.3 times faster than that of a traditional complicated algorithm and has a similar recognition rate of 98%. The study is of great significance to fast intrusion event recognition in OFPS.

Dimension Reduction With Extreme Learning Machine.

PubMed

Kasun, Liyanaarachchi Lekamalage Chamara; Yang, Yan; Huang, Guang-Bin; Zhang, Zhengyou

2016-08-01

Data may often contain noise or irrelevant information, which negatively affect the generalization capability of machine learning algorithms. The objective of dimension reduction algorithms, such as principal component analysis (PCA), non-negative matrix factorization (NMF), random projection (RP), and auto-encoder (AE), is to reduce the noise or irrelevant information of the data. The features of PCA (eigenvectors) and linear AE are not able to represent data as parts (e.g. nose in a face image). On the other hand, NMF and non-linear AE are maimed by slow learning speed and RP only represents a subspace of original data. This paper introduces a dimension reduction framework which to some extend represents data as parts, has fast learning speed, and learns the between-class scatter subspace. To this end, this paper investigates a linear and non-linear dimension reduction framework referred to as extreme learning machine AE (ELM-AE) and sparse ELM-AE (SELM-AE). In contrast to tied weight AE, the hidden neurons in ELM-AE and SELM-AE need not be tuned, and their parameters (e.g, input weights in additive neurons) are initialized using orthogonal and sparse random weights, respectively. Experimental results on USPS handwritten digit recognition data set, CIFAR-10 object recognition, and NORB object recognition data set show the efficacy of linear and non-linear ELM-AE and SELM-AE in terms of discriminative capability, sparsity, training time, and normalized mean square error.

Adaptive learning compressive tracking based on Markov location prediction

NASA Astrophysics Data System (ADS)

Zhou, Xingyu; Fu, Dongmei; Yang, Tao; Shi, Yanan

2017-03-01

Object tracking is an interdisciplinary research topic in image processing, pattern recognition, and computer vision which has theoretical and practical application value in video surveillance, virtual reality, and automatic navigation. Compressive tracking (CT) has many advantages, such as efficiency and accuracy. However, when there are object occlusion, abrupt motion and blur, similar objects, and scale changing, the CT has the problem of tracking drift. We propose the Markov object location prediction to get the initial position of the object. Then CT is used to locate the object accurately, and the classifier parameter adaptive updating strategy is given based on the confidence map. At the same time according to the object location, extract the scale features, which is able to deal with object scale variations effectively. Experimental results show that the proposed algorithm has better tracking accuracy and robustness than current advanced algorithms and achieves real-time performance.

Framework for objective evaluation of privacy filters

NASA Astrophysics Data System (ADS)

Korshunov, Pavel; Melle, Andrea; Dugelay, Jean-Luc; Ebrahimi, Touradj

2013-09-01

Extensive adoption of video surveillance, affecting many aspects of our daily lives, alarms the public about the increasing invasion into personal privacy. To address these concerns, many tools have been proposed for protection of personal privacy in image and video. However, little is understood regarding the effectiveness of such tools and especially their impact on the underlying surveillance tasks, leading to a tradeoff between the preservation of privacy offered by these tools and the intelligibility of activities under video surveillance. In this paper, we investigate this privacy-intelligibility tradeoff objectively by proposing an objective framework for evaluation of privacy filters. We apply the proposed framework on a use case where privacy of people is protected by obscuring faces, assuming an automated video surveillance system. We used several popular privacy protection filters, such as blurring, pixelization, and masking and applied them with varying strengths to people's faces from different public datasets of video surveillance footage. Accuracy of face detection algorithm was used as a measure of intelligibility (a face should be detected to perform a surveillance task), and accuracy of face recognition algorithm as a measure of privacy (a specific person should not be identified). Under these conditions, after application of an ideal privacy protection tool, an obfuscated face would be visible as a face but would not be correctly identified by the recognition algorithm. The experiments demonstrate that, in general, an increase in strength of privacy filters under consideration leads to an increase in privacy (i.e., reduction in recognition accuracy) and to a decrease in intelligibility (i.e., reduction in detection accuracy). Masking also shows to be the most favorable filter across all tested datasets.

Knowledge-based object recognition for different morphological classes of plants

NASA Astrophysics Data System (ADS)

Brendel, Thorsten; Schwanke, Joerg; Jensch, Peter F.; Megnet, Roland

1995-01-01

Micropropagation of plants is done by cutting juvenile plants and placing them into special container-boxes with nutrient-solution where the pieces can grow up and be cut again several times. To produce high amounts of biomass it is necessary to do plant micropropagation by a robotic syshoot. In this paper we describe parts of the vision syshoot that recognizes plants and their particular cutting points. Therefore, it is necessary to extract elements of the plants and relations between these elements (for example root, shoot, leaf). Different species vary in their morphological appearance, variation is also immanent in plants of the same species. Therefore, we introduce several morphological classes of plants from that we expect same recognition methods. As a result of our work we present rules which help users to create specific algorithms for object recognition of plant species.

Using Markov Chains and Multi-Objective Optimization for Energy-Efficient Context Recognition.

PubMed

Janko, Vito; Luštrek, Mitja

2017-12-29

The recognition of the user's context with wearable sensing systems is a common problem in ubiquitous computing. However, the typically small battery of such systems often makes continuous recognition impractical. The strain on the battery can be reduced if the sensor setting is adapted to each context. We propose a method that efficiently finds near-optimal sensor settings for each context. It uses Markov chains to simulate the behavior of the system in different configurations and the multi-objective genetic algorithm to find a set of good non-dominated configurations. The method was evaluated on three real-life datasets and found good trade-offs between the system's energy expenditure and the system's accuracy. One of the solutions, for example, consumed five-times less energy than the default one, while sacrificing only two percentage points of accuracy.

Scaling up spike-and-slab models for unsupervised feature learning.

PubMed

Goodfellow, Ian J; Courville, Aaron; Bengio, Yoshua

2013-08-01

We describe the use of two spike-and-slab models for modeling real-valued data, with an emphasis on their applications to object recognition. The first model, which we call spike-and-slab sparse coding (S3C), is a preexisting model for which we introduce a faster approximate inference algorithm. We introduce a deep variant of S3C, which we call the partially directed deep Boltzmann machine (PD-DBM) and extend our S3C inference algorithm for use on this model. We describe learning procedures for each. We demonstrate that our inference procedure for S3C enables scaling the model to unprecedented large problem sizes, and demonstrate that using S3C as a feature extractor results in very good object recognition performance, particularly when the number of labeled examples is low. We show that the PD-DBM generates better samples than its shallow counterpart, and that unlike DBMs or DBNs, the PD-DBM may be trained successfully without greedy layerwise training.

Salient man-made structure detection in infrared images

NASA Astrophysics Data System (ADS)

Li, Dong-jie; Zhou, Fu-gen; Jin, Ting

2013-09-01

Target detection, segmentation and recognition is a hot research topic in the field of image processing and pattern recognition nowadays, among which salient area or object detection is one of core technologies of precision guided weapon. Many theories have been raised in this paper; we detect salient objects in a series of input infrared images by using the classical feature integration theory and Itti's visual attention system. In order to find the salient object in an image accurately, we present a new method to solve the edge blur problem by calculating and using the edge mask. We also greatly improve the computing speed by improving the center-surround differences method. Unlike the traditional algorithm, we calculate the center-surround differences through rows and columns separately. Experimental results show that our method is effective in detecting salient object accurately and rapidly.

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.

Development of a sonar-based object recognition system

NASA Astrophysics Data System (ADS)

Ecemis, Mustafa Ihsan

2001-02-01

Sonars are used extensively in mobile robotics for obstacle detection, ranging and avoidance. However, these range-finding applications do not exploit the full range of information carried in sonar echoes. In addition, mobile robots need robust object recognition systems. Therefore, a simple and robust object recognition system using ultrasonic sensors may have a wide range of applications in robotics. This dissertation develops and analyzes an object recognition system that uses ultrasonic sensors of the type commonly found on mobile robots. Three principal experiments are used to test the sonar recognition system: object recognition at various distances, object recognition during unconstrained motion, and softness discrimination. The hardware setup, consisting of an inexpensive Polaroid sonar and a data acquisition board, is described first. The software for ultrasound signal generation, echo detection, data collection, and data processing is then presented. Next, the dissertation describes two methods to extract information from the echoes, one in the frequency domain and the other in the time domain. The system uses the fuzzy ARTMAP neural network to recognize objects on the basis of the information content of their echoes. In order to demonstrate that the performance of the system does not depend on the specific classification method being used, the K- Nearest Neighbors (KNN) Algorithm is also implemented. KNN yields a test accuracy similar to fuzzy ARTMAP in all experiments. Finally, the dissertation describes a method for extracting features from the envelope function in order to reduce the dimension of the input vector used by the classifiers. Decreasing the size of the input vectors reduces the memory requirements of the system and makes it run faster. It is shown that this method does not affect the performance of the system dramatically and is more appropriate for some tasks. The results of these experiments demonstrate that sonar can be used to develop a low-cost, low-computation system for real-time object recognition tasks on mobile robots. This system differs from all previous approaches in that it is relatively simple, robust, fast, and inexpensive.

Discriminative region extraction and feature selection based on the combination of SURF and saliency

NASA Astrophysics Data System (ADS)

Deng, Li; Wang, Chunhong; Rao, Changhui

2011-08-01

The objective of this paper is to provide a possible optimization on salient region algorithm, which is extensively used in recognizing and learning object categories. Salient region algorithm owns the superiority of intra-class tolerance, global score of features and automatically prominent scale selection under certain range. However, the major limitation behaves on performance, and that is what we attempt to improve. By reducing the number of pixels involved in saliency calculation, it can be accelerated. We use interest points detected by fast-Hessian, the detector of SURF, as the candidate feature for saliency operation, rather than the whole set in image. This implementation is thereby called Saliency based Optimization over SURF (SOSU for short). Experiment shows that bringing in of such a fast detector significantly speeds up the algorithm. Meanwhile, Robustness of intra-class diversity ensures object recognition accuracy.

CONCAM's Fuzzy-Logic All-Sky Star Recognition Algorithm

NASA Astrophysics Data System (ADS)

Shamir, L.; Nemiroff, R. J.

2004-05-01

One of the purposes of the global Night Sky Live (NSL) network of fisheye CONtinuous CAMeras (CONCAMs) is to monitor and archive the entire bright night sky, track stellar variability, and search for transients. The high quality of raw CONCAM data allows automation of stellar object recognition, although distortions of the fisheye lens and frequent slight shifts in CONCAM orientations can make even this seemingly simple task formidable. To meet this challenge, a fuzzy logic based algorithm has been developed that transforms (x,y) image coordinates in the CCD frame into fuzzy right ascension and declination coordinates for use in matching with star catalogs. Using a training set of reference stars, the algorithm statically builds the fuzzy logic model. At runtime, the algorithm searches for peaks, and then applies the fuzzy logic model to perform the coordinate transformation before choosing the optimal star catalog match. The present fuzzy-logic algorithm works much better than our first generation, straightforward coordinate transformation formula. Following this essential step, algorithms dealing with the higher level data products can then provide a stream of photometry for a few hundred stellar objects visible in the night sky. Accurate photometry further enables the computation of all-sky maps of skyglow and opacity, as well as a search for uncataloged transients. All information is stored in XML-like tagged ASCII files that are instantly copied to the public domain and available at http://NightSkyLive.net. Currently, the NSL software detects stars and creates all-sky image files from eight different locations around the globe every 3 minutes and 56 seconds.

An Underwater Target Detection System for Electro-Optical Imagery Data

DTIC Science & Technology

2010-06-01

detection and segmentation of underwater mine-like objects in the EO images captured with a CCD-based image sensor. The main focus of this research is to...develop a robust detection algorithm that can be used to detect low contrast and partial underwater objects from the EO imagery with low false alarm rate...underwater target detection I. INTRODUCTION Automatic detection and recognition of underwater objects from EO imagery poses a serious challenge due to poor

Extreme Trust Region Policy Optimization for Active Object Recognition.

PubMed

Liu, Huaping; Wu, Yupei; Sun, Fuchun; Huaping Liu; Yupei Wu; Fuchun Sun; Sun, Fuchun; Liu, Huaping; Wu, Yupei

2018-06-01

In this brief, we develop a deep reinforcement learning method to actively recognize objects by choosing a sequence of actions for an active camera that helps to discriminate between the objects. The method is realized using trust region policy optimization, in which the policy is realized by an extreme learning machine and, therefore, leads to efficient optimization algorithm. The experimental results on the publicly available data set show the advantages of the developed extreme trust region optimization method.

Multi-channel feature dictionaries for RGB-D object recognition

NASA Astrophysics Data System (ADS)

Lan, Xiaodong; Li, Qiming; Chong, Mina; Song, Jian; Li, Jun

2018-04-01

Hierarchical matching pursuit (HMP) is a popular feature learning method for RGB-D object recognition. However, the feature representation with only one dictionary for RGB channels in HMP does not capture sufficient visual information. In this paper, we propose multi-channel feature dictionaries based feature learning method for RGB-D object recognition. The process of feature extraction in the proposed method consists of two layers. The K-SVD algorithm is used to learn dictionaries in sparse coding of these two layers. In the first-layer, we obtain features by performing max pooling on sparse codes of pixels in a cell. And the obtained features of cells in a patch are concatenated to generate patch jointly features. Then, patch jointly features in the first-layer are used to learn the dictionary and sparse codes in the second-layer. Finally, spatial pyramid pooling can be applied to the patch jointly features of any layer to generate the final object features in our method. Experimental results show that our method with first or second-layer features can obtain a comparable or better performance than some published state-of-the-art methods.

Handwritten digits recognition based on immune network

NASA Astrophysics Data System (ADS)

Li, Yangyang; Wu, Yunhui; Jiao, Lc; Wu, Jianshe

2011-11-01

With the development of society, handwritten digits recognition technique has been widely applied to production and daily life. It is a very difficult task to solve these problems in the field of pattern recognition. In this paper, a new method is presented for handwritten digit recognition. The digit samples firstly are processed and features extraction. Based on these features, a novel immune network classification algorithm is designed and implemented to the handwritten digits recognition. The proposed algorithm is developed by Jerne's immune network model for feature selection and KNN method for classification. Its characteristic is the novel network with parallel commutating and learning. The performance of the proposed method is experimented to the handwritten number datasets MNIST and compared with some other recognition algorithms-KNN, ANN and SVM algorithm. The result shows that the novel classification algorithm based on immune network gives promising performance and stable behavior for handwritten digits recognition.

Component-based target recognition inspired by human vision

NASA Astrophysics Data System (ADS)

Zheng, Yufeng; Agyepong, Kwabena

2009-05-01

In contrast with machine vision, human can recognize an object from complex background with great flexibility. For example, given the task of finding and circling all cars (no further information) in a picture, you may build a virtual image in mind from the task (or target) description before looking at the picture. Specifically, the virtual car image may be composed of the key components such as driver cabin and wheels. In this paper, we propose a component-based target recognition method by simulating the human recognition process. The component templates (equivalent to the virtual image in mind) of the target (car) are manually decomposed from the target feature image. Meanwhile, the edges of the testing image can be extracted by using a difference of Gaussian (DOG) model that simulates the spatiotemporal response in visual process. A phase correlation matching algorithm is then applied to match the templates with the testing edge image. If all key component templates are matched with the examining object, then this object is recognized as the target. Besides the recognition accuracy, we will also investigate if this method works with part targets (half cars). In our experiments, several natural pictures taken on streets were used to test the proposed method. The preliminary results show that the component-based recognition method is very promising.

An Improved Iris Recognition Algorithm Based on Hybrid Feature and ELM

NASA Astrophysics Data System (ADS)

Wang, Juan

2018-03-01

The iris image is easily polluted by noise and uneven light. This paper proposed an improved extreme learning machine (ELM) based iris recognition algorithm with hybrid feature. 2D-Gabor filters and GLCM is employed to generate a multi-granularity hybrid feature vector. 2D-Gabor filter and GLCM feature work for capturing low-intermediate frequency and high frequency texture information, respectively. Finally, we utilize extreme learning machine for iris recognition. Experimental results reveal our proposed ELM based multi-granularity iris recognition algorithm (ELM-MGIR) has higher accuracy of 99.86%, and lower EER of 0.12% under the premise of real-time performance. The proposed ELM-MGIR algorithm outperforms other mainstream iris recognition algorithms.

Modal-Power-Based Haptic Motion Recognition

NASA Astrophysics Data System (ADS)

Kasahara, Yusuke; Shimono, Tomoyuki; Kuwahara, Hiroaki; Sato, Masataka; Ohnishi, Kouhei

Motion recognition based on sensory information is important for providing assistance to human using robots. Several studies have been carried out on motion recognition based on image information. However, in the motion of humans contact with an object can not be evaluated precisely by image-based recognition. This is because the considering force information is very important for describing contact motion. In this paper, a modal-power-based haptic motion recognition is proposed; modal power is considered to reveal information on both position and force. Modal power is considered to be one of the defining features of human motion. A motion recognition algorithm based on linear discriminant analysis is proposed to distinguish between similar motions. Haptic information is extracted using a bilateral master-slave system. Then, the observed motion is decomposed in terms of primitive functions in a modal space. The experimental results show the effectiveness of the proposed method.

Deep learning

NASA Astrophysics Data System (ADS)

Lecun, Yann; Bengio, Yoshua; Hinton, Geoffrey

2015-05-01

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

DIAC object recognition system

NASA Astrophysics Data System (ADS)

Buurman, Johannes

1992-03-01

This paper describes the object recognition system used in an intelligent robot cell. It is used to recognize and estimate pose and orientation of parts as they enter the cell. The parts are mostly metal and consist of polyhedral and cylindrical shapes. The system uses feature-based stereo vision to acquire a wireframe of the observed part. Features are defined as straight lines and ellipses, which lead to a wireframe of straight lines and circular arcs (the latter using a new algorithm). This wireframe is compared to a number of wire frame models obtained from the CAD database. Experimental results show that image processing hardware and parallelization may add considerably to the speed of the system.

Deep learning.

PubMed

LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey

2015-05-28

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

Modeling IrisCode and its variants as convex polyhedral cones and its security implications.

PubMed

Kong, Adams Wai-Kin

2013-03-01

IrisCode, developed by Daugman, in 1993, is the most influential iris recognition algorithm. A thorough understanding of IrisCode is essential, because over 100 million persons have been enrolled by this algorithm and many biometric personal identification and template protection methods have been developed based on IrisCode. This paper indicates that a template produced by IrisCode or its variants is a convex polyhedral cone in a hyperspace. Its central ray, being a rough representation of the original biometric signal, can be computed by a simple algorithm, which can often be implemented in one Matlab command line. The central ray is an expected ray and also an optimal ray of an objective function on a group of distributions. This algorithm is derived from geometric properties of a convex polyhedral cone but does not rely on any prior knowledge (e.g., iris images). The experimental results show that biometric templates, including iris and palmprint templates, produced by different recognition methods can be matched through the central rays in their convex polyhedral cones and that templates protected by a method extended from IrisCode can be broken into. These experimental results indicate that, without a thorough security analysis, convex polyhedral cone templates cannot be assumed secure. Additionally, the simplicity of the algorithm implies that even junior hackers without knowledge of advanced image processing and biometric databases can still break into protected templates and reveal relationships among templates produced by different recognition methods.

Target Recognition Using Neural Networks for Model Deformation Measurements

NASA Technical Reports Server (NTRS)

Ross, Richard W.; Hibler, David L.

1999-01-01

Optical measurements provide a non-invasive method for measuring deformation of wind tunnel models. Model deformation systems use targets mounted or painted on the surface of the model to identify known positions, and photogrammetric methods are used to calculate 3-D positions of the targets on the model from digital 2-D images. Under ideal conditions, the reflective targets are placed against a dark background and provide high-contrast images, aiding in target recognition. However, glints of light reflecting from the model surface, or reduced contrast caused by light source or model smoothness constraints, can compromise accurate target determination using current algorithmic methods. This paper describes a technique using a neural network and image processing technologies which increases the reliability of target recognition systems. Unlike algorithmic methods, the neural network can be trained to identify the characteristic patterns that distinguish targets from other objects of similar size and appearance and can adapt to changes in lighting and environmental conditions.

Implementation theory of distortion-invariant pattern recognition for optical and digital signal processing systems

NASA Astrophysics Data System (ADS)

Lhamon, Michael Earl

A pattern recognition system which uses complex correlation filter banks requires proportionally more computational effort than single-real valued filters. This introduces increased computation burden but also introduces a higher level of parallelism, that common computing platforms fail to identify. As a result, we consider algorithm mapping to both optical and digital processors. For digital implementation, we develop computationally efficient pattern recognition algorithms, referred to as, vector inner product operators that require less computational effort than traditional fast Fourier methods. These algorithms do not need correlation and they map readily onto parallel digital architectures, which imply new architectures for optical processors. These filters exploit circulant-symmetric matrix structures of the training set data representing a variety of distortions. By using the same mathematical basis as with the vector inner product operations, we are able to extend the capabilities of more traditional correlation filtering to what we refer to as "Super Images". These "Super Images" are used to morphologically transform a complicated input scene into a predetermined dot pattern. The orientation of the dot pattern is related to the rotational distortion of the object of interest. The optical implementation of "Super Images" yields feature reduction necessary for using other techniques, such as artificial neural networks. We propose a parallel digital signal processor architecture based on specific pattern recognition algorithms but general enough to be applicable to other similar problems. Such an architecture is classified as a data flow architecture. Instead of mapping an algorithm to an architecture, we propose mapping the DSP architecture to a class of pattern recognition algorithms. Today's optical processing systems have difficulties implementing full complex filter structures. Typically, optical systems (like the 4f correlators) are limited to phase-only implementation with lower detection performance than full complex electronic systems. Our study includes pseudo-random pixel encoding techniques for approximating full complex filtering. Optical filter bank implementation is possible and they have the advantage of time averaging the entire filter bank at real time rates. Time-averaged optical filtering is computational comparable to billions of digital operations-per-second. For this reason, we believe future trends in high speed pattern recognition will involve hybrid architectures of both optical and DSP elements.

Human activity recognition based on feature selection in smart home using back-propagation algorithm.

PubMed

Fang, Hongqing; He, Lei; Si, Hao; Liu, Peng; Xie, Xiaolei

2014-09-01

In this paper, Back-propagation(BP) algorithm has been used to train the feed forward neural network for human activity recognition in smart home environments, and inter-class distance method for feature selection of observed motion sensor events is discussed and tested. And then, the human activity recognition performances of neural network using BP algorithm have been evaluated and compared with other probabilistic algorithms: Naïve Bayes(NB) classifier and Hidden Markov Model(HMM). The results show that different feature datasets yield different activity recognition accuracy. The selection of unsuitable feature datasets increases the computational complexity and degrades the activity recognition accuracy. Furthermore, neural network using BP algorithm has relatively better human activity recognition performances than NB classifier and HMM. Copyright © 2014 ISA. Published by Elsevier Ltd. All rights reserved.

Augmented reality system

NASA Astrophysics Data System (ADS)

Lin, Chien-Liang; Su, Yu-Zheng; Hung, Min-Wei; Huang, Kuo-Cheng

2010-08-01

In recent years, Augmented Reality (AR)[1][2][3] is very popular in universities and research organizations. The AR technology has been widely used in Virtual Reality (VR) fields, such as sophisticated weapons, flight vehicle development, data model visualization, virtual training, entertainment and arts. AR has characteristics to enhance the display output as a real environment with specific user interactive functions or specific object recognitions. It can be use in medical treatment, anatomy training, precision instrument casting, warplane guidance, engineering and distance robot control. AR has a lot of vantages than VR. This system developed combines sensors, software and imaging algorithms to make users feel real, actual and existing. Imaging algorithms include gray level method, image binarization method, and white balance method in order to make accurate image recognition and overcome the effects of light.

AstroCV: Astronomy computer vision library

NASA Astrophysics Data System (ADS)

González, Roberto E.; Muñoz, Roberto P.; Hernández, Cristian A.

2018-04-01

AstroCV processes and analyzes big astronomical datasets, and is intended to provide a community repository of high performance Python and C++ algorithms used for image processing and computer vision. The library offers methods for object recognition, segmentation and classification, with emphasis in the automatic detection and classification of galaxies.

Comparison Analysis of Recognition Algorithms of Forest-Cover Objects on Hyperspectral Air-Borne and Space-Borne Images

NASA Astrophysics Data System (ADS)

Kozoderov, V. V.; Kondranin, T. V.; Dmitriev, E. V.

2017-12-01

The basic model for the recognition of natural and anthropogenic objects using their spectral and textural features is described in the problem of hyperspectral air-borne and space-borne imagery processing. The model is based on improvements of the Bayesian classifier that is a computational procedure of statistical decision making in machine-learning methods of pattern recognition. The principal component method is implemented to decompose the hyperspectral measurements on the basis of empirical orthogonal functions. Application examples are shown of various modifications of the Bayesian classifier and Support Vector Machine method. Examples are provided of comparing these classifiers and a metrical classifier that operates on finding the minimal Euclidean distance between different points and sets in the multidimensional feature space. A comparison is also carried out with the " K-weighted neighbors" method that is close to the nonparametric Bayesian classifier.

Pattern recognition with composite correlation filters designed with multi-object combinatorial optimization

DOE PAGES

Awwal, Abdul; Diaz-Ramirez, Victor H.; Cuevas, Andres; ...

2014-10-23

Composite correlation filters are used for solving a wide variety of pattern recognition problems. These filters are given by a combination of several training templates chosen by a designer in an ad hoc manner. In this work, we present a new approach for the design of composite filters based on multi-objective combinatorial optimization. Given a vast search space of training templates, an iterative algorithm is used to synthesize a filter with an optimized performance in terms of several competing criteria. Furthermore, by employing a suggested binary-search procedure a filter bank with a minimum number of filters can be constructed, formore » a prespecified trade-off of performance metrics. Computer simulation results obtained with the proposed method in recognizing geometrically distorted versions of a target in cluttered and noisy scenes are discussed and compared in terms of recognition performance and complexity with existing state-of-the-art filters.« less

Pattern recognition with composite correlation filters designed with multi-object combinatorial optimization

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

Awwal, Abdul; Diaz-Ramirez, Victor H.; Cuevas, Andres

Composite correlation filters are used for solving a wide variety of pattern recognition problems. These filters are given by a combination of several training templates chosen by a designer in an ad hoc manner. In this work, we present a new approach for the design of composite filters based on multi-objective combinatorial optimization. Given a vast search space of training templates, an iterative algorithm is used to synthesize a filter with an optimized performance in terms of several competing criteria. Furthermore, by employing a suggested binary-search procedure a filter bank with a minimum number of filters can be constructed, formore » a prespecified trade-off of performance metrics. Computer simulation results obtained with the proposed method in recognizing geometrically distorted versions of a target in cluttered and noisy scenes are discussed and compared in terms of recognition performance and complexity with existing state-of-the-art filters.« less

Using Markov Chains and Multi-Objective Optimization for Energy-Efficient Context Recognition †

PubMed Central

Janko, Vito

2017-01-01

The recognition of the user’s context with wearable sensing systems is a common problem in ubiquitous computing. However, the typically small battery of such systems often makes continuous recognition impractical. The strain on the battery can be reduced if the sensor setting is adapted to each context. We propose a method that efficiently finds near-optimal sensor settings for each context. It uses Markov chains to simulate the behavior of the system in different configurations and the multi-objective genetic algorithm to find a set of good non-dominated configurations. The method was evaluated on three real-life datasets and found good trade-offs between the system’s energy expenditure and the system’s accuracy. One of the solutions, for example, consumed five-times less energy than the default one, while sacrificing only two percentage points of accuracy. PMID:29286301

Fast and efficient search for MPEG-4 video using adjacent pixel intensity difference quantization histogram feature

NASA Astrophysics Data System (ADS)

Lee, Feifei; Kotani, Koji; Chen, Qiu; Ohmi, Tadahiro

2010-02-01

In this paper, a fast search algorithm for MPEG-4 video clips from video database is proposed. An adjacent pixel intensity difference quantization (APIDQ) histogram is utilized as the feature vector of VOP (video object plane), which had been reliably applied to human face recognition previously. Instead of fully decompressed video sequence, partially decoded data, namely DC sequence of the video object are extracted from the video sequence. Combined with active search, a temporal pruning algorithm, fast and robust video search can be realized. The proposed search algorithm has been evaluated by total 15 hours of video contained of TV programs such as drama, talk, news, etc. to search for given 200 MPEG-4 video clips which each length is 15 seconds. Experimental results show the proposed algorithm can detect the similar video clip in merely 80ms, and Equal Error Rate (ERR) of 2 % in drama and news categories are achieved, which are more accurately and robust than conventional fast video search algorithm.

Detecting objects in radiographs for homeland security

NASA Astrophysics Data System (ADS)

Prasad, Lakshman; Snyder, Hans

2005-05-01

We present a general scheme for segmenting a radiographic image into polygons that correspond to visual features. This decomposition provides a vectorized representation that is a high-level description of the image. The polygons correspond to objects or object parts present in the image. This characterization of radiographs allows the direct application of several shape recognition algorithms to identify objects. In this paper we describe the use of constrained Delaunay triangulations as a uniform foundational tool to achieve multiple visual tasks, namely image segmentation, shape decomposition, and parts-based shape matching. Shape decomposition yields parts that serve as tokens representing local shape characteristics. Parts-based shape matching enables the recognition of objects in the presence of occlusions, which commonly occur in radiographs. The polygonal representation of image features affords the efficient design and application of sophisticated geometric filtering methods to detect large-scale structural properties of objects in images. Finally, the representation of radiographs via polygons results in significant reduction of image file sizes and permits the scalable graphical representation of images, along with annotations of detected objects, in the SVG (scalable vector graphics) format that is proposed by the world wide web consortium (W3C). This is a textual representation that can be compressed and encrypted for efficient and secure transmission of information over wireless channels and on the Internet. In particular, our methods described here provide an algorithmic framework for developing image analysis tools for screening cargo at ports of entry for homeland security.

The Pandora multi-algorithm approach to automated pattern recognition in LAr TPC detectors

NASA Astrophysics Data System (ADS)

Marshall, J. S.; Blake, A. S. T.; Thomson, M. A.; Escudero, L.; de Vries, J.; Weston, J.; MicroBooNE Collaboration

2017-09-01

The development and operation of Liquid Argon Time Projection Chambers (LAr TPCs) for neutrino physics has created a need for new approaches to pattern recognition, in order to fully exploit the superb imaging capabilities offered by this technology. The Pandora Software Development Kit provides functionality to aid the process of designing, implementing and running pattern recognition algorithms. It promotes the use of a multi-algorithm approach to pattern recognition: individual algorithms each address a specific task in a particular topology; a series of many tens of algorithms then carefully builds-up a picture of the event. The input to the Pandora pattern recognition is a list of 2D Hits. The output from the chain of over 70 algorithms is a hierarchy of reconstructed 3D Particles, each with an identified particle type, vertex and direction.

The Pandora multi-algorithm approach to automated pattern recognition of cosmic-ray muon and neutrino events in the MicroBooNE detector

NASA Astrophysics Data System (ADS)

Acciarri, R.; Adams, C.; An, R.; Anthony, J.; Asaadi, J.; Auger, M.; Bagby, L.; Balasubramanian, S.; Baller, B.; Barnes, C.; Barr, G.; Bass, M.; Bay, F.; Bishai, M.; Blake, A.; Bolton, T.; Camilleri, L.; Caratelli, D.; Carls, B.; Castillo Fernandez, R.; Cavanna, F.; Chen, H.; Church, E.; Cianci, D.; Cohen, E.; Collin, G. H.; Conrad, J. M.; Convery, M.; Crespo-Anadón, J. I.; Del Tutto, M.; Devitt, D.; Dytman, S.; Eberly, B.; Ereditato, A.; Escudero Sanchez, L.; Esquivel, J.; Fadeeva, A. A.; Fleming, B. T.; Foreman, W.; Furmanski, A. P.; Garcia-Gamez, D.; Garvey, G. T.; Genty, V.; Goeldi, D.; Gollapinni, S.; Graf, N.; Gramellini, E.; Greenlee, H.; Grosso, R.; Guenette, R.; Hackenburg, A.; Hamilton, P.; Hen, O.; Hewes, J.; Hill, C.; Ho, J.; Horton-Smith, G.; Hourlier, A.; Huang, E.-C.; James, C.; Jan de Vries, J.; Jen, C.-M.; Jiang, L.; Johnson, R. A.; Joshi, J.; Jostlein, H.; Kaleko, D.; Karagiorgi, G.; Ketchum, W.; Kirby, B.; Kirby, M.; Kobilarcik, T.; Kreslo, I.; Laube, A.; Li, Y.; Lister, A.; Littlejohn, B. R.; Lockwitz, S.; Lorca, D.; Louis, W. C.; Luethi, M.; Lundberg, B.; Luo, X.; Marchionni, A.; Mariani, C.; Marshall, J.; Martinez Caicedo, D. A.; Meddage, V.; Miceli, T.; Mills, G. B.; Moon, J.; Mooney, M.; Moore, C. D.; Mousseau, J.; Murrells, R.; Naples, D.; Nienaber, P.; Nowak, J.; Palamara, O.; Paolone, V.; Papavassiliou, V.; Pate, S. F.; Pavlovic, Z.; Piasetzky, E.; Porzio, D.; Pulliam, G.; Qian, X.; Raaf, J. L.; Rafique, A.; Rochester, L.; Rudolf von Rohr, C.; Russell, B.; Schmitz, D. W.; Schukraft, A.; Seligman, W.; Shaevitz, M. H.; Sinclair, J.; Smith, A.; Snider, E. L.; Soderberg, M.; Söldner-Rembold, S.; Soleti, S. R.; Spentzouris, P.; Spitz, J.; St. John, J.; Strauss, T.; Szelc, A. M.; Tagg, N.; Terao, K.; Thomson, M.; Toups, M.; Tsai, Y.-T.; Tufanli, S.; Usher, T.; Van De Pontseele, W.; Van de Water, R. G.; Viren, B.; Weber, M.; Wickremasinghe, D. A.; Wolbers, S.; Wongjirad, T.; Woodruff, K.; Yang, T.; Yates, L.; Zeller, G. P.; Zennamo, J.; Zhang, C.

2018-01-01

The development and operation of liquid-argon time-projection chambers for neutrino physics has created a need for new approaches to pattern recognition in order to fully exploit the imaging capabilities offered by this technology. Whereas the human brain can excel at identifying features in the recorded events, it is a significant challenge to develop an automated, algorithmic solution. The Pandora Software Development Kit provides functionality to aid the design and implementation of pattern-recognition algorithms. It promotes the use of a multi-algorithm approach to pattern recognition, in which individual algorithms each address a specific task in a particular topology. Many tens of algorithms then carefully build up a picture of the event and, together, provide a robust automated pattern-recognition solution. This paper describes details of the chain of over one hundred Pandora algorithms and tools used to reconstruct cosmic-ray muon and neutrino events in the MicroBooNE detector. Metrics that assess the current pattern-recognition performance are presented for simulated MicroBooNE events, using a selection of final-state event topologies.

Image recognition of clipped stigma traces in rice seeds

NASA Astrophysics Data System (ADS)

Cheng, F.; Ying, YB

2005-11-01

The objective of this research is to develop algorithm to recognize clipped stigma traces in rice seeds using image processing. At first, the micro-configuration of clipped stigma traces was observed with electronic scanning microscope. Then images of rice seeds were acquired with a color machine vision system. A digital image-processing algorithm based on morphological operations and Hough transform was developed to inspect the occurrence of clipped stigma traces. Five varieties of Jinyou402, Shanyou10, Zhongyou207, Jiayou and you3207 were evaluated. The algorithm was implemented with all image sets using a Matlab 6.5 procedure. The results showed that the algorithm achieved an average accuracy of 96%. The algorithm was proved to be insensitive to the different rice seed varieties.

Toward faster and more accurate star sensors using recursive centroiding and star identification

NASA Astrophysics Data System (ADS)

Samaan, Malak Anees

The objective of this research is to study different novel developed techniques for spacecraft attitude determination methods using star tracker sensors. This dissertation addresses various issues on developing improved star tracker software, presents new approaches for better performance of star trackers, and considers applications to realize high precision attitude estimates. Star-sensors are often included in a spacecraft attitude-system instrument suite, where high accuracy pointing capability is required. Novel methods for image processing, camera parameters ground calibration, autonomous star pattern recognition, and recursive star identification are researched and implemented to achieve high accuracy and a high frame rate star tracker that can be used for many space missions. This dissertation presents the methods and algorithms implemented for the one Field of View 'FOV'Star NavI sensor that was tested aboard the STS-107 mission in spring 2003 and the two fields of view StarNavII sensor for the EO-3 spacecraft scheduled for launch in 2007. The results of this research enable advances in spacecraft attitude determination based upon real time star sensing and pattern recognition. Building upon recent developments in image processing, pattern recognition algorithms, focal plane detectors, electro-optics, and microprocessors, the star tracker concept utilized in this research has the following key objectives for spacecraft of the future: lower cost, lower mass and smaller volume, increased robustness to environment-induced aging and instrument response variations, increased adaptability and autonomy via recursive self-calibration and health-monitoring on-orbit. Many of these attributes are consequences of improved algorithms that are derived in this dissertation.

Biological object recognition in μ-radiography images

NASA Astrophysics Data System (ADS)

Prochazka, A.; Dammer, J.; Weyda, F.; Sopko, V.; Benes, J.; Zeman, J.; Jandejsek, I.

2015-03-01

This study presents an applicability of real-time microradiography to biological objects, namely to horse chestnut leafminer, Cameraria ohridella (Insecta: Lepidoptera, Gracillariidae) and following image processing focusing on image segmentation and object recognition. The microradiography of insects (such as horse chestnut leafminer) provides a non-invasive imaging that leaves the organisms alive. The imaging requires a high spatial resolution (micrometer scale) radiographic system. Our radiographic system consists of a micro-focus X-ray tube and two types of detectors. The first is a charge integrating detector (Hamamatsu flat panel), the second is a pixel semiconductor detector (Medipix2 detector). The latter allows detection of single quantum photon of ionizing radiation. We obtained numerous horse chestnuts leafminer pupae in several microradiography images easy recognizable in automatic mode using the image processing methods. We implemented an algorithm that is able to count a number of dead and alive pupae in images. The algorithm was based on two methods: 1) noise reduction using mathematical morphology filters, 2) Canny edge detection. The accuracy of the algorithm is higher for the Medipix2 (average recall for detection of alive pupae =0.99, average recall for detection of dead pupae =0.83), than for the flat panel (average recall for detection of alive pupae =0.99, average recall for detection of dead pupae =0.77). Therefore, we conclude that Medipix2 has lower noise and better displays contours (edges) of biological objects. Our method allows automatic selection and calculation of dead and alive chestnut leafminer pupae. It leads to faster monitoring of the population of one of the world's important insect pest.

Performance Review of Harmony Search, Differential Evolution and Particle Swarm Optimization

NASA Astrophysics Data System (ADS)

Mohan Pandey, Hari

2017-08-01

Metaheuristic algorithms are effective in the design of an intelligent system. These algorithms are widely applied to solve complex optimization problems, including image processing, big data analytics, language processing, pattern recognition and others. This paper presents a performance comparison of three meta-heuristic algorithms, namely Harmony Search, Differential Evolution, and Particle Swarm Optimization. These algorithms are originated altogether from different fields of meta-heuristics yet share a common objective. The standard benchmark functions are used for the simulation. Statistical tests are conducted to derive a conclusion on the performance. The key motivation to conduct this research is to categorize the computational capabilities, which might be useful to the researchers.

Recognition of Simple 3D Geometrical Objects under Partial Occlusion

NASA Astrophysics Data System (ADS)

Barchunova, Alexandra; Sommer, Gerald

In this paper we present a novel procedure for contour-based recognition of partially occluded three-dimensional objects. In our approach we use images of real and rendered objects whose contours have been deformed by a restricted change of the viewpoint. The preparatory part consists of contour extraction, preprocessing, local structure analysis and feature extraction. The main part deals with an extended construction and functionality of the classifier ensemble Adaptive Occlusion Classifier (AOC). It relies on a hierarchical fragmenting algorithm to perform a local structure analysis which is essential when dealing with occlusions. In the experimental part of this paper we present classification results for five classes of simple geometrical figures: prism, cylinder, half cylinder, a cube, and a bridge. We compare classification results for three classical feature extractors: Fourier descriptors, pseudo Zernike and Zernike moments.

Localized contourlet features in vehicle make and model recognition

NASA Astrophysics Data System (ADS)

Zafar, I.; Edirisinghe, E. A.; Acar, B. S.

2009-02-01

Automatic vehicle Make and Model Recognition (MMR) systems provide useful performance enhancements to vehicle recognitions systems that are solely based on Automatic Number Plate Recognition (ANPR) systems. Several vehicle MMR systems have been proposed in literature. In parallel to this, the usefulness of multi-resolution based feature analysis techniques leading to efficient object classification algorithms have received close attention from the research community. To this effect, Contourlet transforms that can provide an efficient directional multi-resolution image representation has recently been introduced. Already an attempt has been made in literature to use Curvelet/Contourlet transforms in vehicle MMR. In this paper we propose a novel localized feature detection method in Contourlet transform domain that is capable of increasing the classification rates up to 4%, as compared to the previously proposed Contourlet based vehicle MMR approach in which the features are non-localized and thus results in sub-optimal classification. Further we show that the proposed algorithm can achieve the increased classification accuracy of 96% at significantly lower computational complexity due to the use of Two Dimensional Linear Discriminant Analysis (2DLDA) for dimensionality reduction by preserving the features with high between-class variance and low inter-class variance.

A model-based approach for detection of runways and other objects in image sequences acquired using an on-board camera

NASA Technical Reports Server (NTRS)

Kasturi, Rangachar; Devadiga, Sadashiva; Tang, Yuan-Liang

1994-01-01

This research was initiated as a part of the Advanced Sensor and Imaging System Technology (ASSIST) program at NASA Langley Research Center. The primary goal of this research is the development of image analysis algorithms for the detection of runways and other objects using an on-board camera. Initial effort was concentrated on images acquired using a passive millimeter wave (PMMW) sensor. The images obtained using PMMW sensors under poor visibility conditions due to atmospheric fog are characterized by very low spatial resolution but good image contrast compared to those images obtained using sensors operating in the visible spectrum. Algorithms developed for analyzing these images using a model of the runway and other objects are described in Part 1 of this report. Experimental verification of these algorithms was limited to a sequence of images simulated from a single frame of PMMW image. Subsequent development and evaluation of algorithms was done using video image sequences. These images have better spatial and temporal resolution compared to PMMW images. Algorithms for reliable recognition of runways and accurate estimation of spatial position of stationary objects on the ground have been developed and evaluated using several image sequences. These algorithms are described in Part 2 of this report. A list of all publications resulting from this work is also included.

A GPU-paralleled implementation of an enhanced face recognition algorithm

NASA Astrophysics Data System (ADS)

Chen, Hao; Liu, Xiyang; Shao, Shuai; Zan, Jiguo

2013-03-01

Face recognition algorithm based on compressed sensing and sparse representation is hotly argued in these years. The scheme of this algorithm increases recognition rate as well as anti-noise capability. However, the computational cost is expensive and has become a main restricting factor for real world applications. In this paper, we introduce a GPU-accelerated hybrid variant of face recognition algorithm named parallel face recognition algorithm (pFRA). We describe here how to carry out parallel optimization design to take full advantage of many-core structure of a GPU. The pFRA is tested and compared with several other implementations under different data sample size. Finally, Our pFRA, implemented with NVIDIA GPU and Computer Unified Device Architecture (CUDA) programming model, achieves a significant speedup over the traditional CPU implementations.

Data Reduction Algorithm Using Nonnegative Matrix Factorization with Nonlinear Constraints

NASA Astrophysics Data System (ADS)

Sembiring, Pasukat

2017-12-01

Processing ofdata with very large dimensions has been a hot topic in recent decades. Various techniques have been proposed in order to execute the desired information or structure. Non- Negative Matrix Factorization (NMF) based on non-negatives data has become one of the popular methods for shrinking dimensions. The main strength of this method is non-negative object, the object model by a combination of some basic non-negative parts, so as to provide a physical interpretation of the object construction. The NMF is a dimension reduction method thathasbeen used widely for numerous applications including computer vision,text mining, pattern recognitions,and bioinformatics. Mathematical formulation for NMF did not appear as a convex optimization problem and various types of algorithms have been proposed to solve the problem. The Framework of Alternative Nonnegative Least Square(ANLS) are the coordinates of the block formulation approaches that have been proven reliable theoretically and empirically efficient. This paper proposes a new algorithm to solve NMF problem based on the framework of ANLS.This algorithm inherits the convergenceproperty of the ANLS framework to nonlinear constraints NMF formulations.

Communication target object recognition for D2D connection with feature size limit

NASA Astrophysics Data System (ADS)

Ok, Jiheon; Kim, Soochang; Kim, Young-hoon; Lee, Chulhee

2015-03-01

Recently, a new concept of device-to-device (D2D) communication, which is called "point-and-link communication" has attracted great attentions due to its intuitive and simple operation. This approach enables user to communicate with target devices without any pre-identification information such as SSIDs, MAC addresses by selecting the target image displayed on the user's own device. In this paper, we present an efficient object matching algorithm that can be applied to look(point)-and-link communications for mobile services. Due to the limited channel bandwidth and low computational power of mobile terminals, the matching algorithm should satisfy low-complexity, low-memory and realtime requirements. To meet these requirements, we propose fast and robust feature extraction by considering the descriptor size and processing time. The proposed algorithm utilizes a HSV color histogram, SIFT (Scale Invariant Feature Transform) features and object aspect ratios. To reduce the descriptor size under 300 bytes, a limited number of SIFT key points were chosen as feature points and histograms were binarized while maintaining required performance. Experimental results show the robustness and the efficiency of the proposed algorithm.

Ocean feature recognition using genetic algorithms with fuzzy fitness functions (GA/F3)

NASA Technical Reports Server (NTRS)

Ankenbrandt, C. A.; Buckles, B. P.; Petry, F. E.; Lybanon, M.

1990-01-01

A model for genetic algorithms with semantic nets is derived for which the relationships between concepts is depicted as a semantic net. An organism represents the manner in which objects in a scene are attached to concepts in the net. Predicates between object pairs are continuous valued truth functions in the form of an inverse exponential function (e sub beta lxl). 1:n relationships are combined via the fuzzy OR (Max (...)). Finally, predicates between pairs of concepts are resolved by taking the average of the combined predicate values of the objects attached to the concept at the tail of the arc representing the predicate in the semantic net. The method is illustrated by applying it to the identification of oceanic features in the North Atlantic.

Target recognition of ladar range images using slice image: comparison of four improved algorithms

NASA Astrophysics Data System (ADS)

Xia, Wenze; Han, Shaokun; Cao, Jingya; Wang, Liang; Zhai, Yu; Cheng, Yang

2017-07-01

Compared with traditional 3-D shape data, ladar range images possess properties of strong noise, shape degeneracy, and sparsity, which make feature extraction and representation difficult. The slice image is an effective feature descriptor to resolve this problem. We propose four improved algorithms on target recognition of ladar range images using slice image. In order to improve resolution invariance of the slice image, mean value detection instead of maximum value detection is applied in these four improved algorithms. In order to improve rotation invariance of the slice image, three new improved feature descriptors-which are feature slice image, slice-Zernike moments, and slice-Fourier moments-are applied to the last three improved algorithms, respectively. Backpropagation neural networks are used as feature classifiers in the last two improved algorithms. The performance of these four improved recognition systems is analyzed comprehensively in the aspects of the three invariances, recognition rate, and execution time. The final experiment results show that the improvements for these four algorithms reach the desired effect, the three invariances of feature descriptors are not directly related to the final recognition performance of recognition systems, and these four improved recognition systems have different performances under different conditions.

Finger vein recognition based on finger crease location

NASA Astrophysics Data System (ADS)

Lu, Zhiying; Ding, Shumeng; Yin, Jing

2016-07-01

Finger vein recognition technology has significant advantages over other methods in terms of accuracy, uniqueness, and stability, and it has wide promising applications in the field of biometric recognition. We propose using finger creases to locate and extract an object region. Then we use linear fitting to overcome the problem of finger rotation in the plane. The method of modular adaptive histogram equalization (MAHE) is presented to enhance image contrast and reduce computational cost. To extract the finger vein features, we use a fusion method, which can obtain clear and distinguishable vein patterns under different conditions. We used the Hausdorff average distance algorithm to examine the recognition performance of the system. The experimental results demonstrate that MAHE can better balance the recognition accuracy and the expenditure of time compared with three other methods. Our resulting equal error rate throughout the total procedure was 3.268% in a database of 153 finger vein images.

Target recognitions in multiple-camera closed-circuit television using color constancy

NASA Astrophysics Data System (ADS)

Soori, Umair; Yuen, Peter; Han, Ji Wen; Ibrahim, Izzati; Chen, Wentao; Hong, Kan; Merfort, Christian; James, David; Richardson, Mark

2013-04-01

People tracking in crowded scenes from closed-circuit television (CCTV) footage has been a popular and challenging task in computer vision. Due to the limited spatial resolution in the CCTV footage, the color of people's dress may offer an alternative feature for their recognition and tracking. However, there are many factors, such as variable illumination conditions, viewing angles, and camera calibration, that may induce illusive modification of intrinsic color signatures of the target. Our objective is to recognize and track targets in multiple camera views using color as the detection feature, and to understand if a color constancy (CC) approach may help to reduce these color illusions due to illumination and camera artifacts and thereby improve target recognition performance. We have tested a number of CC algorithms using various color descriptors to assess the efficiency of target recognition from a real multicamera Imagery Library for Intelligent Detection Systems (i-LIDS) data set. Various classifiers have been used for target detection, and the figure of merit to assess the efficiency of target recognition is achieved through the area under the receiver operating characteristics (AUROC). We have proposed two modifications of luminance-based CC algorithms: one with a color transfer mechanism and the other using a pixel-wise sigmoid function for an adaptive dynamic range compression, a method termed enhanced luminance reflectance CC (ELRCC). We found that both algorithms improve the efficiency of target recognitions substantially better than that of the raw data without CC treatment, and in some cases the ELRCC improves target tracking by over 100% within the AUROC assessment metric. The performance of the ELRCC has been assessed over 10 selected targets from three different camera views of the i-LIDS footage, and the averaged target recognition efficiency over all these targets is found to be improved by about 54% in AUROC after the data are processed by the proposed ELRCC algorithm. This amount of improvement represents a reduction of probability of false alarm by about a factor of 5 at the probability of detection of 0.5. Our study concerns mainly the detection of colored targets; and issues for the recognition of white or gray targets will be addressed in a forthcoming study.

Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems.

PubMed

Gao, Lei; Bourke, A K; Nelson, John

2014-06-01

Physical activity has a positive impact on people's well-being and it had been shown to decrease the occurrence of chronic diseases in the older adult population. To date, a substantial amount of research studies exist, which focus on activity recognition using inertial sensors. Many of these studies adopt a single sensor approach and focus on proposing novel features combined with complex classifiers to improve the overall recognition accuracy. In addition, the implementation of the advanced feature extraction algorithms and the complex classifiers exceed the computing ability of most current wearable sensor platforms. This paper proposes a method to adopt multiple sensors on distributed body locations to overcome this problem. The objective of the proposed system is to achieve higher recognition accuracy with "light-weight" signal processing algorithms, which run on a distributed computing based sensor system comprised of computationally efficient nodes. For analysing and evaluating the multi-sensor system, eight subjects were recruited to perform eight normal scripted activities in different life scenarios, each repeated three times. Thus a total of 192 activities were recorded resulting in 864 separate annotated activity states. The methods for designing such a multi-sensor system required consideration of the following: signal pre-processing algorithms, sampling rate, feature selection and classifier selection. Each has been investigated and the most appropriate approach is selected to achieve a trade-off between recognition accuracy and computing execution time. A comparison of six different systems, which employ single or multiple sensors, is presented. The experimental results illustrate that the proposed multi-sensor system can achieve an overall recognition accuracy of 96.4% by adopting the mean and variance features, using the Decision Tree classifier. The results demonstrate that elaborate classifiers and feature sets are not required to achieve high recognition accuracies on a multi-sensor system. Copyright © 2014 IPEM. Published by Elsevier Ltd. All rights reserved.

A modified approach combining FNEA and watershed algorithms for segmenting remotely-sensed optical images

NASA Astrophysics Data System (ADS)

Liu, Likun

2018-01-01

In the field of remote sensing image processing, remote sensing image segmentation is a preliminary step for later analysis of remote sensing image processing and semi-auto human interpretation, fully-automatic machine recognition and learning. Since 2000, a technique of object-oriented remote sensing image processing method and its basic thought prevails. The core of the approach is Fractal Net Evolution Approach (FNEA) multi-scale segmentation algorithm. The paper is intent on the research and improvement of the algorithm, which analyzes present segmentation algorithms and selects optimum watershed algorithm as an initialization. Meanwhile, the algorithm is modified by modifying an area parameter, and then combining area parameter with a heterogeneous parameter further. After that, several experiments is carried on to prove the modified FNEA algorithm, compared with traditional pixel-based method (FCM algorithm based on neighborhood information) and combination of FNEA and watershed, has a better segmentation result.

Pedestrian recognition using automotive radar sensors

NASA Astrophysics Data System (ADS)

Bartsch, A.; Fitzek, F.; Rasshofer, R. H.

2012-09-01

The application of modern series production automotive radar sensors to pedestrian recognition is an important topic in research on future driver assistance systems. The aim of this paper is to understand the potential and limits of such sensors in pedestrian recognition. This knowledge could be used to develop next generation radar sensors with improved pedestrian recognition capabilities. A new raw radar data signal processing algorithm is proposed that allows deep insights into the object classification process. The impact of raw radar data properties can be directly observed in every layer of the classification system by avoiding machine learning and tracking. This gives information on the limiting factors of raw radar data in terms of classification decision making. To accomplish the very challenging distinction between pedestrians and static objects, five significant and stable object features from the spatial distribution and Doppler information are found. Experimental results with data from a 77 GHz automotive radar sensor show that over 95% of pedestrians can be classified correctly under optimal conditions, which is compareable to modern machine learning systems. The impact of the pedestrian's direction of movement, occlusion, antenna beam elevation angle, linear vehicle movement, and other factors are investigated and discussed. The results show that under real life conditions, radar only based pedestrian recognition is limited due to insufficient Doppler frequency and spatial resolution as well as antenna side lobe effects.

The Pandora multi-algorithm approach to automated pattern recognition of cosmic-ray muon and neutrino events in the MicroBooNE detector

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

Acciarri, R.; Adams, C.; An, R.

The development and operation of Liquid-Argon Time-Projection Chambers for neutrino physics has created a need for new approaches to pattern recognition in order to fully exploit the imaging capabilities offered by this technology. Whereas the human brain can excel at identifying features in the recorded events, it is a significant challenge to develop an automated, algorithmic solution. The Pandora Software Development Kit provides functionality to aid the design and implementation of pattern-recognition algorithms. It promotes the use of a multi-algorithm approach to pattern recognition, in which individual algorithms each address a specific task in a particular topology. Many tens ofmore » algorithms then carefully build up a picture of the event and, together, provide a robust automated pattern-recognition solution. This paper describes details of the chain of over one hundred Pandora algorithms and tools used to reconstruct cosmic-ray muon and neutrino events in the MicroBooNE detector. Metrics that assess the current pattern-recognition performance are presented for simulated MicroBooNE events, using a selection of final-state event topologies.« less

The Pandora multi-algorithm approach to automated pattern recognition of cosmic-ray muon and neutrino events in the MicroBooNE detector

DOE PAGES

Acciarri, R.; Adams, C.; An, R.; ...

2018-01-29

The development and operation of Liquid-Argon Time-Projection Chambers for neutrino physics has created a need for new approaches to pattern recognition in order to fully exploit the imaging capabilities offered by this technology. Whereas the human brain can excel at identifying features in the recorded events, it is a significant challenge to develop an automated, algorithmic solution. The Pandora Software Development Kit provides functionality to aid the design and implementation of pattern-recognition algorithms. It promotes the use of a multi-algorithm approach to pattern recognition, in which individual algorithms each address a specific task in a particular topology. Many tens ofmore » algorithms then carefully build up a picture of the event and, together, provide a robust automated pattern-recognition solution. This paper describes details of the chain of over one hundred Pandora algorithms and tools used to reconstruct cosmic-ray muon and neutrino events in the MicroBooNE detector. Metrics that assess the current pattern-recognition performance are presented for simulated MicroBooNE events, using a selection of final-state event topologies.« less

Information surfing with the JHU/APL coherent imager

NASA Astrophysics Data System (ADS)

Ratto, Christopher R.; Shipley, Kara R.; Beagley, Nathaniel; Wolfe, Kevin C.

2015-05-01

The ability to perform remote forensics in situ is an important application of autonomous undersea vehicles (AUVs). Forensics objectives may include remediation of mines and/or unexploded ordnance, as well as monitoring of seafloor infrastructure. At JHU/APL, digital holography is being explored for the potential application to underwater imaging and integration with an AUV. In previous work, a feature-based approach was developed for processing the holographic imagery and performing object recognition. In this work, the results of the image processing method were incorporated into a Bayesian framework for autonomous path planning referred to as information surfing. The framework was derived assuming that the location of the object of interest is known a priori, but the type of object and its pose are unknown. The path-planning algorithm adaptively modifies the trajectory of the sensing platform based on historical performance of object and pose classification. The algorithm is called information surfing because the direction of motion is governed by the local information gradient. Simulation experiments were carried out using holographic imagery collected from submerged objects. The autonomous sensing algorithm was compared to a deterministic sensing CONOPS, and demonstrated improved accuracy and faster convergence in several cases.

Score-Level Fusion of Phase-Based and Feature-Based Fingerprint Matching Algorithms

NASA Astrophysics Data System (ADS)

Ito, Koichi; Morita, Ayumi; Aoki, Takafumi; Nakajima, Hiroshi; Kobayashi, Koji; Higuchi, Tatsuo

This paper proposes an efficient fingerprint recognition algorithm combining phase-based image matching and feature-based matching. In our previous work, we have already proposed an efficient fingerprint recognition algorithm using Phase-Only Correlation (POC), and developed commercial fingerprint verification units for access control applications. The use of Fourier phase information of fingerprint images makes it possible to achieve robust recognition for weakly impressed, low-quality fingerprint images. This paper presents an idea of improving the performance of POC-based fingerprint matching by combining it with feature-based matching, where feature-based matching is introduced in order to improve recognition efficiency for images with nonlinear distortion. Experimental evaluation using two different types of fingerprint image databases demonstrates efficient recognition performance of the combination of the POC-based algorithm and the feature-based algorithm.

A new FOD recognition algorithm based on multi-source information fusion and experiment analysis

NASA Astrophysics Data System (ADS)

Li, Yu; Xiao, Gang

2011-08-01

Foreign Object Debris (FOD) is a kind of substance, debris or article alien to an aircraft or system, which would potentially cause huge damage when it appears on the airport runway. Due to the airport's complex circumstance, quick and precise detection of FOD target on the runway is one of the important protections for airplane's safety. A multi-sensor system including millimeter-wave radar and Infrared image sensors is introduced and a developed new FOD detection and recognition algorithm based on inherent feature of FOD is proposed in this paper. Firstly, the FOD's location and coordinate can be accurately obtained by millimeter-wave radar, and then according to the coordinate IR camera will take target images and background images. Secondly, in IR image the runway's edges which are straight lines can be extracted by using Hough transformation method. The potential target region, that is, runway region, can be segmented from the whole image. Thirdly, background subtraction is utilized to localize the FOD target in runway region. Finally, in the detailed small images of FOD target, a new characteristic is discussed and used in target classification. The experiment results show that this algorithm can effectively reduce the computational complexity, satisfy the real-time requirement and possess of high detection and recognition probability.

Model and algorithmic framework for detection and correction of cognitive errors.

PubMed

Feki, Mohamed Ali; Biswas, Jit; Tolstikov, Andrei

2009-01-01

This paper outlines an approach that we are taking for elder-care applications in the smart home, involving cognitive errors and their compensation. Our approach involves high level modeling of daily activities of the elderly by breaking down these activities into smaller units, which can then be automatically recognized at a low level by collections of sensors placed in the homes of the elderly. This separation allows us to employ plan recognition algorithms and systems at a high level, while developing stand-alone activity recognition algorithms and systems at a low level. It also allows the mixing and matching of multi-modality sensors of various kinds that go to support the same high level requirement. Currently our plan recognition algorithms are still at a conceptual stage, whereas a number of low level activity recognition algorithms and systems have been developed. Herein we present our model for plan recognition, providing a brief survey of the background literature. We also present some concrete results that we have achieved for activity recognition, emphasizing how these results are incorporated into the overall plan recognition system.

Physical environment virtualization for human activities recognition

NASA Astrophysics Data System (ADS)

Poshtkar, Azin; Elangovan, Vinayak; Shirkhodaie, Amir; Chan, Alex; Hu, Shuowen

2015-05-01

Human activity recognition research relies heavily on extensive datasets to verify and validate performance of activity recognition algorithms. However, obtaining real datasets are expensive and highly time consuming. A physics-based virtual simulation can accelerate the development of context based human activity recognition algorithms and techniques by generating relevant training and testing videos simulating diverse operational scenarios. In this paper, we discuss in detail the requisite capabilities of a virtual environment to aid as a test bed for evaluating and enhancing activity recognition algorithms. To demonstrate the numerous advantages of virtual environment development, a newly developed virtual environment simulation modeling (VESM) environment is presented here to generate calibrated multisource imagery datasets suitable for development and testing of recognition algorithms for context-based human activities. The VESM environment serves as a versatile test bed to generate a vast amount of realistic data for training and testing of sensor processing algorithms. To demonstrate the effectiveness of VESM environment, we present various simulated scenarios and processed results to infer proper semantic annotations from the high fidelity imagery data for human-vehicle activity recognition under different operational contexts.

Vehicle logo recognition using multi-level fusion model

NASA Astrophysics Data System (ADS)

Ming, Wei; Xiao, Jianli

2018-04-01

Vehicle logo recognition plays an important role in manufacturer identification and vehicle recognition. This paper proposes a new vehicle logo recognition algorithm. It has a hierarchical framework, which consists of two fusion levels. At the first level, a feature fusion model is employed to map the original features to a higher dimension feature space. In this space, the vehicle logos become more recognizable. At the second level, a weighted voting strategy is proposed to promote the accuracy and the robustness of the recognition results. To evaluate the performance of the proposed algorithm, extensive experiments are performed, which demonstrate that the proposed algorithm can achieve high recognition accuracy and work robustly.

Three-dimensional obstacle classification in laser range data

NASA Astrophysics Data System (ADS)

Armbruster, Walter; Bers, Karl-Heinz

1998-10-01

The threat of hostile surveillance and weapon systems require military aircraft to fly under extreme conditions such as low altitude, high speed, poor visibility and incomplete terrain information. The probability of collision with natural and man-made obstacles during such contour missions is high if detection capability is restricted to conventional vision aids. Forward-looking scanning laser rangefinders which are presently being flight tested and evaluated at German proving grounds, provide a possible solution, having a large field of view, high angular and range resolution, a high pulse repetition rate, and sufficient pulse energy to register returns from wires at over 500 m range (depends on the system) with a high hit-and-detect probability. Despite the efficiency of the sensor, acceptance of current obstacle warning systems by test pilots is not very high, mainly due to the systems' inadequacies in obstacle recognition and visualization. This has motivated the development and the testing of more advanced 3d-scene analysis algorithm at FGAN-FIM to replace the obstacle recognition component of current warning systems. The basic ideas are to increase the recognition probability and to reduce the false alarm rate for hard-to-extract obstacles such as wires, by using more readily recognizable objects such as terrain, poles, pylons, trees, etc. by implementing a hierarchical classification procedure to generate a parametric description of the terrain surface as well as the class, position, orientation, size and shape of all objects in the scene. The algorithms can be used for other applications such as terrain following, autonomous obstacle avoidance, and automatic target recognition.

Recognition of fiducial marks applied to robotic systems. Thesis

NASA Technical Reports Server (NTRS)

Georges, Wayne D.

1991-01-01

The objective was to devise a method to determine the position and orientation of the links of a PUMA 560 using fiducial marks. As a result, it is necessary to design fiducial marks and a corresponding feature extraction algorithm. The marks used are composites of three basic shapes, a circle, an equilateral triangle and a square. Once a mark is imaged, it is thresholded and the borders of each shape are extracted. These borders are subsequently used in a feature extraction algorithm. Two feature extraction algorithms are used to determine which one produces the most reliable results. The first algorithm is based on moment invariants and the second is based on the discrete version of the psi-s curve of the boundary. The latter algorithm is clearly superior for this application.

[Multi-Target Recognition of Internal and External Defects of Potato by Semi-Transmission Hyperspectral Imaging and Manifold Learning Algorithm].

PubMed

Huang, Tao; Li, Xiao-yu; Jin, Rui; Ku, Jing; Xu, Sen-miao; Xu, Meng-ling; Wu, Zhen-zhong; Kong, De-guo

2015-04-01

The present paper put forward a non-destructive detection method which combines semi-transmission hyperspectral imaging technology with manifold learning dimension reduction algorithm and least squares support vector machine (LSSVM) to recognize internal and external defects in potatoes simultaneously. Three hundred fifteen potatoes were bought in farmers market as research object, and semi-transmission hyperspectral image acquisition system was constructed to acquire the hyperspectral images of normal external defects (bud and green rind) and internal defect (hollow heart) potatoes. In order to conform to the actual production, defect part is randomly put right, side and back to the acquisition probe when the hyperspectral images of external defects potatoes are acquired. The average spectrums (390-1,040 nm) were extracted from the region of interests for spectral preprocessing. Then three kinds of manifold learning algorithm were respectively utilized to reduce the dimension of spectrum data, including supervised locally linear embedding (SLLE), locally linear embedding (LLE) and isometric mapping (ISOMAP), the low-dimensional data gotten by manifold learning algorithms is used as model input, Error Correcting Output Code (ECOC) and LSSVM were combined to develop the multi-target classification model. By comparing and analyzing results of the three models, we concluded that SLLE is the optimal manifold learning dimension reduction algorithm, and the SLLE-LSSVM model is determined to get the best recognition rate for recognizing internal and external defects potatoes. For test set data, the single recognition rate of normal, bud, green rind and hollow heart potato reached 96.83%, 86.96%, 86.96% and 95% respectively, and he hybrid recognition rate was 93.02%. The results indicate that combining the semi-transmission hyperspectral imaging technology with SLLE-LSSVM is a feasible qualitative analytical method which can simultaneously recognize the internal and external defects potatoes and also provide technical reference for rapid on-line non-destructive detecting of the internal and external defects potatoes.

Automated detection and recognition of wildlife using thermal cameras.

PubMed

Christiansen, Peter; Steen, Kim Arild; Jørgensen, Rasmus Nyholm; Karstoft, Henrik

2014-07-30

In agricultural mowing operations, thousands of animals are injured or killed each year, due to the increased working widths and speeds of agricultural machinery. Detection and recognition of wildlife within the agricultural fields is important to reduce wildlife mortality and, thereby, promote wildlife-friendly farming. The work presented in this paper contributes to the automated detection and classification of animals in thermal imaging. The methods and results are based on top-view images taken manually from a lift to motivate work towards unmanned aerial vehicle-based detection and recognition. Hot objects are detected based on a threshold dynamically adjusted to each frame. For the classification of animals, we propose a novel thermal feature extraction algorithm. For each detected object, a thermal signature is calculated using morphological operations. The thermal signature describes heat characteristics of objects and is partly invariant to translation, rotation, scale and posture. The discrete cosine transform (DCT) is used to parameterize the thermal signature and, thereby, calculate a feature vector, which is used for subsequent classification. Using a k-nearest-neighbor (kNN) classifier, animals are discriminated from non-animals with a balanced classification accuracy of 84.7% in an altitude range of 3-10 m and an accuracy of 75.2% for an altitude range of 10-20 m. To incorporate temporal information in the classification, a tracking algorithm is proposed. Using temporal information improves the balanced classification accuracy to 93.3% in an altitude range 3-10 of meters and 77.7% in an altitude range of 10-20 m.

High-speed cell recognition algorithm for ultrafast flow cytometer imaging system.

PubMed

Zhao, Wanyue; Wang, Chao; Chen, Hongwei; Chen, Minghua; Yang, Sigang

2018-04-01

An optical time-stretch flow imaging system enables high-throughput examination of cells/particles with unprecedented high speed and resolution. A significant amount of raw image data is produced. A high-speed cell recognition algorithm is, therefore, highly demanded to analyze large amounts of data efficiently. A high-speed cell recognition algorithm consisting of two-stage cascaded detection and Gaussian mixture model (GMM) classification is proposed. The first stage of detection extracts cell regions. The second stage integrates distance transform and the watershed algorithm to separate clustered cells. Finally, the cells detected are classified by GMM. We compared the performance of our algorithm with support vector machine. Results show that our algorithm increases the running speed by over 150% without sacrificing the recognition accuracy. This algorithm provides a promising solution for high-throughput and automated cell imaging and classification in the ultrafast flow cytometer imaging platform. (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).

High-speed cell recognition algorithm for ultrafast flow cytometer imaging system

NASA Astrophysics Data System (ADS)

Zhao, Wanyue; Wang, Chao; Chen, Hongwei; Chen, Minghua; Yang, Sigang

2018-04-01

An optical time-stretch flow imaging system enables high-throughput examination of cells/particles with unprecedented high speed and resolution. A significant amount of raw image data is produced. A high-speed cell recognition algorithm is, therefore, highly demanded to analyze large amounts of data efficiently. A high-speed cell recognition algorithm consisting of two-stage cascaded detection and Gaussian mixture model (GMM) classification is proposed. The first stage of detection extracts cell regions. The second stage integrates distance transform and the watershed algorithm to separate clustered cells. Finally, the cells detected are classified by GMM. We compared the performance of our algorithm with support vector machine. Results show that our algorithm increases the running speed by over 150% without sacrificing the recognition accuracy. This algorithm provides a promising solution for high-throughput and automated cell imaging and classification in the ultrafast flow cytometer imaging platform.

Microscopic image analysis for reticulocyte based on watershed algorithm

NASA Astrophysics Data System (ADS)

Wang, J. Q.; Liu, G. F.; Liu, J. G.; Wang, G.

2007-12-01

We present a watershed-based algorithm in the analysis of light microscopic image for reticulocyte (RET), which will be used in an automated recognition system for RET in peripheral blood. The original images, obtained by micrography, are segmented by modified watershed algorithm and are recognized in term of gray entropy and area of connective area. In the process of watershed algorithm, judgment conditions are controlled according to character of the image, besides, the segmentation is performed by morphological subtraction. The algorithm was simulated with MATLAB software. It is similar for automated and manual scoring and there is good correlation(r=0.956) between the methods, which is resulted from 50 pieces of RET images. The result indicates that the algorithm for peripheral blood RETs is comparable to conventional manual scoring, and it is superior in objectivity. This algorithm avoids time-consuming calculation such as ultra-erosion and region-growth, which will speed up the computation consequentially.

ACQUA: Automated Cyanobacterial Quantification Algorithm for toxic filamentous genera using spline curves, pattern recognition and machine learning.

PubMed

Gandola, Emanuele; Antonioli, Manuela; Traficante, Alessio; Franceschini, Simone; Scardi, Michele; Congestri, Roberta

2016-05-01

Toxigenic cyanobacteria are one of the main health risks associated with water resources worldwide, as their toxins can affect humans and fauna exposed via drinking water, aquaculture and recreation. Microscopy monitoring of cyanobacteria in water bodies and massive growth systems is a routine operation for cell abundance and growth estimation. Here we present ACQUA (Automated Cyanobacterial Quantification Algorithm), a new fully automated image analysis method designed for filamentous genera in Bright field microscopy. A pre-processing algorithm has been developed to highlight filaments of interest from background signals due to other phytoplankton and dust. A spline-fitting algorithm has been designed to recombine interrupted and crossing filaments in order to perform accurate morphometric analysis and to extract the surface pattern information of highlighted objects. In addition, 17 specific pattern indicators have been developed and used as input data for a machine-learning algorithm dedicated to the recognition between five widespread toxic or potentially toxic filamentous genera in freshwater: Aphanizomenon, Cylindrospermopsis, Dolichospermum, Limnothrix and Planktothrix. The method was validated using freshwater samples from three Italian volcanic lakes comparing automated vs. manual results. ACQUA proved to be a fast and accurate tool to rapidly assess freshwater quality and to characterize cyanobacterial assemblages in aquatic environments. Copyright © 2016 Elsevier B.V. All rights reserved.

Pattern recognition applied to infrared images for early alerts in fog

NASA Astrophysics Data System (ADS)

Boucher, Vincent; Marchetti, Mario; Dumoulin, Jean; Cord, Aurélien

2014-09-01

Fog conditions are the cause of severe car accidents in western countries because of the poor induced visibility. Its forecast and intensity are still very difficult to predict by weather services. Infrared cameras allow to detect and to identify objects in fog while visibility is too low for eye detection. Over the past years, the implementation of cost effective infrared cameras on some vehicles has enabled such detection. On the other hand pattern recognition algorithms based on Canny filters and Hough transformation are a common tool applied to images. Based on these facts, a joint research program between IFSTTAR and Cerema has been developed to study the benefit of infrared images obtained in a fog tunnel during its natural dissipation. Pattern recognition algorithms have been applied, specifically on road signs which shape is usually associated to a specific meaning (circular for a speed limit, triangle for an alert, …). It has been shown that road signs were detected early enough in images, with respect to images in the visible spectrum, to trigger useful alerts for Advanced Driver Assistance Systems.

Evaluation of Available Software for Reconstruction of a Structure from its Imagery

DTIC Science & Technology

2017-04-01

Math . 2, 164–168. Lowe, D. G. (1999) Object recognition from local scale-invariant features, in Proc. Int. Conf. Computer Vision, Vol. 2, pp. 1150–1157...Marquardt, D. (1963) An algorithm for least-squares estimation of nonlinear parameters, SIAM J. Appl. Math . 11(2), 431–441. UNCLASSIFIED 11 DST-Group–TR

Structure from Motion

DTIC Science & Technology

1988-11-17

NOTATION 17. COSATI CODES 18. SUBJECT TERMS (Continue on reverse if ntcestary and identify by block number) FIELD GROUP SUB-GROUP ,-.:image...ambiguity in the recognition of partially occluded objects. V 1 , t : ., , ’ -, L: \\ : _ 20. DISTRIBUTION/AVAILABILITY OF ABSTRACT 21. ABSTRACT...constraints involved in the problem. More information can be found in [ 1 ]. Motion-based segmentation. Edge detection algorithms based on visual motion

Chinese License Plates Recognition Method Based on A Robust and Efficient Feature Extraction and BPNN Algorithm

NASA Astrophysics Data System (ADS)

Zhang, Ming; Xie, Fei; Zhao, Jing; Sun, Rui; Zhang, Lei; Zhang, Yue

2018-04-01

The prosperity of license plate recognition technology has made great contribution to the development of Intelligent Transport System (ITS). In this paper, a robust and efficient license plate recognition method is proposed which is based on a combined feature extraction model and BPNN (Back Propagation Neural Network) algorithm. Firstly, the candidate region of the license plate detection and segmentation method is developed. Secondly, a new feature extraction model is designed considering three sets of features combination. Thirdly, the license plates classification and recognition method using the combined feature model and BPNN algorithm is presented. Finally, the experimental results indicate that the license plate segmentation and recognition both can be achieved effectively by the proposed algorithm. Compared with three traditional methods, the recognition accuracy of the proposed method has increased to 95.7% and the consuming time has decreased to 51.4ms.

Tensor Rank Preserving Discriminant Analysis for Facial Recognition.

PubMed

Tao, Dapeng; Guo, Yanan; Li, Yaotang; Gao, Xinbo

2017-10-12

Facial recognition, one of the basic topics in computer vision and pattern recognition, has received substantial attention in recent years. However, for those traditional facial recognition algorithms, the facial images are reshaped to a long vector, thereby losing part of the original spatial constraints of each pixel. In this paper, a new tensor-based feature extraction algorithm termed tensor rank preserving discriminant analysis (TRPDA) for facial image recognition is proposed; the proposed method involves two stages: in the first stage, the low-dimensional tensor subspace of the original input tensor samples was obtained; in the second stage, discriminative locality alignment was utilized to obtain the ultimate vector feature representation for subsequent facial recognition. On the one hand, the proposed TRPDA algorithm fully utilizes the natural structure of the input samples, and it applies an optimization criterion that can directly handle the tensor spectral analysis problem, thereby decreasing the computation cost compared those traditional tensor-based feature selection algorithms. On the other hand, the proposed TRPDA algorithm extracts feature by finding a tensor subspace that preserves most of the rank order information of the intra-class input samples. Experiments on the three facial databases are performed here to determine the effectiveness of the proposed TRPDA algorithm.

Object recognition based on Google's reverse image search and image similarity

NASA Astrophysics Data System (ADS)

Horváth, András.

2015-12-01

Image classification is one of the most challenging tasks in computer vision and a general multiclass classifier could solve many different tasks in image processing. Classification is usually done by shallow learning for predefined objects, which is a difficult task and very different from human vision, which is based on continuous learning of object classes and one requires years to learn a large taxonomy of objects which are not disjunct nor independent. In this paper I present a system based on Google image similarity algorithm and Google image database, which can classify a large set of different objects in a human like manner, identifying related classes and taxonomies.

An improved architecture for video rate image transformations

NASA Technical Reports Server (NTRS)

Fisher, Timothy E.; Juday, Richard D.

1989-01-01

Geometric image transformations are of interest to pattern recognition algorithms for their use in simplifying some aspects of the pattern recognition process. Examples include reducing sensitivity to rotation, scale, and perspective of the object being recognized. The NASA Programmable Remapper can perform a wide variety of geometric transforms at full video rate. An architecture is proposed that extends its abilities and alleviates many of the first version's shortcomings. The need for the improvements are discussed in the context of the initial Programmable Remapper and the benefits and limitations it has delivered. The implementation and capabilities of the proposed architecture are discussed.

Multifeature-based high-resolution palmprint recognition.

PubMed

Dai, Jifeng; Zhou, Jie

2011-05-01

Palmprint is a promising biometric feature for use in access control and forensic applications. Previous research on palmprint recognition mainly concentrates on low-resolution (about 100 ppi) palmprints. But for high-security applications (e.g., forensic usage), high-resolution palmprints (500 ppi or higher) are required from which more useful information can be extracted. In this paper, we propose a novel recognition algorithm for high-resolution palmprint. The main contributions of the proposed algorithm include the following: 1) use of multiple features, namely, minutiae, density, orientation, and principal lines, for palmprint recognition to significantly improve the matching performance of the conventional algorithm. 2) Design of a quality-based and adaptive orientation field estimation algorithm which performs better than the existing algorithm in case of regions with a large number of creases. 3) Use of a novel fusion scheme for an identification application which performs better than conventional fusion methods, e.g., weighted sum rule, SVMs, or Neyman-Pearson rule. Besides, we analyze the discriminative power of different feature combinations and find that density is very useful for palmprint recognition. Experimental results on the database containing 14,576 full palmprints show that the proposed algorithm has achieved a good performance. In the case of verification, the recognition system's False Rejection Rate (FRR) is 16 percent, which is 17 percent lower than the best existing algorithm at a False Acceptance Rate (FAR) of 10(-5), while in the identification experiment, the rank-1 live-scan partial palmprint recognition rate is improved from 82.0 to 91.7 percent.

Color constancy in 3D-2D face recognition

NASA Astrophysics Data System (ADS)

Meyer, Manuel; Riess, Christian; Angelopoulou, Elli; Evangelopoulos, Georgios; Kakadiaris, Ioannis A.

2013-05-01

Face is one of the most popular biometric modalities. However, up to now, color is rarely actively used in face recognition. Yet, it is well-known that when a person recognizes a face, color cues can become as important as shape, especially when combined with the ability of people to identify the color of objects independent of illuminant color variations. In this paper, we examine the feasibility and effect of explicitly embedding illuminant color information in face recognition systems. We empirically examine the theoretical maximum gain of including known illuminant color to a 3D-2D face recognition system. We also investigate the impact of using computational color constancy methods for estimating the illuminant color, which is then incorporated into the face recognition framework. Our experiments show that under close-to-ideal illumination estimates, one can improve face recognition rates by 16%. When the illuminant color is algorithmically estimated, the improvement is approximately 5%. These results suggest that color constancy has a positive impact on face recognition, but the accuracy of the illuminant color estimate has a considerable effect on its benefits.

Mechanisms of face perception

PubMed Central

Tsao, Doris Y.

2009-01-01

Faces are among the most informative stimuli we ever perceive: Even a split-second glimpse of a person's face tells us their identity, sex, mood, age, race, and direction of attention. The specialness of face processing is acknowledged in the artificial vision community, where contests for face recognition algorithms abound. Neurological evidence strongly implicates a dedicated machinery for face processing in the human brain, to explain the double dissociability of face and object recognition deficits. Furthermore, it has recently become clear that macaques too have specialized neural machinery for processing faces. Here we propose a unifying hypothesis, deduced from computational, neurological, fMRI, and single-unit experiments: that what makes face processing special is that it is gated by an obligatory detection process. We will clarify this idea in concrete algorithmic terms, and show how it can explain a variety of phenomena associated with face processing. PMID:18558862

Textual and shape-based feature extraction and neuro-fuzzy classifier for nuclear track recognition

NASA Astrophysics Data System (ADS)

Khayat, Omid; Afarideh, Hossein

2013-04-01

Track counting algorithms as one of the fundamental principles of nuclear science have been emphasized in the recent years. Accurate measurement of nuclear tracks on solid-state nuclear track detectors is the aim of track counting systems. Commonly track counting systems comprise a hardware system for the task of imaging and software for analysing the track images. In this paper, a track recognition algorithm based on 12 defined textual and shape-based features and a neuro-fuzzy classifier is proposed. Features are defined so as to discern the tracks from the background and small objects. Then, according to the defined features, tracks are detected using a trained neuro-fuzzy system. Features and the classifier are finally validated via 100 Alpha track images and 40 training samples. It is shown that principle textual and shape-based features concomitantly yield a high rate of track detection compared with the single-feature based methods.

Citrus fruit recognition using color image analysis

NASA Astrophysics Data System (ADS)

Xu, Huirong; Ying, Yibin

2004-10-01

An algorithm for the automatic recognition of citrus fruit on the tree was developed. Citrus fruits have different color with leaves and branches portions. Fifty-three color images with natural citrus-grove scenes were digitized and analyzed for red, green, and blue (RGB) color content. The color characteristics of target surfaces (fruits, leaves, or branches) were extracted using the range of interest (ROI) tool. Several types of contrast color indices were designed and tested. In this study, the fruit image was enhanced using the (R-B) contrast color index because results show that the fruit have the highest color difference among the objects in the image. A dynamic threshold function was derived from this color model and used to distinguish citrus fruit from background. The results show that the algorithm worked well under frontlighting or backlighting condition. However, there are misclassifications when the fruit or the background is under a brighter sunlight.

Comparing visual representations across human fMRI and computational vision

PubMed Central

Leeds, Daniel D.; Seibert, Darren A.; Pyles, John A.; Tarr, Michael J.

2013-01-01

Feedforward visual object perception recruits a cortical network that is assumed to be hierarchical, progressing from basic visual features to complete object representations. However, the nature of the intermediate features related to this transformation remains poorly understood. Here, we explore how well different computer vision recognition models account for neural object encoding across the human cortical visual pathway as measured using fMRI. These neural data, collected during the viewing of 60 images of real-world objects, were analyzed with a searchlight procedure as in Kriegeskorte, Goebel, and Bandettini (2006): Within each searchlight sphere, the obtained patterns of neural activity for all 60 objects were compared to model responses for each computer recognition algorithm using representational dissimilarity analysis (Kriegeskorte et al., 2008). Although each of the computer vision methods significantly accounted for some of the neural data, among the different models, the scale invariant feature transform (Lowe, 2004), encoding local visual properties gathered from “interest points,” was best able to accurately and consistently account for stimulus representations within the ventral pathway. More generally, when present, significance was observed in regions of the ventral-temporal cortex associated with intermediate-level object perception. Differences in model effectiveness and the neural location of significant matches may be attributable to the fact that each model implements a different featural basis for representing objects (e.g., more holistic or more parts-based). Overall, we conclude that well-known computer vision recognition systems may serve as viable proxies for theories of intermediate visual object representation. PMID:24273227

Stereo-Based Region-Growing using String Matching

NASA Technical Reports Server (NTRS)

Mandelbaum, Robert; Mintz, Max

1995-01-01

We present a novel stereo algorithm based on a coarse texture segmentation preprocessing phase. Matching is performed using a string comparison. Matching sub-strings correspond to matching sequences of textures. Inter-scanline clustering of matching sub-strings yields regions of matching texture. The shape of these regions yield information concerning object's height, width and azimuthal position relative to the camera pair. Hence, rather than the standard dense depth map, the output of this algorithm is a segmentation of objects in the scene. Such a format is useful for the integration of stereo with other sensor modalities on a mobile robotic platform. It is also useful for localization; the height and width of a detected object may be used for landmark recognition, while depth and relative azimuthal location determine pose. The algorithm does not rely on the monotonicity of order of image primitives. Occlusions, exposures, and foreshortening effects are not problematic. The algorithm can deal with certain types of transparencies. It is computationally efficient, and very amenable to parallel implementation. Further, the epipolar constraints may be relaxed to some small but significant degree. A version of the algorithm has been implemented and tested on various types of images. It performs best on random dot stereograms, on images with easily filtered backgrounds (as in synthetic images), and on real scenes with uncontrived backgrounds.

Design method of ARM based embedded iris recognition system

NASA Astrophysics Data System (ADS)

Wang, Yuanbo; He, Yuqing; Hou, Yushi; Liu, Ting

2008-03-01

With the advantages of non-invasiveness, uniqueness, stability and low false recognition rate, iris recognition has been successfully applied in many fields. Up to now, most of the iris recognition systems are based on PC. However, a PC is not portable and it needs more power. In this paper, we proposed an embedded iris recognition system based on ARM. Considering the requirements of iris image acquisition and recognition algorithm, we analyzed the design method of the iris image acquisition module, designed the ARM processing module and its peripherals, studied the Linux platform and the recognition algorithm based on this platform, finally actualized the design method of ARM-based iris imaging and recognition system. Experimental results show that the ARM platform we used is fast enough to run the iris recognition algorithm, and the data stream can flow smoothly between the camera and the ARM chip based on the embedded Linux system. It's an effective method of using ARM to actualize portable embedded iris recognition system.

3D automatic anatomy recognition based on iterative graph-cut-ASM

NASA Astrophysics Data System (ADS)

Chen, Xinjian; Udupa, Jayaram K.; Bagci, Ulas; Alavi, Abass; Torigian, Drew A.

2010-02-01

We call the computerized assistive process of recognizing, delineating, and quantifying organs and tissue regions in medical imaging, occurring automatically during clinical image interpretation, automatic anatomy recognition (AAR). The AAR system we are developing includes five main parts: model building, object recognition, object delineation, pathology detection, and organ system quantification. In this paper, we focus on the delineation part. For the modeling part, we employ the active shape model (ASM) strategy. For recognition and delineation, we integrate several hybrid strategies of combining purely image based methods with ASM. In this paper, an iterative Graph-Cut ASM (IGCASM) method is proposed for object delineation. An algorithm called GC-ASM was presented at this symposium last year for object delineation in 2D images which attempted to combine synergistically ASM and GC. Here, we extend this method to 3D medical image delineation. The IGCASM method effectively combines the rich statistical shape information embodied in ASM with the globally optimal delineation capability of the GC method. We propose a new GC cost function, which effectively integrates the specific image information with the ASM shape model information. The proposed methods are tested on a clinical abdominal CT data set. The preliminary results show that: (a) it is feasible to explicitly bring prior 3D statistical shape information into the GC framework; (b) the 3D IGCASM delineation method improves on ASM and GC and can provide practical operational time on clinical images.

Comparison of Two Sepsis Recognition Methods in a Pediatric Emergency Department

PubMed Central

Balamuth, Fran; Alpern, Elizabeth R.; Grundmeier, Robert W.; Chilutti, Marianne; Weiss, Scott L.; Fitzgerald, Julie C.; Hayes, Katie; Bilker, Warren; Lautenbach, Ebbing

2015-01-01

Objectives To compare the effectiveness of physician judgment and an electronic algorithmic alert to identify pediatric patients with severe sepsis/septic shock in a pediatric emergency department (ED). Methods This was an observational cohort study of patients older than 56 days with fever or hypothermia. All patients were evaluated for potential sepsis in real time by the ED clinical team. An electronic algorithmic alert was retrospectively applied to identify patients with potential sepsis independent of physician judgment. The primary outcome was the proportion of patients correctly identified with severe sepsis/septic shock defined by consensus criteria. Test characteristics were determined and receiver operating characteristic (ROC) curves were compared. Results Of 19,524 eligible patient visits, 88 patients developed consensus-confirmed severe sepsis or septic shock. Physician judgment identified 159, and the algorithmic alert identified 3,301 patients with potential sepsis. Physician judgment had sensitivity of 72.7% (95% CI = 72.1% to 73.4%) and specificity 99.5% (95% CI = 99.4% to 99.6%); the algorithmic alert had sensitivity 92.1% (95% CI = 91.7% to 92.4%), and specificity 83.4% (95% CI = 82.9% to 83.9%) for severe sepsis/septic shock. There was no significant difference in the area under the ROC curve for physician judgment (0.86, 95% CI = 0.81 to 0.91) or the algorithm (0.88, 95% CI = 0.85 to 0.91; p = 0.54). A combination method using either positive physician judgment or an algorithmic alert improved sensitivity to 96.6% and specificity to 83.3%. A sequential approach, in which positive identification by the algorithmic alert was then confirmed by physician judgment, achieved 68.2% sensitivity and 99.6% specificity. Positive and negative predictive values for physician judgment vs. algorithmic alert were 40.3% vs. 2.5% and 99.88 % vs. 99.96%, respectively. Conclusions The electronic algorithmic alert was more sensitive but less specific than physician judgment for recognition of pediatric severe sepsis and septic shock. These findings can help to guide institutions in selecting pediatric sepsis recognition methods based on institutional needs and priorities. PMID:26474032

Comparison of Two Sepsis Recognition Methods in a Pediatric Emergency Department.

PubMed

Balamuth, Fran; Alpern, Elizabeth R; Grundmeier, Robert W; Chilutti, Marianne; Weiss, Scott L; Fitzgerald, Julie C; Hayes, Katie; Bilker, Warren; Lautenbach, Ebbing

2015-11-01

The objective was to compare the effectiveness of physician judgment and an electronic algorithmic alert to identify pediatric patients with severe sepsis/septic shock in a pediatric emergency department (ED). This was an observational cohort study of patients older than 56 days with fever or hypothermia. All patients were evaluated for potential sepsis in real time by the ED clinical team. An electronic algorithmic alert was retrospectively applied to identify patients with potential sepsis independent of physician judgment. The primary outcome was the proportion of patients correctly identified with severe sepsis/septic shock defined by consensus criteria. Test characteristics were determined and receiver operating characteristic (ROC) curves were compared. Of 19,524 eligible patient visits, 88 patients developed consensus-confirmed severe sepsis or septic shock. Physician judgment identified 159 and the algorithmic alert identified 3,301 patients with potential sepsis. Physician judgment had sensitivity of 72.7% (95% confidence interval [CI] = 72.1% to 73.4%) and specificity of 99.5% (95% CI = 99.4% to 99.6%); the algorithmic alert had sensitivity of 92.1% (95% CI = 91.7% to 92.4%) and specificity of 83.4% (95% CI = 82.9% to 83.9%) for severe sepsis/septic shock. There was no significant difference in the area under the ROC curve for physician judgment (0.86, 95% CI = 0.81 to 0.91) or the algorithm (0.88, 95% CI = 0.85 to 0.91; p = 0.54). A combination method using either positive physician judgment or an algorithmic alert improved sensitivity to 96.6% and specificity to 83.3%. A sequential approach, in which positive identification by the algorithmic alert was then confirmed by physician judgment, achieved 68.2% sensitivity and 99.6% specificity. Positive and negative predictive values for physician judgment versus algorithmic alert were 40.3% versus 2.5% and 99.88% versus 99.96%, respectively. The electronic algorithmic alert was more sensitive but less specific than physician judgment for recognition of pediatric severe sepsis and septic shock. These findings can help to guide institutions in selecting pediatric sepsis recognition methods based on institutional needs and priorities. © 2015 by the Society for Academic Emergency Medicine.

Introducing memory and association mechanism into a biologically inspired visual model.

PubMed

Qiao, Hong; Li, Yinlin; Tang, Tang; Wang, Peng

2014-09-01

A famous biologically inspired hierarchical model (HMAX model), which was proposed recently and corresponds to V1 to V4 of the ventral pathway in primate visual cortex, has been successfully applied to multiple visual recognition tasks. The model is able to achieve a set of position- and scale-tolerant recognition, which is a central problem in pattern recognition. In this paper, based on some other biological experimental evidence, we introduce the memory and association mechanism into the HMAX model. The main contributions of the work are: 1) mimicking the active memory and association mechanism and adding the top down adjustment to the HMAX model, which is the first try to add the active adjustment to this famous model and 2) from the perspective of information, algorithms based on the new model can reduce the computation storage and have a good recognition performance. The new model is also applied to object recognition processes. The primary experimental results show that our method is efficient with a much lower memory requirement.

Using advanced computer vision algorithms on small mobile robots

NASA Astrophysics Data System (ADS)

Kogut, G.; Birchmore, F.; Biagtan Pacis, E.; Everett, H. R.

2006-05-01

The Technology Transfer project employs a spiral development process to enhance the functionality and autonomy of mobile robot systems in the Joint Robotics Program (JRP) Robotic Systems Pool by converging existing component technologies onto a transition platform for optimization. An example of this approach is the implementation of advanced computer vision algorithms on small mobile robots. We demonstrate the implementation and testing of the following two algorithms useful on mobile robots: 1) object classification using a boosted Cascade of classifiers trained with the Adaboost training algorithm, and 2) human presence detection from a moving platform. Object classification is performed with an Adaboost training system developed at the University of California, San Diego (UCSD) Computer Vision Lab. This classification algorithm has been used to successfully detect the license plates of automobiles in motion in real-time. While working towards a solution to increase the robustness of this system to perform generic object recognition, this paper demonstrates an extension to this application by detecting soda cans in a cluttered indoor environment. The human presence detection from a moving platform system uses a data fusion algorithm which combines results from a scanning laser and a thermal imager. The system is able to detect the presence of humans while both the humans and the robot are moving simultaneously. In both systems, the two aforementioned algorithms were implemented on embedded hardware and optimized for use in real-time. Test results are shown for a variety of environments.

Real-Time Laser Ultrasound Tomography for Profilometry of Solids

NASA Astrophysics Data System (ADS)

Zarubin, V. P.; Bychkov, A. S.; Karabutov, A. A.; Simonova, V. A.; Kudinov, I. A.; Cherepetskaya, E. B.

2018-01-01

We studied the possibility of applying laser ultrasound tomography for profilometry of solids. The proposed approach provides high spatial resolution and efficiency, as well as profilometry of contaminated objects or objects submerged in liquids. The algorithms for the construction of tomograms and recognition of the profiles of studied objects using the parallel programming technology NDIVIA CUDA are proposed. A prototype of the real-time laser ultrasound profilometer was used to obtain the profiles of solid surfaces of revolution. The proposed method allows the real-time determination of the surface position for cylindrical objects with an approximation accuracy of up to 16 μm.

Speech recognition for embedded automatic positioner for laparoscope

NASA Astrophysics Data System (ADS)

Chen, Xiaodong; Yin, Qingyun; Wang, Yi; Yu, Daoyin

2014-07-01

In this paper a novel speech recognition methodology based on Hidden Markov Model (HMM) is proposed for embedded Automatic Positioner for Laparoscope (APL), which includes a fixed point ARM processor as the core. The APL system is designed to assist the doctor in laparoscopic surgery, by implementing the specific doctor's vocal control to the laparoscope. Real-time respond to the voice commands asks for more efficient speech recognition algorithm for the APL. In order to reduce computation cost without significant loss in recognition accuracy, both arithmetic and algorithmic optimizations are applied in the method presented. First, depending on arithmetic optimizations most, a fixed point frontend for speech feature analysis is built according to the ARM processor's character. Then the fast likelihood computation algorithm is used to reduce computational complexity of the HMM-based recognition algorithm. The experimental results show that, the method shortens the recognition time within 0.5s, while the accuracy higher than 99%, demonstrating its ability to achieve real-time vocal control to the APL.

System of technical vision for autonomous unmanned aerial vehicles

NASA Astrophysics Data System (ADS)

Bondarchuk, A. S.

2018-05-01

This paper is devoted to the implementation of image recognition algorithm using the LabVIEW software. The created virtual instrument is designed to detect the objects on the frames from the camera mounted on the UAV. The trained classifier is invariant to changes in rotation, as well as to small changes in the camera's viewing angle. Finding objects in the image using particle analysis, allows you to classify regions of different sizes. This method allows the system of technical vision to more accurately determine the location of the objects of interest and their movement relative to the camera.

Recognition of upper airway and surrounding structures at MRI in pediatric PCOS and OSAS

NASA Astrophysics Data System (ADS)

Tong, Yubing; Udupa, J. K.; Odhner, D.; Sin, Sanghun; Arens, Raanan

2013-03-01

Obstructive Sleep Apnea Syndrome (OSAS) is common in obese children with risk being 4.5 fold compared to normal control subjects. Polycystic Ovary Syndrome (PCOS) has recently been shown to be associated with OSAS that may further lead to significant cardiovascular and neuro-cognitive deficits. We are investigating image-based biomarkers to understand the architectural and dynamic changes in the upper airway and the surrounding hard and soft tissue structures via MRI in obese teenage children to study OSAS. At the previous SPIE conferences, we presented methods underlying Fuzzy Object Models (FOMs) for Automatic Anatomy Recognition (AAR) based on CT images of the thorax and the abdomen. The purpose of this paper is to demonstrate that the AAR approach is applicable to a different body region and image modality combination, namely in the study of upper airway structures via MRI. FOMs were built hierarchically, the smaller sub-objects forming the offspring of larger parent objects. FOMs encode the uncertainty and variability present in the form and relationships among the objects over a study population. Totally 11 basic objects (17 including composite) were modeled. Automatic recognition for the best pose of FOMs in a given image was implemented by using four methods - a one-shot method that does not require search, another three searching methods that include Fisher Linear Discriminate (FLD), a b-scale energy optimization strategy, and optimum threshold recognition method. In all, 30 multi-fold cross validation experiments based on 15 patient MRI data sets were carried out to assess the accuracy of recognition. The results indicate that the objects can be recognized with an average location error of less than 5 mm or 2-3 voxels. Then the iterative relative fuzzy connectedness (IRFC) algorithm was adopted for delineation of the target organs based on the recognized results. The delineation results showed an overall FP and TP volume fraction of 0.02 and 0.93.

Implementation of jump-diffusion algorithms for understanding FLIR scenes

NASA Astrophysics Data System (ADS)

Lanterman, Aaron D.; Miller, Michael I.; Snyder, Donald L.

1995-07-01

Our pattern theoretic approach to the automated understanding of forward-looking infrared (FLIR) images brings the traditionally separate endeavors of detection, tracking, and recognition together into a unified jump-diffusion process. New objects are detected and object types are recognized through discrete jump moves. Between jumps, the location and orientation of objects are estimated via continuous diffusions. An hypothesized scene, simulated from the emissive characteristics of the hypothesized scene elements, is compared with the collected data by a likelihood function based on sensor statistics. This likelihood is combined with a prior distribution defined over the set of possible scenes to form a posterior distribution. The jump-diffusion process empirically generates the posterior distribution. Both the diffusion and jump operations involve the simulation of a scene produced by a hypothesized configuration. Scene simulation is most effectively accomplished by pipelined rendering engines such as silicon graphics. We demonstrate the execution of our algorithm on a silicon graphics onyx/reality engine.

Tracking and recognition face in videos with incremental local sparse representation model

NASA Astrophysics Data System (ADS)

Wang, Chao; Wang, Yunhong; Zhang, Zhaoxiang

2013-10-01

This paper addresses the problem of tracking and recognizing faces via incremental local sparse representation. First a robust face tracking algorithm is proposed via employing local sparse appearance and covariance pooling method. In the following face recognition stage, with the employment of a novel template update strategy, which combines incremental subspace learning, our recognition algorithm adapts the template to appearance changes and reduces the influence of occlusion and illumination variation. This leads to a robust video-based face tracking and recognition with desirable performance. In the experiments, we test the quality of face recognition in real-world noisy videos on YouTube database, which includes 47 celebrities. Our proposed method produces a high face recognition rate at 95% of all videos. The proposed face tracking and recognition algorithms are also tested on a set of noisy videos under heavy occlusion and illumination variation. The tracking results on challenging benchmark videos demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods. In the case of the challenging dataset in which faces undergo occlusion and illumination variation, and tracking and recognition experiments under significant pose variation on the University of California, San Diego (Honda/UCSD) database, our proposed method also consistently demonstrates a high recognition rate.

Target recognition in passive terahertz image of human body

NASA Astrophysics Data System (ADS)

Zhao, Ran; Zhao, Yuan-meng; Deng, Chao; Zhang, Cun-lin; Li, Yue

2014-11-01

THz radiation can penetrate through many nonpolar dielectric materials and can be used for nondestructive/noninvasive sensing and imaging of targets under nonpolar, nonmetallic covers or containers. Thus using THz systems to "see through" concealing barriers (i.e. packaging, corrugated cardboard, clothing) has been proposed as a new security screening method. Objects that can be detected by THz include concealed weapons, explosives, and chemical agents under clothing. Passive THz imaging system can detect THz wave from human body without transmit any electromagnetic wave, and the suspicious objects will become visible because the THz wave is blocked by this items. We can find out whether or not someone is carrying dangerous objects through this image. In this paper, the THz image enhancement, segmentation and contour extraction algorithms were studied to achieve effective target image detection. First, the terahertz images are enhanced and their grayscales are stretched. Then we apply global threshold segmentation to extract the target, and finally the targets are marked on the image. Experimental results showed that the algorithm proposed in this paper can extract and mark targets effectively, so that people can identify suspicious objects under clothing quickly. The algorithm can significantly improve the usefulness of the terahertz security apparatus.

Face sketch recognition based on edge enhancement via deep learning

NASA Astrophysics Data System (ADS)

Xie, Zhenzhu; Yang, Fumeng; Zhang, Yuming; Wu, Congzhong

2017-11-01

In this paper,we address the face sketch recognition problem. Firstly, we utilize the eigenface algorithm to convert a sketch image into a synthesized sketch face image. Subsequently, considering the low-level vision problem in synthesized face sketch image .Super resolution reconstruction algorithm based on CNN(convolutional neural network) is employed to improve the visual effect. To be specific, we uses a lightweight super-resolution structure to learn a residual mapping instead of directly mapping the feature maps from the low-level space to high-level patch representations, which making the networks are easier to optimize and have lower computational complexity. Finally, we adopt LDA(Linear Discriminant Analysis) algorithm to realize face sketch recognition on synthesized face image before super resolution and after respectively. Extensive experiments on the face sketch database(CUFS) from CUHK demonstrate that the recognition rate of SVM(Support Vector Machine) algorithm improves from 65% to 69% and the recognition rate of LDA(Linear Discriminant Analysis) algorithm improves from 69% to 75%.What'more,the synthesized face image after super resolution can not only better describer image details such as hair ,nose and mouth etc, but also improve the recognition accuracy effectively.

Face recognition algorithm using extended vector quantization histogram features.

PubMed

Yan, Yan; Lee, Feifei; Wu, Xueqian; Chen, Qiu

2018-01-01

In this paper, we propose a face recognition algorithm based on a combination of vector quantization (VQ) and Markov stationary features (MSF). The VQ algorithm has been shown to be an effective method for generating features; it extracts a codevector histogram as a facial feature representation for face recognition. Still, the VQ histogram features are unable to convey spatial structural information, which to some extent limits their usefulness in discrimination. To alleviate this limitation of VQ histograms, we utilize Markov stationary features (MSF) to extend the VQ histogram-based features so as to add spatial structural information. We demonstrate the effectiveness of our proposed algorithm by achieving recognition results superior to those of several state-of-the-art methods on publicly available face databases.

A Random Forest-based ensemble method for activity recognition.

PubMed

Feng, Zengtao; Mo, Lingfei; Li, Meng

2015-01-01

This paper presents a multi-sensor ensemble approach to human physical activity (PA) recognition, using random forest. We designed an ensemble learning algorithm, which integrates several independent Random Forest classifiers based on different sensor feature sets to build a more stable, more accurate and faster classifier for human activity recognition. To evaluate the algorithm, PA data collected from the PAMAP (Physical Activity Monitoring for Aging People), which is a standard, publicly available database, was utilized to train and test. The experimental results show that the algorithm is able to correctly recognize 19 PA types with an accuracy of 93.44%, while the training is faster than others. The ensemble classifier system based on the RF (Random Forest) algorithm can achieve high recognition accuracy and fast calculation.

The fast iris image clarity evaluation based on Tenengrad and ROI selection

NASA Astrophysics Data System (ADS)

Gao, Shuqin; Han, Min; Cheng, Xu

2018-04-01

In iris recognition system, the clarity of iris image is an important factor that influences recognition effect. In the process of recognition, the blurred image may possibly be rejected by the automatic iris recognition system, which will lead to the failure of identification. Therefore it is necessary to evaluate the iris image definition before recognition. Considered the existing evaluation methods on iris image definition, we proposed a fast algorithm to evaluate the definition of iris image in this paper. In our algorithm, firstly ROI (Region of Interest) is extracted based on the reference point which is determined by using the feature of the light spots within the pupil, then Tenengrad operator is used to evaluate the iris image's definition. Experiment results show that, the iris image definition algorithm proposed in this paper could accurately distinguish the iris images of different clarity, and the algorithm has the merit of low computational complexity and more effectiveness.

Optimal pattern synthesis for speech recognition based on principal component analysis

NASA Astrophysics Data System (ADS)

Korsun, O. N.; Poliyev, A. V.

2018-02-01

The algorithm for building an optimal pattern for the purpose of automatic speech recognition, which increases the probability of correct recognition, is developed and presented in this work. The optimal pattern forming is based on the decomposition of an initial pattern to principal components, which enables to reduce the dimension of multi-parameter optimization problem. At the next step the training samples are introduced and the optimal estimates for principal components decomposition coefficients are obtained by a numeric parameter optimization algorithm. Finally, we consider the experiment results that show the improvement in speech recognition introduced by the proposed optimization algorithm.

Dynamic programming and graph algorithms in computer vision.

PubMed

Felzenszwalb, Pedro F; Zabih, Ramin

2011-04-01

Optimization is a powerful paradigm for expressing and solving problems in a wide range of areas, and has been successfully applied to many vision problems. Discrete optimization techniques are especially interesting since, by carefully exploiting problem structure, they often provide nontrivial guarantees concerning solution quality. In this paper, we review dynamic programming and graph algorithms, and discuss representative examples of how these discrete optimization techniques have been applied to some classical vision problems. We focus on the low-level vision problem of stereo, the mid-level problem of interactive object segmentation, and the high-level problem of model-based recognition.

Real-time road detection in infrared imagery

NASA Astrophysics Data System (ADS)

Andre, Haritini E.; McCoy, Keith

1990-09-01

Automatic road detection is an important part in many scene recognition applications. The extraction of roads provides a means of navigation and position update for remotely piloted vehicles or autonomous vehicles. Roads supply strong contextual information which can be used to improve the performance of automatic target recognition (ATh) systems by directing the search for targets and adjusting target classification confidences. This paper will describe algorithmic techniques for labeling roads in high-resolution infrared imagery. In addition, realtime implementation of this structural approach using a processor array based on the Martin Marietta Geometric Arithmetic Parallel Processor (GAPPTh) chip will be addressed. The algorithm described is based on the hypothesis that a road consists of pairs of line segments separated by a distance "d" with opposite gradient directions (antiparallel). The general nature of the algorithm, in addition to its parallel implementation in a single instruction, multiple data (SIMD) machine, are improvements to existing work. The algorithm seeks to identify line segments meeting the road hypothesis in a manner that performs well, even when the side of the road is fragmented due to occlusion or intersections. The use of geometrical relationships between line segments is a powerful yet flexible method of road classification which is independent of orientation. In addition, this approach can be used to nominate other types of objects with minor parametric changes.

Multi-frame knowledge based text enhancement for mobile phone captured videos

NASA Astrophysics Data System (ADS)

Ozarslan, Suleyman; Eren, P. Erhan

2014-02-01

In this study, we explore automated text recognition and enhancement using mobile phone captured videos of store receipts. We propose a method which includes Optical Character Resolution (OCR) enhanced by our proposed Row Based Multiple Frame Integration (RB-MFI), and Knowledge Based Correction (KBC) algorithms. In this method, first, the trained OCR engine is used for recognition; then, the RB-MFI algorithm is applied to the output of the OCR. The RB-MFI algorithm determines and combines the most accurate rows of the text outputs extracted by using OCR from multiple frames of the video. After RB-MFI, KBC algorithm is applied to these rows to correct erroneous characters. Results of the experiments show that the proposed video-based approach which includes the RB-MFI and the KBC algorithm increases the word character recognition rate to 95%, and the character recognition rate to 98%.

[A new peak detection algorithm of Raman spectra].

PubMed

Jiang, Cheng-Zhi; Sun, Qiang; Liu, Ying; Liang, Jing-Qiu; An, Yan; Liu, Bing

2014-01-01

The authors proposed a new Raman peak recognition method named bi-scale correlation algorithm. The algorithm uses the combination of the correlation coefficient and the local signal-to-noise ratio under two scales to achieve Raman peak identification. We compared the performance of the proposed algorithm with that of the traditional continuous wavelet transform method through MATLAB, and then tested the algorithm with real Raman spectra. The results show that the average time for identifying a Raman spectrum is 0.51 s with the algorithm, while it is 0.71 s with the continuous wavelet transform. When the signal-to-noise ratio of Raman peak is greater than or equal to 6 (modern Raman spectrometers feature an excellent signal-to-noise ratio), the recognition accuracy with the algorithm is higher than 99%, while it is less than 84% with the continuous wavelet transform method. The mean and the standard deviations of the peak position identification error of the algorithm are both less than that of the continuous wavelet transform method. Simulation analysis and experimental verification prove that the new algorithm possesses the following advantages: no needs of human intervention, no needs of de-noising and background removal operation, higher recognition speed and higher recognition accuracy. The proposed algorithm is operable in Raman peak identification.

Non-Convex Sparse and Low-Rank Based Robust Subspace Segmentation for Data Mining.

PubMed

Cheng, Wenlong; Zhao, Mingbo; Xiong, Naixue; Chui, Kwok Tai

2017-07-15

Parsimony, including sparsity and low-rank, has shown great importance for data mining in social networks, particularly in tasks such as segmentation and recognition. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an objective function with convex l ₁-norm or nuclear norm constraints. However, the obtained results by convex optimization are usually suboptimal to solutions of original sparse or low-rank problems. In this paper, a novel robust subspace segmentation algorithm has been proposed by integrating l p -norm and Schatten p -norm constraints. Our so-obtained affinity graph can better capture local geometrical structure and the global information of the data. As a consequence, our algorithm is more generative, discriminative and robust. An efficient linearized alternating direction method is derived to realize our model. Extensive segmentation experiments are conducted on public datasets. The proposed algorithm is revealed to be more effective and robust compared to five existing algorithms.

An improved finger-vein recognition algorithm based on template matching

NASA Astrophysics Data System (ADS)

Liu, Yueyue; Di, Si; Jin, Jian; Huang, Daoping

2016-10-01

Finger-vein recognition has became the most popular biometric identify methods. The investigation on the recognition algorithms always is the key point in this field. So far, there are many applicable algorithms have been developed. However, there are still some problems in practice, such as the variance of the finger position which may lead to the image distortion and shifting; during the identification process, some matching parameters determined according to experience may also reduce the adaptability of algorithm. Focus on above mentioned problems, this paper proposes an improved finger-vein recognition algorithm based on template matching. In order to enhance the robustness of the algorithm for the image distortion, the least squares error method is adopted to correct the oblique finger. During the feature extraction, local adaptive threshold method is adopted. As regard as the matching scores, we optimized the translation preferences as well as matching distance between the input images and register images on the basis of Naoto Miura algorithm. Experimental results indicate that the proposed method can improve the robustness effectively under the finger shifting and rotation conditions.

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

PubMed

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

Bilayer segmentation of webcam videos using tree-based classifiers.

PubMed

Yin, Pei; Criminisi, Antonio; Winn, John; Essa, Irfan

2011-01-01

This paper presents an automatic segmentation algorithm for video frames captured by a (monocular) webcam that closely approximates depth segmentation from a stereo camera. The frames are segmented into foreground and background layers that comprise a subject (participant) and other objects and individuals. The algorithm produces correct segmentations even in the presence of large background motion with a nearly stationary foreground. This research makes three key contributions: First, we introduce a novel motion representation, referred to as "motons," inspired by research in object recognition. Second, we propose estimating the segmentation likelihood from the spatial context of motion. The estimation is efficiently learned by random forests. Third, we introduce a general taxonomy of tree-based classifiers that facilitates both theoretical and experimental comparisons of several known classification algorithms and generates new ones. In our bilayer segmentation algorithm, diverse visual cues such as motion, motion context, color, contrast, and spatial priors are fused by means of a conditional random field (CRF) model. Segmentation is then achieved by binary min-cut. Experiments on many sequences of our videochat application demonstrate that our algorithm, which requires no initialization, is effective in a variety of scenes, and the segmentation results are comparable to those obtained by stereo systems.

Importance of multi-modal approaches to effectively identify cataract cases from electronic health records

PubMed Central

Rasmussen, Luke V; Berg, Richard L; Linneman, James G; McCarty, Catherine A; Waudby, Carol; Chen, Lin; Denny, Joshua C; Wilke, Russell A; Pathak, Jyotishman; Carrell, David; Kho, Abel N; Starren, Justin B

2012-01-01

Objective There is increasing interest in using electronic health records (EHRs) to identify subjects for genomic association studies, due in part to the availability of large amounts of clinical data and the expected cost efficiencies of subject identification. We describe the construction and validation of an EHR-based algorithm to identify subjects with age-related cataracts. Materials and methods We used a multi-modal strategy consisting of structured database querying, natural language processing on free-text documents, and optical character recognition on scanned clinical images to identify cataract subjects and related cataract attributes. Extensive validation on 3657 subjects compared the multi-modal results to manual chart review. The algorithm was also implemented at participating electronic MEdical Records and GEnomics (eMERGE) institutions. Results An EHR-based cataract phenotyping algorithm was successfully developed and validated, resulting in positive predictive values (PPVs) >95%. The multi-modal approach increased the identification of cataract subject attributes by a factor of three compared to single-mode approaches while maintaining high PPV. Components of the cataract algorithm were successfully deployed at three other institutions with similar accuracy. Discussion A multi-modal strategy incorporating optical character recognition and natural language processing may increase the number of cases identified while maintaining similar PPVs. Such algorithms, however, require that the needed information be embedded within clinical documents. Conclusion We have demonstrated that algorithms to identify and characterize cataracts can be developed utilizing data collected via the EHR. These algorithms provide a high level of accuracy even when implemented across multiple EHRs and institutional boundaries. PMID:22319176

Recognition of partially occluded threat objects using the annealed Hopefield network

NASA Technical Reports Server (NTRS)

Kim, Jung H.; Yoon, Sung H.; Park, Eui H.; Ntuen, Celestine A.

1992-01-01

Recognition of partially occluded objects has been an important issue to airport security because occlusion causes significant problems in identifying and locating objects during baggage inspection. The neural network approach is suitable for the problems in the sense that the inherent parallelism of neural networks pursues many hypotheses in parallel resulting in high computation rates. Moreover, they provide a greater degree of robustness or fault tolerance than conventional computers. The annealed Hopfield network which is derived from the mean field annealing (MFA) has been developed to find global solutions of a nonlinear system. In the study, it has been proven that the system temperature of MFA is equivalent to the gain of the sigmoid function of a Hopfield network. In our early work, we developed the hybrid Hopfield network (HHN) for fast and reliable matching. However, HHN doesn't guarantee global solutions and yields false matching under heavily occluded conditions because HHN is dependent on initial states by its nature. In this paper, we present the annealed Hopfield network (AHN) for occluded object matching problems. In AHN, the mean field theory is applied to the hybird Hopfield network in order to improve computational complexity of the annealed Hopfield network and provide reliable matching under heavily occluded conditions. AHN is slower than HHN. However, AHN provides near global solutions without initial restrictions and provides less false matching than HHN. In conclusion, a new algorithm based upon a neural network approach was developed to demonstrate the feasibility of the automated inspection of threat objects from x-ray images. The robustness of the algorithm is proved by identifying occluded target objects with large tolerance of their features.

Bibliography of In-House and Contract Reports, Supplement 18

DTIC Science & Technology

1992-10-01

Transparent Conforming Overlays 46 TITLE REPORT NO. YEAR Development, Service Tests, and Production Model 1307 -TR 1953 Tests, Autofocusing Rectifier...Development, Test, Preparation, Delivery, and ETL- 1307 1982 Installation of Algorithms for Optimal Adjustment of Inertial Survey Data Developmental Optical...B: Terrain ETL- 0428 1986 and Object Modeling Recognition (March 13, 1985 - March 13, 1986) Knowledge-Based Vision Techniques - Task B: Terrain ETL

Bio-Inspired Neural Model for Learning Dynamic Models

NASA Technical Reports Server (NTRS)

Duong, Tuan; Duong, Vu; Suri, Ronald

2009-01-01

A neural-network mathematical model that, relative to prior such models, places greater emphasis on some of the temporal aspects of real neural physical processes, has been proposed as a basis for massively parallel, distributed algorithms that learn dynamic models of possibly complex external processes by means of learning rules that are local in space and time. The algorithms could be made to perform such functions as recognition and prediction of words in speech and of objects depicted in video images. The approach embodied in this model is said to be "hardware-friendly" in the following sense: The algorithms would be amenable to execution by special-purpose computers implemented as very-large-scale integrated (VLSI) circuits that would operate at relatively high speeds and low power demands.

Multispectral image analysis for object recognition and classification

NASA Astrophysics Data System (ADS)

Viau, C. R.; Payeur, P.; Cretu, A.-M.

2016-05-01

Computer and machine vision applications are used in numerous fields to analyze static and dynamic imagery in order to assist or automate decision-making processes. Advancements in sensor technologies now make it possible to capture and visualize imagery at various wavelengths (or bands) of the electromagnetic spectrum. Multispectral imaging has countless applications in various fields including (but not limited to) security, defense, space, medical, manufacturing and archeology. The development of advanced algorithms to process and extract salient information from the imagery is a critical component of the overall system performance. The fundamental objective of this research project was to investigate the benefits of combining imagery from the visual and thermal bands of the electromagnetic spectrum to improve the recognition rates and accuracy of commonly found objects in an office setting. A multispectral dataset (visual and thermal) was captured and features from the visual and thermal images were extracted and used to train support vector machine (SVM) classifiers. The SVM's class prediction ability was evaluated separately on the visual, thermal and multispectral testing datasets.

A new method for recognizing quadric surfaces from range data and its application to telerobotics and automation, final phase

NASA Technical Reports Server (NTRS)

Mielke, Roland; Dcunha, Ivan; Alvertos, Nicolas

1994-01-01

In the final phase of the proposed research a complete top to down three dimensional object recognition scheme has been proposed. The various three dimensional objects included spheres, cones, cylinders, ellipsoids, paraboloids, and hyperboloids. Utilizing a newly developed blob determination technique, a given range scene with several non-cluttered quadric surfaces is segmented. Next, using the earlier (phase 1) developed alignment scheme, each of the segmented objects are then aligned in a desired coordinate system. For each of the quadric surfaces based upon their intersections with certain pre-determined planes, a set of distinct features (curves) are obtained. A database with entities such as the equations of the planes and angular bounds of these planes has been created for each of the quadric surfaces. Real range data of spheres, cones, cylinders, and parallelpipeds have been utilized for the recognition process. The developed algorithm gave excellent results for the real data as well as for several sets of simulated range data.

Shaped-Based Recognition of 3D Objects From 2D Projections

DTIC Science & Technology

2006-12-01

functions for a typical minimization by the graduated assignment algorithm. (The solid line is E , which uses the Euclid- ean distances to the nearest...of E and E0 generally decrease during the optimiza- tion process, but they can also rise because of changes in the assignment variables Mjk...m+ 1)× (n+ 1) match matrix M that minimizes the objective function E = mX j=1 nX k=1 Mjk ³ d (T (lj) , l 0 k) 2 − δ2 ´ . (7) M defines the

Force/torque and tactile sensors for sensor-based manipulator control

NASA Technical Reports Server (NTRS)

Vanbrussel, H.; Belieen, H.; Bao, Chao-Ying

1989-01-01

The autonomy of manipulators, in space and in industrial environments, can be dramatically enhanced by the use of force/torque and tactile sensors. The development and future use of a six-component force/torque sensor for the Hermes Robot Arm (HERA) Basic End-Effector (BEE) is discussed. Then a multifunctional gripper system based on tactile sensors is described. The basic transducing element of the sensor is a sheet of pressure-sensitive polymer. Tactile image processing algorithms for slip detection, object position estimation, and object recognition are described.

Monitoring of facial stress during space flight: Optical computer recognition combining discriminative and generative methods

NASA Astrophysics Data System (ADS)

Dinges, David F.; Venkataraman, Sundara; McGlinchey, Eleanor L.; Metaxas, Dimitris N.

2007-02-01

Astronauts are required to perform mission-critical tasks at a high level of functional capability throughout spaceflight. Stressors can compromise their ability to do so, making early objective detection of neurobehavioral problems in spaceflight a priority. Computer optical approaches offer a completely unobtrusive way to detect distress during critical operations in space flight. A methodology was developed and a study completed to determine whether optical computer recognition algorithms could be used to discriminate facial expressions during stress induced by performance demands. Stress recognition from a facial image sequence is a subject that has not received much attention although it is an important problem for many applications beyond space flight (security, human-computer interaction, etc.). This paper proposes a comprehensive method to detect stress from facial image sequences by using a model-based tracker. The image sequences were captured as subjects underwent a battery of psychological tests under high- and low-stress conditions. A cue integration-based tracking system accurately captured the rigid and non-rigid parameters of different parts of the face (eyebrows, lips). The labeled sequences were used to train the recognition system, which consisted of generative (hidden Markov model) and discriminative (support vector machine) parts that yield results superior to using either approach individually. The current optical algorithm methods performed at a 68% accuracy rate in an experimental study of 60 healthy adults undergoing periods of high-stress versus low-stress performance demands. Accuracy and practical feasibility of the technique is being improved further with automatic multi-resolution selection for the discretization of the mask, and automated face detection and mask initialization algorithms.

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.

Anthropomorphic robot for recognition and drawing generalized object images

NASA Astrophysics Data System (ADS)

Ginzburg, Vera M.

1998-10-01

The process of recognition, for instance, understanding the text, written by different fonts, consists in the depriving of the individual attributes of the letters in the particular font. It is shown that such process, in Nature and technique, can be provided by the narrowing the spatial frequency of the object's image by its defocusing. In defocusing images remain only areas, so-called Informative Fragments (IFs), which all together form the generalized (stylized) image of many identical objects. It is shown that the variety of shapes of IFs is restricted and can be presented by `Geometrical alphabet'. The `letters' for this alphabet can be created using two basic `genetic' figures: a stripe and round spot. It is known from physiology that the special cells of visual cortex response to these particular figures. The prototype of such `genetic' alphabet has been made using Boolean algebra (Venn's diagrams). The algorithm for drawing the letter's (`genlet's') shape in this alphabet and generalized images of objects (for example, `sleeping cat'), are given. A scheme of an anthropomorphic robot is shown together with results of model computer experiment of the robot's action--`drawing' the generalized image.

A Human Activity Recognition System Using Skeleton Data from RGBD Sensors.

PubMed

Cippitelli, Enea; Gasparrini, Samuele; Gambi, Ennio; Spinsante, Susanna

2016-01-01

The aim of Active and Assisted Living is to develop tools to promote the ageing in place of elderly people, and human activity recognition algorithms can help to monitor aged people in home environments. Different types of sensors can be used to address this task and the RGBD sensors, especially the ones used for gaming, are cost-effective and provide much information about the environment. This work aims to propose an activity recognition algorithm exploiting skeleton data extracted by RGBD sensors. The system is based on the extraction of key poses to compose a feature vector, and a multiclass Support Vector Machine to perform classification. Computation and association of key poses are carried out using a clustering algorithm, without the need of a learning algorithm. The proposed approach is evaluated on five publicly available datasets for activity recognition, showing promising results especially when applied for the recognition of AAL related actions. Finally, the current applicability of this solution in AAL scenarios and the future improvements needed are discussed.

Gaussian mixture models-based ship target recognition algorithm in remote sensing infrared images

NASA Astrophysics Data System (ADS)

Yao, Shoukui; Qin, Xiaojuan

2018-02-01

Since the resolution of remote sensing infrared images is low, the features of ship targets become unstable. The issue of how to recognize ships with fuzzy features is an open problem. In this paper, we propose a novel ship target recognition algorithm based on Gaussian mixture models (GMMs). In the proposed algorithm, there are mainly two steps. At the first step, the Hu moments of these ship target images are calculated, and the GMMs are trained on the moment features of ships. At the second step, the moment feature of each ship image is assigned to the trained GMMs for recognition. Because of the scale, rotation, translation invariance property of Hu moments and the power feature-space description ability of GMMs, the GMMs-based ship target recognition algorithm can recognize ship reliably. Experimental results of a large simulating image set show that our approach is effective in distinguishing different ship types, and obtains a satisfactory ship recognition performance.

Word recognition using a lexicon constrained by first/last character decisions

NASA Astrophysics Data System (ADS)

Zhao, Sheila X.; Srihari, Sargur N.

1995-03-01

In lexicon based recognition of machine-printed word images, the size of the lexicon can be quite extensive. The recognition performance is closely related to the size of the lexicon. Recognition performance drops quickly when lexicon size increases. Here, we present an algorithm to improve the word recognition performance by reducing the size of the given lexicon. The algorithm utilizes the information provided by the first and last characters of a word to reduce the size of the given lexicon. Given a word image and a lexicon that contains the word in the image, the first and last characters are segmented and then recognized by a character classifier. The possible candidates based on the results given by the classifier are selected, which give us the sub-lexicon. Then a word shape analysis algorithm is applied to produce the final ranking of the given lexicon. The algorithm was tested on a set of machine- printed gray-scale word images which includes a wide range of print types and qualities.

Learning graph matching.

PubMed

Caetano, Tibério S; McAuley, Julian J; Cheng, Li; Le, Quoc V; Smola, Alex J

2009-06-01

As a fundamental problem in pattern recognition, graph matching has applications in a variety of fields, from computer vision to computational biology. In graph matching, patterns are modeled as graphs and pattern recognition amounts to finding a correspondence between the nodes of different graphs. Many formulations of this problem can be cast in general as a quadratic assignment problem, where a linear term in the objective function encodes node compatibility and a quadratic term encodes edge compatibility. The main research focus in this theme is about designing efficient algorithms for approximately solving the quadratic assignment problem, since it is NP-hard. In this paper we turn our attention to a different question: how to estimate compatibility functions such that the solution of the resulting graph matching problem best matches the expected solution that a human would manually provide. We present a method for learning graph matching: the training examples are pairs of graphs and the 'labels' are matches between them. Our experimental results reveal that learning can substantially improve the performance of standard graph matching algorithms. In particular, we find that simple linear assignment with such a learning scheme outperforms Graduated Assignment with bistochastic normalisation, a state-of-the-art quadratic assignment relaxation algorithm.

Vision-based posture recognition using an ensemble classifier and a vote filter

NASA Astrophysics Data System (ADS)

Ji, Peng; Wu, Changcheng; Xu, Xiaonong; Song, Aiguo; Li, Huijun

2016-10-01

Posture recognition is a very important Human-Robot Interaction (HRI) way. To segment effective posture from an image, we propose an improved region grow algorithm which combining with the Single Gauss Color Model. The experiment shows that the improved region grow algorithm can get the complete and accurate posture than traditional Single Gauss Model and region grow algorithm, and it can eliminate the similar region from the background at the same time. In the posture recognition part, and in order to improve the recognition rate, we propose a CNN ensemble classifier, and in order to reduce the misjudgments during a continuous gesture control, a vote filter is proposed and applied to the sequence of recognition results. Comparing with CNN classifier, the CNN ensemble classifier we proposed can yield a 96.27% recognition rate, which is better than that of CNN classifier, and the proposed vote filter can improve the recognition result and reduce the misjudgments during the consecutive gesture switch.

An Indoor Pedestrian Positioning Method Using HMM with a Fuzzy Pattern Recognition Algorithm in a WLAN Fingerprint System

PubMed Central

Ni, Yepeng; Liu, Jianbo; Liu, Shan; Bai, Yaxin

2016-01-01

With the rapid development of smartphones and wireless networks, indoor location-based services have become more and more prevalent. Due to the sophisticated propagation of radio signals, the Received Signal Strength Indicator (RSSI) shows a significant variation during pedestrian walking, which introduces critical errors in deterministic indoor positioning. To solve this problem, we present a novel method to improve the indoor pedestrian positioning accuracy by embedding a fuzzy pattern recognition algorithm into a Hidden Markov Model. The fuzzy pattern recognition algorithm follows the rule that the RSSI fading has a positive correlation to the distance between the measuring point and the AP location even during a dynamic positioning measurement. Through this algorithm, we use the RSSI variation trend to replace the specific RSSI value to achieve a fuzzy positioning. The transition probability of the Hidden Markov Model is trained by the fuzzy pattern recognition algorithm with pedestrian trajectories. Using the Viterbi algorithm with the trained model, we can obtain a set of hidden location states. In our experiments, we demonstrate that, compared with the deterministic pattern matching algorithm, our method can greatly improve the positioning accuracy and shows robust environmental adaptability. PMID:27618053

[Non-destructive detection research for hollow heart of potato based on semi-transmission hyperspectral imaging and SVM].

PubMed

Huang, Tao; Li, Xiao-yu; Xu, Meng-ling; Jin, Rui; Ku, Jing; Xu, Sen-miao; Wu, Zhen-zhong

2015-01-01

The quality of potato is directly related to their edible value and industrial value. Hollow heart of potato, as a physiological disease occurred inside the tuber, is difficult to be detected. This paper put forward a non-destructive detection method by using semi-transmission hyperspectral imaging with support vector machine (SVM) to detect hollow heart of potato. Compared to reflection and transmission hyperspectral image, semi-transmission hyperspectral image can get clearer image which contains the internal quality information of agricultural products. In this study, 224 potato samples (149 normal samples and 75 hollow samples) were selected as the research object, and semi-transmission hyperspectral image acquisition system was constructed to acquire the hyperspectral images (390-1 040 nn) of the potato samples, and then the average spectrum of region of interest were extracted for spectral characteristics analysis. Normalize was used to preprocess the original spectrum, and prediction model were developed based on SVM using all wave bands, the accurate recognition rate of test set is only 87. 5%. In order to simplify the model competitive.adaptive reweighed sampling algorithm (CARS) and successive projection algorithm (SPA) were utilized to select important variables from the all 520 spectral variables and 8 variables were selected (454, 601, 639, 664, 748, 827, 874 and 936 nm). 94. 64% of the accurate recognition rate of test set was obtained by using the 8 variables to develop SVM model. Parameter optimization algorithms, including artificial fish swarm algorithm (AFSA), genetic algorithm (GA) and grid search algorithm, were used to optimize the SVM model parameters: penalty parameter c and kernel parameter g. After comparative analysis, AFSA, a new bionic optimization algorithm based on the foraging behavior of fish swarm, was proved to get the optimal model parameter (c=10. 659 1, g=0. 349 7), and the recognition accuracy of 10% were obtained for the AFSA-SVM model. The results indicate that combining the semi-transmission hyperspectral imaging technology with CARS-SPA and AFSA-SVM can accurately detect hollow heart of potato, and also provide technical support for rapid non-destructive detecting of hollow heart of potato.

Visual feature extraction and establishment of visual tags in the intelligent visual internet of things

NASA Astrophysics Data System (ADS)

Zhao, Yiqun; Wang, Zhihui

2015-12-01

The Internet of things (IOT) is a kind of intelligent networks which can be used to locate, track, identify and supervise people and objects. One of important core technologies of intelligent visual internet of things ( IVIOT) is the intelligent visual tag system. In this paper, a research is done into visual feature extraction and establishment of visual tags of the human face based on ORL face database. Firstly, we use the principal component analysis (PCA) algorithm for face feature extraction, then adopt the support vector machine (SVM) for classifying and face recognition, finally establish a visual tag for face which is already classified. We conducted a experiment focused on a group of people face images, the result show that the proposed algorithm have good performance, and can show the visual tag of objects conveniently.

The use of Merging and Aggregation Operators for MRDB Data Feeding

NASA Astrophysics Data System (ADS)

Kozioł, Krystian; Lupa, Michał

2013-12-01

This paper presents the application of two generalization operators - merging and displacement - in the process of automatic data feeding in a multiresolution data base of topographic objects from large-scale data-bases (1 : 500-1 : 5000). An ordered collection of objects makes a layer of development that in the process of generalization is subjected to the processes of merging and displacement in order to maintain recognizability in the reduced scale of the map. The solution to the above problem is the algorithms described in the work; these algorithms use the standard recognition of drawings (Chrobak 2010), independent of the user. A digital cartographic generalization process is a set of consecutive operators where merging and aggregation play a key role. The proper operation has a significant impact on the qualitative assessment of data generalization

Optical character recognition of handwritten Arabic using hidden Markov models

NASA Astrophysics Data System (ADS)

Aulama, Mohannad M.; Natsheh, Asem M.; Abandah, Gheith A.; Olama, Mohammed M.

2011-04-01

The problem of optical character recognition (OCR) of handwritten Arabic has not received a satisfactory solution yet. In this paper, an Arabic OCR algorithm is developed based on Hidden Markov Models (HMMs) combined with the Viterbi algorithm, which results in an improved and more robust recognition of characters at the sub-word level. Integrating the HMMs represents another step of the overall OCR trends being currently researched in the literature. The proposed approach exploits the structure of characters in the Arabic language in addition to their extracted features to achieve improved recognition rates. Useful statistical information of the Arabic language is initially extracted and then used to estimate the probabilistic parameters of the mathematical HMM. A new custom implementation of the HMM is developed in this study, where the transition matrix is built based on the collected large corpus, and the emission matrix is built based on the results obtained via the extracted character features. The recognition process is triggered using the Viterbi algorithm which employs the most probable sequence of sub-words. The model was implemented to recognize the sub-word unit of Arabic text raising the recognition rate from being linked to the worst recognition rate for any character to the overall structure of the Arabic language. Numerical results show that there is a potentially large recognition improvement by using the proposed algorithms.

Optical character recognition of handwritten Arabic using hidden Markov models

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

Aulama, Mohannad M.; Natsheh, Asem M.; Abandah, Gheith A.

2011-01-01

The problem of optical character recognition (OCR) of handwritten Arabic has not received a satisfactory solution yet. In this paper, an Arabic OCR algorithm is developed based on Hidden Markov Models (HMMs) combined with the Viterbi algorithm, which results in an improved and more robust recognition of characters at the sub-word level. Integrating the HMMs represents another step of the overall OCR trends being currently researched in the literature. The proposed approach exploits the structure of characters in the Arabic language in addition to their extracted features to achieve improved recognition rates. Useful statistical information of the Arabic language ismore » initially extracted and then used to estimate the probabilistic parameters of the mathematical HMM. A new custom implementation of the HMM is developed in this study, where the transition matrix is built based on the collected large corpus, and the emission matrix is built based on the results obtained via the extracted character features. The recognition process is triggered using the Viterbi algorithm which employs the most probable sequence of sub-words. The model was implemented to recognize the sub-word unit of Arabic text raising the recognition rate from being linked to the worst recognition rate for any character to the overall structure of the Arabic language. Numerical results show that there is a potentially large recognition improvement by using the proposed algorithms.« less

Three Dimensional Object Recognition Using a Complex Autoregressive Model

DTIC Science & Technology

1993-12-01

3.4.2 Template Matching Algorithm ...................... 3-16 3.4.3 K-Nearest-Neighbor ( KNN ) Techniques ................. 3-25 3.4.4 Hidden Markov Model...Neighbor ( KNN ) Test Results ...................... 4-13 4.2.1 Single-Look 1-NN Testing .......................... 4-14 4.2.2 Multiple-Look 1-NN Testing...4-15 4.2.3 Discussion of KNN Test Results ...................... 4-15 4.3 Hidden Markov Model (HMM) Test Results

Decoding ensemble activity from neurophysiological recordings in the temporal cortex.

PubMed

Kreiman, Gabriel

2011-01-01

We study subjects with pharmacologically intractable epilepsy who undergo semi-chronic implantation of electrodes for clinical purposes. We record physiological activity from tens to more than one hundred electrodes implanted in different parts of neocortex. These recordings provide higher spatial and temporal resolution than non-invasive measures of human brain activity. Here we discuss our efforts to develop hardware and algorithms to interact with the human brain by decoding ensemble activity in single trials. We focus our discussion on decoding visual information during a variety of visual object recognition tasks but the same technologies and algorithms can also be directly applied to other cognitive phenomena.

Optimization of Support Vector Machine (SVM) for Object Classification

NASA Technical Reports Server (NTRS)

Scholten, Matthew; Dhingra, Neil; Lu, Thomas T.; Chao, Tien-Hsin

2012-01-01

The Support Vector Machine (SVM) is a powerful algorithm, useful in classifying data into species. The SVMs implemented in this research were used as classifiers for the final stage in a Multistage Automatic Target Recognition (ATR) system. A single kernel SVM known as SVMlight, and a modified version known as a SVM with K-Means Clustering were used. These SVM algorithms were tested as classifiers under varying conditions. Image noise levels varied, and the orientation of the targets changed. The classifiers were then optimized to demonstrate their maximum potential as classifiers. Results demonstrate the reliability of SVM as a method for classification. From trial to trial, SVM produces consistent results.

Dynamic Programming and Graph Algorithms in Computer Vision*

PubMed Central

Felzenszwalb, Pedro F.; Zabih, Ramin

2013-01-01

Optimization is a powerful paradigm for expressing and solving problems in a wide range of areas, and has been successfully applied to many vision problems. Discrete optimization techniques are especially interesting, since by carefully exploiting problem structure they often provide non-trivial guarantees concerning solution quality. In this paper we briefly review dynamic programming and graph algorithms, and discuss representative examples of how these discrete optimization techniques have been applied to some classical vision problems. We focus on the low-level vision problem of stereo; the mid-level problem of interactive object segmentation; and the high-level problem of model-based recognition. PMID:20660950

Essential Autonomous Science Inference on Rovers (EASIR)

NASA Technical Reports Server (NTRS)

Roush, Ted L.; Shipman, Mark; Morris, Robert; Gazis, Paul; Pedersen, Liam

2003-01-01

Existing constraints on time, computational, and communication resources associated with Mars rover missions suggest on-board science evaluation of sensor data can contribute to decreasing human-directed operational planning, optimizing returned science data volumes, and recognition of unique or novel data. All of which act to increase the scientific return from a mission. Many different levels of science autonomy exist and each impacts the data collected and returned by, and activities of, rovers. Several computational algorithms, designed to recognize objects of interest to geologists and biologists, are discussed. The algorithms represent various functions that producing scientific opinions and several scenarios illustrate how the opinions can be used.

Distributed pheromone-based swarming control of unmanned air and ground vehicles for RSTA

NASA Astrophysics Data System (ADS)

Sauter, John A.; Mathews, Robert S.; Yinger, Andrew; Robinson, Joshua S.; Moody, John; Riddle, Stephanie

2008-04-01

The use of unmanned vehicles in Reconnaissance, Surveillance, and Target Acquisition (RSTA) applications has received considerable attention recently. Cooperating land and air vehicles can support multiple sensor modalities providing pervasive and ubiquitous broad area sensor coverage. However coordination of multiple air and land vehicles serving different mission objectives in a dynamic and complex environment is a challenging problem. Swarm intelligence algorithms, inspired by the mechanisms used in natural systems to coordinate the activities of many entities provide a promising alternative to traditional command and control approaches. This paper describes recent advances in a fully distributed digital pheromone algorithm that has demonstrated its effectiveness in managing the complexity of swarming unmanned systems. The results of a recent demonstration at NASA's Wallops Island of multiple Aerosonde Unmanned Air Vehicles (UAVs) and Pioneer Unmanned Ground Vehicles (UGVs) cooperating in a coordinated RSTA application are discussed. The vehicles were autonomously controlled by the onboard digital pheromone responding to the needs of the automatic target recognition algorithms. UAVs and UGVs controlled by the same pheromone algorithm self-organized to perform total area surveillance, automatic target detection, sensor cueing, and automatic target recognition with no central processing or control and minimal operator input. Complete autonomy adds several safety and fault tolerance requirements which were integrated into the basic pheromone framework. The adaptive algorithms demonstrated the ability to handle some unplanned hardware failures during the demonstration without any human intervention. The paper describes lessons learned and the next steps for this promising technology.

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.

Window-based method for approximating the Hausdorff in three-dimensional range imagery

DOEpatents

Koch, Mark W [Albuquerque, NM

2009-06-02

One approach to pattern recognition is to use a template from a database of objects and match it to a probe image containing the unknown. Accordingly, the Hausdorff distance can be used to measure the similarity of two sets of points. In particular, the Hausdorff can measure the goodness of a match in the presence of occlusion, clutter, and noise. However, existing 3D algorithms for calculating the Hausdorff are computationally intensive, making them impractical for pattern recognition that requires scanning of large databases. The present invention is directed to a new method that can efficiently, in time and memory, compute the Hausdorff for 3D range imagery. The method uses a window-based approach.

Fast processing of microscopic images using object-based extended depth of field.

PubMed

Intarapanich, Apichart; Kaewkamnerd, Saowaluck; Pannarut, Montri; Shaw, Philip J; Tongsima, Sissades

2016-12-22

Microscopic analysis requires that foreground objects of interest, e.g. cells, are in focus. In a typical microscopic specimen, the foreground objects may lie on different depths of field necessitating capture of multiple images taken at different focal planes. The extended depth of field (EDoF) technique is a computational method for merging images from different depths of field into a composite image with all foreground objects in focus. Composite images generated by EDoF can be applied in automated image processing and pattern recognition systems. However, current algorithms for EDoF are computationally intensive and impractical, especially for applications such as medical diagnosis where rapid sample turnaround is important. Since foreground objects typically constitute a minor part of an image, the EDoF technique could be made to work much faster if only foreground regions are processed to make the composite image. We propose a novel algorithm called object-based extended depths of field (OEDoF) to address this issue. The OEDoF algorithm consists of four major modules: 1) color conversion, 2) object region identification, 3) good contrast pixel identification and 4) detail merging. First, the algorithm employs color conversion to enhance contrast followed by identification of foreground pixels. A composite image is constructed using only these foreground pixels, which dramatically reduces the computational time. We used 250 images obtained from 45 specimens of confirmed malaria infections to test our proposed algorithm. The resulting composite images with all in-focus objects were produced using the proposed OEDoF algorithm. We measured the performance of OEDoF in terms of image clarity (quality) and processing time. The features of interest selected by the OEDoF algorithm are comparable in quality with equivalent regions in images processed by the state-of-the-art complex wavelet EDoF algorithm; however, OEDoF required four times less processing time. This work presents a modification of the extended depth of field approach for efficiently enhancing microscopic images. This selective object processing scheme used in OEDoF can significantly reduce the overall processing time while maintaining the clarity of important image features. The empirical results from parasite-infected red cell images revealed that our proposed method efficiently and effectively produced in-focus composite images. With the speed improvement of OEDoF, this proposed algorithm is suitable for processing large numbers of microscope images, e.g., as required for medical diagnosis.

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot

PubMed Central

Taniguchi, Tadahiro; Yoshino, Ryo; Takano, Toshiaki

2018-01-01

In this paper, we propose an active perception method for recognizing object categories based on the multimodal hierarchical Dirichlet process (MHDP). The MHDP enables a robot to form object categories using multimodal information, e.g., visual, auditory, and haptic information, which can be observed by performing actions on an object. However, performing many actions on a target object requires a long time. In a real-time scenario, i.e., when the time is limited, the robot has to determine the set of actions that is most effective for recognizing a target object. We propose an active perception for MHDP method that uses the information gain (IG) maximization criterion and lazy greedy algorithm. We show that the IG maximization criterion is optimal in the sense that the criterion is equivalent to a minimization of the expected Kullback–Leibler divergence between a final recognition state and the recognition state after the next set of actions. However, a straightforward calculation of IG is practically impossible. Therefore, we derive a Monte Carlo approximation method for IG by making use of a property of the MHDP. We also show that the IG has submodular and non-decreasing properties as a set function because of the structure of the graphical model of the MHDP. Therefore, the IG maximization problem is reduced to a submodular maximization problem. This means that greedy and lazy greedy algorithms are effective and have a theoretical justification for their performance. We conducted an experiment using an upper-torso humanoid robot and a second one using synthetic data. The experimental results show that the method enables the robot to select a set of actions that allow it to recognize target objects quickly and accurately. The numerical experiment using the synthetic data shows that the proposed method can work appropriately even when the number of actions is large and a set of target objects involves objects categorized into multiple classes. The results support our theoretical outcomes. PMID:29872389

Multimodal Hierarchical Dirichlet Process-Based Active Perception by a Robot.

PubMed

Taniguchi, Tadahiro; Yoshino, Ryo; Takano, Toshiaki

2018-01-01

In this paper, we propose an active perception method for recognizing object categories based on the multimodal hierarchical Dirichlet process (MHDP). The MHDP enables a robot to form object categories using multimodal information, e.g., visual, auditory, and haptic information, which can be observed by performing actions on an object. However, performing many actions on a target object requires a long time. In a real-time scenario, i.e., when the time is limited, the robot has to determine the set of actions that is most effective for recognizing a target object. We propose an active perception for MHDP method that uses the information gain (IG) maximization criterion and lazy greedy algorithm. We show that the IG maximization criterion is optimal in the sense that the criterion is equivalent to a minimization of the expected Kullback-Leibler divergence between a final recognition state and the recognition state after the next set of actions. However, a straightforward calculation of IG is practically impossible. Therefore, we derive a Monte Carlo approximation method for IG by making use of a property of the MHDP. We also show that the IG has submodular and non-decreasing properties as a set function because of the structure of the graphical model of the MHDP. Therefore, the IG maximization problem is reduced to a submodular maximization problem. This means that greedy and lazy greedy algorithms are effective and have a theoretical justification for their performance. We conducted an experiment using an upper-torso humanoid robot and a second one using synthetic data. The experimental results show that the method enables the robot to select a set of actions that allow it to recognize target objects quickly and accurately. The numerical experiment using the synthetic data shows that the proposed method can work appropriately even when the number of actions is large and a set of target objects involves objects categorized into multiple classes. The results support our theoretical outcomes.

Collegial Activity Learning between Heterogeneous Sensors.

PubMed

Feuz, Kyle D; Cook, Diane J

2017-11-01

Activity recognition algorithms have matured and become more ubiquitous in recent years. However, these algorithms are typically customized for a particular sensor platform. In this paper we introduce PECO, a Personalized activity ECOsystem, that transfers learned activity information seamlessly between sensor platforms in real time so that any available sensor can continue to track activities without requiring its own extensive labeled training data. We introduce a multi-view transfer learning algorithm that facilitates this information handoff between sensor platforms and provide theoretical performance bounds for the algorithm. In addition, we empirically evaluate PECO using datasets that utilize heterogeneous sensor platforms to perform activity recognition. These results indicate that not only can activity recognition algorithms transfer important information to new sensor platforms, but any number of platforms can work together as colleagues to boost performance.

Pulmonary Nodule Recognition Based on Multiple Kernel Learning Support Vector Machine-PSO

PubMed Central

Zhu, Zhichuan; Zhao, Qingdong; Liu, Liwei; Zhang, Lijuan

2018-01-01

Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely used in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has achieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course of parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is introduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm so as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertia weights such as constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition. The experimental results show that the model training time of the proposed MKL-SVM-PSO algorithm is only 1/7 of the training time of the MKL-SVM grid search algorithm, achieving better recognition effect. Moreover, Euclidean norm of normalized error vector is proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence. Through statistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial weight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the parameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence is much closer to the optimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified. PMID:29853983

Pulmonary Nodule Recognition Based on Multiple Kernel Learning Support Vector Machine-PSO.

PubMed

Li, Yang; Zhu, Zhichuan; Hou, Alin; Zhao, Qingdong; Liu, Liwei; Zhang, Lijuan

2018-01-01

Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely used in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has achieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course of parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is introduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm so as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertia weights such as constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition. The experimental results show that the model training time of the proposed MKL-SVM-PSO algorithm is only 1/7 of the training time of the MKL-SVM grid search algorithm, achieving better recognition effect. Moreover, Euclidean norm of normalized error vector is proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence. Through statistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial weight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the parameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence is much closer to the optimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified.

Acoustic diagnosis of pulmonary hypertension: automated speech- recognition-inspired classification algorithm outperforms physicians

NASA Astrophysics Data System (ADS)

Kaddoura, Tarek; Vadlamudi, Karunakar; Kumar, Shine; Bobhate, Prashant; Guo, Long; Jain, Shreepal; Elgendi, Mohamed; Coe, James Y.; Kim, Daniel; Taylor, Dylan; Tymchak, Wayne; Schuurmans, Dale; Zemp, Roger J.; Adatia, Ian

2016-09-01

We hypothesized that an automated speech- recognition-inspired classification algorithm could differentiate between the heart sounds in subjects with and without pulmonary hypertension (PH) and outperform physicians. Heart sounds, electrocardiograms, and mean pulmonary artery pressures (mPAp) were recorded simultaneously. Heart sound recordings were digitized to train and test speech-recognition-inspired classification algorithms. We used mel-frequency cepstral coefficients to extract features from the heart sounds. Gaussian-mixture models classified the features as PH (mPAp ≥ 25 mmHg) or normal (mPAp < 25 mmHg). Physicians blinded to patient data listened to the same heart sound recordings and attempted a diagnosis. We studied 164 subjects: 86 with mPAp ≥ 25 mmHg (mPAp 41 ± 12 mmHg) and 78 with mPAp < 25 mmHg (mPAp 17 ± 5 mmHg) (p  < 0.005). The correct diagnostic rate of the automated speech-recognition-inspired algorithm was 74% compared to 56% by physicians (p = 0.005). The false positive rate for the algorithm was 34% versus 50% (p = 0.04) for clinicians. The false negative rate for the algorithm was 23% and 68% (p = 0.0002) for physicians. We developed an automated speech-recognition-inspired classification algorithm for the acoustic diagnosis of PH that outperforms physicians that could be used to screen for PH and encourage earlier specialist referral.

Mathematical algorithm for the automatic recognition of intestinal parasites.

PubMed

Alva, Alicia; Cangalaya, Carla; Quiliano, Miguel; Krebs, Casey; Gilman, Robert H; Sheen, Patricia; Zimic, Mirko

2017-01-01

Parasitic infections are generally diagnosed by professionals trained to recognize the morphological characteristics of the eggs in microscopic images of fecal smears. However, this laboratory diagnosis requires medical specialists which are lacking in many of the areas where these infections are most prevalent. In response to this public health issue, we developed a software based on pattern recognition analysis from microscopi digital images of fecal smears, capable of automatically recognizing and diagnosing common human intestinal parasites. To this end, we selected 229, 124, 217, and 229 objects from microscopic images of fecal smears positive for Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica, respectively. Representative photographs were selected by a parasitologist. We then implemented our algorithm in the open source program SCILAB. The algorithm processes the image by first converting to gray-scale, then applies a fourteen step filtering process, and produces a skeletonized and tri-colored image. The features extracted fall into two general categories: geometric characteristics and brightness descriptions. Individual characteristics were quantified and evaluated with a logistic regression to model their ability to correctly identify each parasite separately. Subsequently, all algorithms were evaluated for false positive cross reactivity with the other parasites studied, excepting Taenia sp. which shares very few morphological characteristics with the others. The principal result showed that our algorithm reached sensitivities between 99.10%-100% and specificities between 98.13%- 98.38% to detect each parasite separately. We did not find any cross-positivity in the algorithms for the three parasites evaluated. In conclusion, the results demonstrated the capacity of our computer algorithm to automatically recognize and diagnose Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica with a high sensitivity and specificity.

Mathematical algorithm for the automatic recognition of intestinal parasites

PubMed Central

Alva, Alicia; Cangalaya, Carla; Quiliano, Miguel; Krebs, Casey; Gilman, Robert H.; Sheen, Patricia; Zimic, Mirko

2017-01-01

Parasitic infections are generally diagnosed by professionals trained to recognize the morphological characteristics of the eggs in microscopic images of fecal smears. However, this laboratory diagnosis requires medical specialists which are lacking in many of the areas where these infections are most prevalent. In response to this public health issue, we developed a software based on pattern recognition analysis from microscopi digital images of fecal smears, capable of automatically recognizing and diagnosing common human intestinal parasites. To this end, we selected 229, 124, 217, and 229 objects from microscopic images of fecal smears positive for Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica, respectively. Representative photographs were selected by a parasitologist. We then implemented our algorithm in the open source program SCILAB. The algorithm processes the image by first converting to gray-scale, then applies a fourteen step filtering process, and produces a skeletonized and tri-colored image. The features extracted fall into two general categories: geometric characteristics and brightness descriptions. Individual characteristics were quantified and evaluated with a logistic regression to model their ability to correctly identify each parasite separately. Subsequently, all algorithms were evaluated for false positive cross reactivity with the other parasites studied, excepting Taenia sp. which shares very few morphological characteristics with the others. The principal result showed that our algorithm reached sensitivities between 99.10%-100% and specificities between 98.13%- 98.38% to detect each parasite separately. We did not find any cross-positivity in the algorithms for the three parasites evaluated. In conclusion, the results demonstrated the capacity of our computer algorithm to automatically recognize and diagnose Taenia sp., Trichuris trichiura, Diphyllobothrium latum, and Fasciola hepatica with a high sensitivity and specificity. PMID:28410387

Knowledge-based vision for space station object motion detection, recognition, and tracking

NASA Technical Reports Server (NTRS)

Symosek, P.; Panda, D.; Yalamanchili, S.; Wehner, W., III

1987-01-01

Computer vision, especially color image analysis and understanding, has much to offer in the area of the automation of Space Station tasks such as construction, satellite servicing, rendezvous and proximity operations, inspection, experiment monitoring, data management and training. Knowledge-based techniques improve the performance of vision algorithms for unstructured environments because of their ability to deal with imprecise a priori information or inaccurately estimated feature data and still produce useful results. Conventional techniques using statistical and purely model-based approaches lack flexibility in dealing with the variabilities anticipated in the unstructured viewing environment of space. Algorithms developed under NASA sponsorship for Space Station applications to demonstrate the value of a hypothesized architecture for a Video Image Processor (VIP) are presented. Approaches to the enhancement of the performance of these algorithms with knowledge-based techniques and the potential for deployment of highly-parallel multi-processor systems for these algorithms are discussed.

Laser radar system for obstacle avoidance

NASA Astrophysics Data System (ADS)

Bers, Karlheinz; Schulz, Karl R.; Armbruster, Walter

2005-09-01

The threat of hostile surveillance and weapon systems require military aircraft to fly under extreme conditions such as low altitude, high speed, poor visibility and incomplete terrain information. The probability of collision with natural and man-made obstacles during such contour missions is high if detection capability is restricted to conventional vision aids. Forward-looking scanning laser radars which are build by the EADS company and presently being flight tested and evaluated at German proving grounds, provide a possible solution, having a large field of view, high angular and range resolution, a high pulse repetition rate, and sufficient pulse energy to register returns from objects at distances of military relevance with a high hit-and-detect probability. The development of advanced 3d-scene analysis algorithms had increased the recognition probability and reduced the false alarm rate by using more readily recognizable objects such as terrain, poles, pylons, trees, etc. to generate a parametric description of the terrain surface as well as the class, position, orientation, size and shape of all objects in the scene. The sensor system and the implemented algorithms can be used for other applications such as terrain following, autonomous obstacle avoidance, and automatic target recognition. This paper describes different 3D-imaging ladar sensors with unique system architecture but different components matched for different military application. Emphasis is laid on an obstacle warning system with a high probability of detection of thin wires, the real time processing of the measured range image data, obstacle classification und visualization.

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

DOE PAGES

James, Conrad D.; Aimone, James B.; Miner, Nadine E.; ...

2017-01-04

In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classesmore » such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.« less

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

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

James, Conrad D.; Aimone, James B.; Miner, Nadine E.

In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classesmore » such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.« less

Flightspeed Integral Image Analysis Toolkit

NASA Technical Reports Server (NTRS)

Thompson, David R.

2009-01-01

The Flightspeed Integral Image Analysis Toolkit (FIIAT) is a C library that provides image analysis functions in a single, portable package. It provides basic low-level filtering, texture analysis, and subwindow descriptor for applications dealing with image interpretation and object recognition. Designed with spaceflight in mind, it addresses: Ease of integration (minimal external dependencies) Fast, real-time operation using integer arithmetic where possible (useful for platforms lacking a dedicated floatingpoint processor) Written entirely in C (easily modified) Mostly static memory allocation 8-bit image data The basic goal of the FIIAT library is to compute meaningful numerical descriptors for images or rectangular image regions. These n-vectors can then be used directly for novelty detection or pattern recognition, or as a feature space for higher-level pattern recognition tasks. The library provides routines for leveraging training data to derive descriptors that are most useful for a specific data set. Its runtime algorithms exploit a structure known as the "integral image." This is a caching method that permits fast summation of values within rectangular regions of an image. This integral frame facilitates a wide range of fast image-processing functions. This toolkit has applicability to a wide range of autonomous image analysis tasks in the space-flight domain, including novelty detection, object and scene classification, target detection for autonomous instrument placement, and science analysis of geomorphology. It makes real-time texture and pattern recognition possible for platforms with severe computational restraints. The software provides an order of magnitude speed increase over alternative software libraries currently in use by the research community. FIIAT can commercially support intelligent video cameras used in intelligent surveillance. It is also useful for object recognition by robots or other autonomous vehicles

A novel speech processing algorithm based on harmonicity cues in cochlear implant

NASA Astrophysics Data System (ADS)

Wang, Jian; Chen, Yousheng; Zhang, Zongping; Chen, Yan; Zhang, Weifeng

2017-08-01

This paper proposed a novel speech processing algorithm in cochlear implant, which used harmonicity cues to enhance tonal information in Mandarin Chinese speech recognition. The input speech was filtered by a 4-channel band-pass filter bank. The frequency ranges for the four bands were: 300-621, 621-1285, 1285-2657, and 2657-5499 Hz. In each pass band, temporal envelope and periodicity cues (TEPCs) below 400 Hz were extracted by full wave rectification and low-pass filtering. The TEPCs were modulated by a sinusoidal carrier, the frequency of which was fundamental frequency (F0) and its harmonics most close to the center frequency of each band. Signals from each band were combined together to obtain an output speech. Mandarin tone, word, and sentence recognition in quiet listening conditions were tested for the extensively used continuous interleaved sampling (CIS) strategy and the novel F0-harmonic algorithm. Results found that the F0-harmonic algorithm performed consistently better than CIS strategy in Mandarin tone, word, and sentence recognition. In addition, sentence recognition rate was higher than word recognition rate, as a result of contextual information in the sentence. Moreover, tone 3 and 4 performed better than tone 1 and tone 2, due to the easily identified features of the former. In conclusion, the F0-harmonic algorithm could enhance tonal information in cochlear implant speech processing due to the use of harmonicity cues, thereby improving Mandarin tone, word, and sentence recognition. Further study will focus on the test of the F0-harmonic algorithm in noisy listening conditions.

Twelve automated thresholding methods for segmentation of PET images: a phantom study.

PubMed

Prieto, Elena; Lecumberri, Pablo; Pagola, Miguel; Gómez, Marisol; Bilbao, Izaskun; Ecay, Margarita; Peñuelas, Iván; Martí-Climent, Josep M

2012-06-21

Tumor volume delineation over positron emission tomography (PET) images is of great interest for proper diagnosis and therapy planning. However, standard segmentation techniques (manual or semi-automated) are operator dependent and time consuming while fully automated procedures are cumbersome or require complex mathematical development. The aim of this study was to segment PET images in a fully automated way by implementing a set of 12 automated thresholding algorithms, classical in the fields of optical character recognition, tissue engineering or non-destructive testing images in high-tech structures. Automated thresholding algorithms select a specific threshold for each image without any a priori spatial information of the segmented object or any special calibration of the tomograph, as opposed to usual thresholding methods for PET. Spherical (18)F-filled objects of different volumes were acquired on clinical PET/CT and on a small animal PET scanner, with three different signal-to-background ratios. Images were segmented with 12 automatic thresholding algorithms and results were compared with the standard segmentation reference, a threshold at 42% of the maximum uptake. Ridler and Ramesh thresholding algorithms based on clustering and histogram-shape information, respectively, provided better results that the classical 42%-based threshold (p < 0.05). We have herein demonstrated that fully automated thresholding algorithms can provide better results than classical PET segmentation tools.

Twelve automated thresholding methods for segmentation of PET images: a phantom study

NASA Astrophysics Data System (ADS)

Prieto, Elena; Lecumberri, Pablo; Pagola, Miguel; Gómez, Marisol; Bilbao, Izaskun; Ecay, Margarita; Peñuelas, Iván; Martí-Climent, Josep M.

2012-06-01

Tumor volume delineation over positron emission tomography (PET) images is of great interest for proper diagnosis and therapy planning. However, standard segmentation techniques (manual or semi-automated) are operator dependent and time consuming while fully automated procedures are cumbersome or require complex mathematical development. The aim of this study was to segment PET images in a fully automated way by implementing a set of 12 automated thresholding algorithms, classical in the fields of optical character recognition, tissue engineering or non-destructive testing images in high-tech structures. Automated thresholding algorithms select a specific threshold for each image without any a priori spatial information of the segmented object or any special calibration of the tomograph, as opposed to usual thresholding methods for PET. Spherical 18F-filled objects of different volumes were acquired on clinical PET/CT and on a small animal PET scanner, with three different signal-to-background ratios. Images were segmented with 12 automatic thresholding algorithms and results were compared with the standard segmentation reference, a threshold at 42% of the maximum uptake. Ridler and Ramesh thresholding algorithms based on clustering and histogram-shape information, respectively, provided better results that the classical 42%-based threshold (p < 0.05). We have herein demonstrated that fully automated thresholding algorithms can provide better results than classical PET segmentation tools.

Infrared vehicle recognition using unsupervised feature learning based on K-feature

NASA Astrophysics Data System (ADS)

Lin, Jin; Tan, Yihua; Xia, Haijiao; Tian, Jinwen

2018-02-01

Subject to the complex battlefield environment, it is difficult to establish a complete knowledge base in practical application of vehicle recognition algorithms. The infrared vehicle recognition is always difficult and challenging, which plays an important role in remote sensing. In this paper we propose a new unsupervised feature learning method based on K-feature to recognize vehicle in infrared images. First, we use the target detection algorithm which is based on the saliency to detect the initial image. Then, the unsupervised feature learning based on K-feature, which is generated by Kmeans clustering algorithm that extracted features by learning a visual dictionary from a large number of samples without label, is calculated to suppress the false alarm and improve the accuracy. Finally, the vehicle target recognition image is finished by some post-processing. Large numbers of experiments demonstrate that the proposed method has satisfy recognition effectiveness and robustness for vehicle recognition in infrared images under complex backgrounds, and it also improve the reliability of it.

Wide-threat detection: recognition of adversarial missions and activity patterns in Empire Challenge 2009

NASA Astrophysics Data System (ADS)

Levchuk, Georgiy; Shabarekh, Charlotte; Furjanic, Caitlin

2011-06-01

In this paper, we present results of adversarial activity recognition using data collected in the Empire Challenge (EC 09) exercise. The EC09 experiment provided an opportunity to evaluate our probabilistic spatiotemporal mission recognition algorithms using the data from live air-born and ground sensors. Using ambiguous and noisy data about locations of entities and motion events on the ground, the algorithms inferred the types and locations of OPFOR activities, including reconnaissance, cache runs, IED emplacements, logistics, and planning meetings. In this paper, we present detailed summary of the validation study and recognition accuracy results. Our algorithms were able to detect locations and types of over 75% of hostile activities in EC09 while producing 25% false alarms.

An adaptive deep Q-learning strategy for handwritten digit recognition.

PubMed

Qiao, Junfei; Wang, Gongming; Li, Wenjing; Chen, Min

2018-02-22

Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time. Copyright © 2018 Elsevier Ltd. All rights reserved.

Automated recognition and tracking of aerosol threat plumes with an IR camera pod

NASA Astrophysics Data System (ADS)

Fauth, Ryan; Powell, Christopher; Gruber, Thomas; Clapp, Dan

2012-06-01

Protection of fixed sites from chemical, biological, or radiological aerosol plume attacks depends on early warning so that there is time to take mitigating actions. Early warning requires continuous, autonomous, and rapid coverage of large surrounding areas; however, this must be done at an affordable cost. Once a potential threat plume is detected though, a different type of sensor (e.g., a more expensive, slower sensor) may be cued for identification purposes, but the problem is to quickly identify all of the potential threats around the fixed site of interest. To address this problem of low cost, persistent, wide area surveillance, an IR camera pod and multi-image stitching and processing algorithms have been developed for automatic recognition and tracking of aerosol plumes. A rugged, modular, static pod design, which accommodates as many as four micro-bolometer IR cameras for 45deg to 180deg of azimuth coverage, is presented. Various OpenCV1 based image-processing algorithms, including stitching of multiple adjacent FOVs, recognition of aerosol plume objects, and the tracking of aerosol plumes, are presented using process block diagrams and sample field test results, including chemical and biological simulant plumes. Methods for dealing with the background removal, brightness equalization between images, and focus quality for optimal plume tracking are also discussed.

A Fault Recognition System for Gearboxes of Wind Turbines

NASA Astrophysics Data System (ADS)

Yang, Zhiling; Huang, Haiyue; Yin, Zidong

2017-12-01

Costs of maintenance and loss of power generation caused by the faults of wind turbines gearboxes are the main components of operation costs for a wind farm. Therefore, the technology of condition monitoring and fault recognition for wind turbines gearboxes is becoming a hot topic. A condition monitoring and fault recognition system (CMFRS) is presented for CBM of wind turbines gearboxes in this paper. The vibration signals from acceleration sensors at different locations of gearbox and the data from supervisory control and data acquisition (SCADA) system are collected to CMFRS. Then the feature extraction and optimization algorithm is applied to these operational data. Furthermore, to recognize the fault of gearboxes, the GSO-LSSVR algorithm is proposed, combining the least squares support vector regression machine (LSSVR) with the Glowworm Swarm Optimization (GSO) algorithm. Finally, the results show that the fault recognition system used in this paper has a high rate for identifying three states of wind turbines’ gears; besides, the combination of date features can affect the identifying rate and the selection optimization algorithm presented in this paper can get a pretty good date feature subset for the fault recognition.

A Kalman-Filter-Based Common Algorithm Approach for Object Detection in Surgery Scene to Assist Surgeon's Situation Awareness in Robot-Assisted Laparoscopic Surgery

PubMed Central

2018-01-01

Although the use of the surgical robot is rapidly expanding for various medical treatments, there still exist safety issues and concerns about robot-assisted surgeries due to limited vision through a laparoscope, which may cause compromised situation awareness and surgical errors requiring rapid emergency conversion to open surgery. To assist surgeon's situation awareness and preventive emergency response, this study proposes situation information guidance through a vision-based common algorithm architecture for automatic detection and tracking of intraoperative hemorrhage and surgical instruments. The proposed common architecture comprises the location of the object of interest using feature texture, morphological information, and the tracking of the object based on Kalman filter for robustness with reduced error. The average recall and precision of the instrument detection in four prostate surgery videos were 96% and 86%, and the accuracy of the hemorrhage detection in two prostate surgery videos was 98%. Results demonstrate the robustness of the automatic intraoperative object detection and tracking which can be used to enhance the surgeon's preventive state recognition during robot-assisted surgery. PMID:29854366

Fast and accurate face recognition based on image compression

NASA Astrophysics Data System (ADS)

Zheng, Yufeng; Blasch, Erik

2017-05-01

Image compression is desired for many image-related applications especially for network-based applications with bandwidth and storage constraints. The face recognition community typical reports concentrate on the maximal compression rate that would not decrease the recognition accuracy. In general, the wavelet-based face recognition methods such as EBGM (elastic bunch graph matching) and FPB (face pattern byte) are of high performance but run slowly due to their high computation demands. The PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) algorithms run fast but perform poorly in face recognition. In this paper, we propose a novel face recognition method based on standard image compression algorithm, which is termed as compression-based (CPB) face recognition. First, all gallery images are compressed by the selected compression algorithm. Second, a mixed image is formed with the probe and gallery images and then compressed. Third, a composite compression ratio (CCR) is computed with three compression ratios calculated from: probe, gallery and mixed images. Finally, the CCR values are compared and the largest CCR corresponds to the matched face. The time cost of each face matching is about the time of compressing the mixed face image. We tested the proposed CPB method on the "ASUMSS face database" (visible and thermal images) from 105 subjects. The face recognition accuracy with visible images is 94.76% when using JPEG compression. On the same face dataset, the accuracy of FPB algorithm was reported as 91.43%. The JPEG-compressionbased (JPEG-CPB) face recognition is standard and fast, which may be integrated into a real-time imaging device.

Assessing the quality of activities in a smart environment.

PubMed

Cook, Diane J; Schmitter-Edgecombe, M

2009-01-01

Pervasive computing technology can provide valuable health monitoring and assistance technology to help individuals live independent lives in their own homes. As a critical part of this technology, our objective is to design software algorithms that recognize and assess the consistency of activities of daily living that individuals perform in their own homes. We have designed algorithms that automatically learn Markov models for each class of activity. These models are used to recognize activities that are performed in a smart home and to identify errors and inconsistencies in the performed activity. We validate our approach using data collected from 60 volunteers who performed a series of activities in our smart apartment testbed. The results indicate that the algorithms correctly label the activities and successfully assess the completeness and consistency of the performed task. Our results indicate that activity recognition and assessment can be automated using machine learning algorithms and smart home technology. These algorithms will be useful for automating remote health monitoring and interventions.

A Greedy Algorithm for Brain MRI's Registration.

PubMed

Chesseboeuf, Clément

2016-12-01

This document presents a non-rigid registration algorithm for the use of brain magnetic resonance (MR) images comparison. More precisely, we want to compare pre-operative and post-operative MR images in order to assess the deformation due to a surgical removal. The proposed algorithm has been studied in Chesseboeuf et al. ((Non-rigid registration of magnetic resonance imaging of brain. IEEE, 385-390. doi: 10.1109/IPTA.2015.7367172 , 2015), following ideas of Trouvé (An infinite dimensional group approach for physics based models in patterns recognition. Technical Report DMI Ecole Normale Supérieure, Cachan, 1995), in which the author introduces the algorithm within a very general framework. Here we recalled this theory from a practical point of view. The emphasis is on illustrations and description of the numerical procedure. Our version of the algorithm is associated with a particular matching criterion. Then, a section is devoted to the description of this object. In the last section we focus on the construction of a statistical method of evaluation.

Diagnostic Accuracy Comparison of Artificial Immune Algorithms for Primary Headaches.

PubMed

Çelik, Ufuk; Yurtay, Nilüfer; Koç, Emine Rabia; Tepe, Nermin; Güllüoğlu, Halil; Ertaş, Mustafa

2015-01-01

The present study evaluated the diagnostic accuracy of immune system algorithms with the aim of classifying the primary types of headache that are not related to any organic etiology. They are divided into four types: migraine, tension, cluster, and other primary headaches. After we took this main objective into consideration, three different neurologists were required to fill in the medical records of 850 patients into our web-based expert system hosted on our project web site. In the evaluation process, Artificial Immune Systems (AIS) were used as the classification algorithms. The AIS are classification algorithms that are inspired by the biological immune system mechanism that involves significant and distinct capabilities. These algorithms simulate the specialties of the immune system such as discrimination, learning, and the memorizing process in order to be used for classification, optimization, or pattern recognition. According to the results, the accuracy level of the classifier used in this study reached a success continuum ranging from 95% to 99%, except for the inconvenient one that yielded 71% accuracy.

A Palmprint Recognition Algorithm Using Phase-Only Correlation

NASA Astrophysics Data System (ADS)

Ito, Koichi; Aoki, Takafumi; Nakajima, Hiroshi; Kobayashi, Koji; Higuchi, Tatsuo

This paper presents a palmprint recognition algorithm using Phase-Only Correlation (POC). The use of phase components in 2D (two-dimensional) discrete Fourier transforms of palmprint images makes it possible to achieve highly robust image registration and matching. In the proposed algorithm, POC is used to align scaling, rotation and translation between two palmprint images, and evaluate similarity between them. Experimental evaluation using a palmprint image database clearly demonstrates efficient matching performance of the proposed algorithm.

Simulation and performance of an artificial retina for 40 MHz track reconstruction

DOE PAGES

Abba, A.; Bedeschi, F.; Citterio, M.; ...

2015-03-05

We present the results of a detailed simulation of the artificial retina pattern-recognition algorithm, designed to reconstruct events with hundreds of charged-particle tracks in pixel and silicon detectors at LHCb with LHC crossing frequency of 40 MHz. Performances of the artificial retina algorithm are assessed using the official Monte Carlo samples of the LHCb experiment. We found performances for the retina pattern-recognition algorithm comparable with the full LHCb reconstruction algorithm.

Ventral-stream-like shape representation: from pixel intensity values to trainable object-selective COSFIRE models

PubMed Central

Azzopardi, George; Petkov, Nicolai

2014-01-01

The remarkable abilities of the primate visual system have inspired the construction of computational models of some visual neurons. We propose a trainable hierarchical object recognition model, which we call S-COSFIRE (S stands for Shape and COSFIRE stands for Combination Of Shifted FIlter REsponses) and use it to localize and recognize objects of interests embedded in complex scenes. It is inspired by the visual processing in the ventral stream (V1/V2 → V4 → TEO). Recognition and localization of objects embedded in complex scenes is important for many computer vision applications. Most existing methods require prior segmentation of the objects from the background which on its turn requires recognition. An S-COSFIRE filter is automatically configured to be selective for an arrangement of contour-based features that belong to a prototype shape specified by an example. The configuration comprises selecting relevant vertex detectors and determining certain blur and shift parameters. The response is computed as the weighted geometric mean of the blurred and shifted responses of the selected vertex detectors. S-COSFIRE filters share similar properties with some neurons in inferotemporal cortex, which provided inspiration for this work. We demonstrate the effectiveness of S-COSFIRE filters in two applications: letter and keyword spotting in handwritten manuscripts and object spotting in complex scenes for the computer vision system of a domestic robot. S-COSFIRE filters are effective to recognize and localize (deformable) objects in images of complex scenes without requiring prior segmentation. They are versatile trainable shape detectors, conceptually simple and easy to implement. The presented hierarchical shape representation contributes to a better understanding of the brain and to more robust computer vision algorithms. PMID:25126068

Real and virtual explorations of the environment and interactive tracking of movable objects for the blind on the basis of tactile-acoustical maps and 3D environment models.

PubMed

Hub, Andreas; Hartter, Tim; Kombrink, Stefan; Ertl, Thomas

2008-01-01

PURPOSE.: This study describes the development of a multi-functional assistant system for the blind which combines localisation, real and virtual navigation within modelled environments and the identification and tracking of fixed and movable objects. The approximate position of buildings is determined with a global positioning sensor (GPS), then the user establishes exact position at a specific landmark, like a door. This location initialises indoor navigation, based on an inertial sensor, a step recognition algorithm and map. Tracking of movable objects is provided by another inertial sensor and a head-mounted stereo camera, combined with 3D environmental models. This study developed an algorithm based on shape and colour to identify objects and used a common face detection algorithm to inform the user of the presence and position of others. The system allows blind people to determine their position with approximately 1 metre accuracy. Virtual exploration of the environment can be accomplished by moving one's finger on a touch screen of a small portable tablet PC. The name of rooms, building features and hazards, modelled objects and their positions are presented acoustically or in Braille. Given adequate environmental models, this system offers blind people the opportunity to navigate independently and safely, even within unknown environments. Additionally, the system facilitates education and rehabilitation by providing, in several languages, object names, features and relative positions.

Use of laser range finders and range image analysis in automated assembly tasks

NASA Technical Reports Server (NTRS)

Alvertos, Nicolas; Dcunha, Ivan

1990-01-01

A proposition to study the effect of filtering processes on range images and to evaluate the performance of two different laser range mappers is made. Median filtering was utilized to remove noise from the range images. First and second order derivatives are then utilized to locate the similarities and dissimilarities between the processed and the original images. Range depth information is converted into spatial coordinates, and a set of coefficients which describe 3-D objects is generated using the algorithm developed in the second phase of this research. Range images of spheres and cylinders are used for experimental purposes. An algorithm was developed to compare the performance of two different laser range mappers based upon the range depth information of surfaces generated by each of the mappers. Furthermore, an approach based on 2-D analytic geometry is also proposed which serves as a basis for the recognition of regular 3-D geometric objects.

DCL System Research Using Advanced Approaches for Land-based or Ship-based Real-Time Recognition and Localization of Marine Mammals

DTIC Science & Technology

2012-09-30

recognition. Algorithm design and statistical analysis and feature analysis. Post -Doctoral Associate, Cornell University, Bioacoustics Research...short. The HPC-ADA was designed based on fielded systems [1-4, 6] that offer a variety of desirable attributes, specifically dynamic resource...The software package was designed to utilize parallel and distributed processing for running recognition and other advanced algorithms. DeLMA

False match elimination for face recognition based on SIFT algorithm

NASA Astrophysics Data System (ADS)

Gu, Xuyuan; Shi, Ping; Shao, Meide

2011-06-01

The SIFT (Scale Invariant Feature Transform) is a well known algorithm used to detect and describe local features in images. It is invariant to image scale, rotation and robust to the noise and illumination. In this paper, a novel method used for face recognition based on SIFT is proposed, which combines the optimization of SIFT, mutual matching and Progressive Sample Consensus (PROSAC) together and can eliminate the false matches of face recognition effectively. Experiments on ORL face database show that many false matches can be eliminated and better recognition rate is achieved.

Webly-Supervised Fine-Grained Visual Categorization via Deep Domain Adaptation.

PubMed

Xu, Zhe; Huang, Shaoli; Zhang, Ya; Tao, Dacheng

2018-05-01

Learning visual representations from web data has recently attracted attention for object recognition. Previous studies have mainly focused on overcoming label noise and data bias and have shown promising results by learning directly from web data. However, we argue that it might be better to transfer knowledge from existing human labeling resources to improve performance at nearly no additional cost. In this paper, we propose a new semi-supervised method for learning via web data. Our method has the unique design of exploiting strong supervision, i.e., in addition to standard image-level labels, our method also utilizes detailed annotations including object bounding boxes and part landmarks. By transferring as much knowledge as possible from existing strongly supervised datasets to weakly supervised web images, our method can benefit from sophisticated object recognition algorithms and overcome several typical problems found in webly-supervised learning. We consider the problem of fine-grained visual categorization, in which existing training resources are scarce, as our main research objective. Comprehensive experimentation and extensive analysis demonstrate encouraging performance of the proposed approach, which, at the same time, delivers a new pipeline for fine-grained visual categorization that is likely to be highly effective for real-world applications.

Safe trajectory estimation at a pedestrian crossing to assist visually impaired people.

PubMed

Alghamdi, Saleh; van Schyndel, Ron; Khalil, Ibrahim

2012-01-01

The aim of this paper is to present a service for blind and people with low vision to assist them to cross the street independently. The presented approach provides the user with significant information such as detection of pedestrian crossing signal from any point of view, when the pedestrian crossing signal light is green, the detection of dynamic and fixed obstacles, predictions of the movement of fellow pedestrians and information on objects which may intersect his path. Our approach is based on capturing multiple frames using a depth camera which is attached to a user's headgear. Currently a testbed system is built on a helmet and is connected to a laptop in the user's backpack. In this paper, we discussed efficiency of using Speeded-Up Robust Features (SURF) algorithm for object recognition for purposes of blind people assistance. The system predicts the movement of objects of interest to provide the user with information on the safest path to navigate and information on the surrounding area. Evaluation of this approach on real sequence video frames provides 90% of human detection and more than 80% for recognition of other related objects.

Implementation and preliminary evaluation of 'C-tone': A novel algorithm to improve lexical tone recognition in Mandarin-speaking cochlear implant users.

PubMed

Ping, Lichuan; Wang, Ningyuan; Tang, Guofang; Lu, Thomas; Yin, Li; Tu, Wenhe; Fu, Qian-Jie

2017-09-01

Because of limited spectral resolution, Mandarin-speaking cochlear implant (CI) users have difficulty perceiving fundamental frequency (F0) cues that are important to lexical tone recognition. To improve Mandarin tone recognition in CI users, we implemented and evaluated a novel real-time algorithm (C-tone) to enhance the amplitude contour, which is strongly correlated with the F0 contour. The C-tone algorithm was implemented in clinical processors and evaluated in eight users of the Nurotron NSP-60 CI system. Subjects were given 2 weeks of experience with C-tone. Recognition of Chinese tones, monosyllables, and disyllables in quiet was measured with and without the C-tone algorithm. Subjective quality ratings were also obtained for C-tone. After 2 weeks of experience with C-tone, there were small but significant improvements in recognition of lexical tones, monosyllables, and disyllables (P < 0.05 in all cases). Among lexical tones, the largest improvements were observed for Tone 3 (falling-rising) and the smallest for Tone 4 (falling). Improvements with C-tone were greater for disyllables than for monosyllables. Subjective quality ratings showed no strong preference for or against C-tone, except for perception of own voice, where C-tone was preferred. The real-time C-tone algorithm provided small but significant improvements for speech performance in quiet with no change in sound quality. Pre-processing algorithms to reduce noise and better real-time F0 extraction would improve the benefits of C-tone in complex listening environments. Chinese CI users' speech recognition in quiet can be significantly improved by modifying the amplitude contour to better resemble the F0 contour.

Neural system for heartbeats recognition using genetically integrated ensemble of classifiers.

PubMed

Osowski, Stanislaw; Siwek, Krzysztof; Siroic, Robert

2011-03-01

This paper presents the application of genetic algorithm for the integration of neural classifiers combined in the ensemble for the accurate recognition of heartbeat types on the basis of ECG registration. The idea presented in this paper is that using many classifiers arranged in the form of ensemble leads to the increased accuracy of the recognition. In such ensemble the important problem is the integration of all classifiers into one effective classification system. This paper proposes the use of genetic algorithm. It was shown that application of the genetic algorithm is very efficient and allows to reduce significantly the total error of heartbeat recognition. This was confirmed by the numerical experiments performed on the MIT BIH Arrhythmia Database. Copyright © 2011 Elsevier Ltd. All rights reserved.

Kalman filter-based tracking of moving objects using linear ultrasonic sensor array for road vehicles

NASA Astrophysics Data System (ADS)

Li, Shengbo Eben; Li, Guofa; Yu, Jiaying; Liu, Chang; Cheng, Bo; Wang, Jianqiang; Li, Keqiang

2018-01-01

Detection and tracking of objects in the side-near-field has attracted much attention for the development of advanced driver assistance systems. This paper presents a cost-effective approach to track moving objects around vehicles using linearly arrayed ultrasonic sensors. To understand the detection characteristics of a single sensor, an empirical detection model was developed considering the shapes and surface materials of various detected objects. Eight sensors were arrayed linearly to expand the detection range for further application in traffic environment recognition. Two types of tracking algorithms, including an Extended Kalman filter (EKF) and an Unscented Kalman filter (UKF), for the sensor array were designed for dynamic object tracking. The ultrasonic sensor array was designed to have two types of fire sequences: mutual firing or serial firing. The effectiveness of the designed algorithms were verified in two typical driving scenarios: passing intersections with traffic sign poles or street lights, and overtaking another vehicle. Experimental results showed that both EKF and UKF had more precise tracking position and smaller RMSE (root mean square error) than a traditional triangular positioning method. The effectiveness also encourages the application of cost-effective ultrasonic sensors in the near-field environment perception in autonomous driving systems.

Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label.

PubMed

Xu, Jin; Xu, Zhao-Xia; Lu, Ping; Guo, Rui; Yan, Hai-Xia; Xu, Wen-Jie; Wang, Yi-Qin; Xia, Chun-Ming

2016-11-01

To develop an effective Chinese Medicine (CM) diagnostic model of coronary heart disease (CHD) and to confifirm the scientifific validity of CM theoretical basis from an algorithmic viewpoint. Four types of objective diagnostic data were collected from 835 CHD patients by using a self-developed CM inquiry scale for the diagnosis of heart problems, a tongue diagnosis instrument, a ZBOX-I pulse digital collection instrument, and the sound of an attending acquisition system. These diagnostic data was analyzed and a CM diagnostic model was established using a multi-label learning algorithm (REAL). REAL was employed to establish a Xin (Heart) qi defificiency, Xin yang defificiency, Xin yin defificiency, blood stasis, and phlegm fifive-card CM diagnostic model, which had recognition rates of 80.32%, 89.77%, 84.93%, 85.37%, and 69.90%, respectively. The multi-label learning method established using four diagnostic models based on mutual information feature selection yielded good recognition results. The characteristic model parameters were selected by maximizing the mutual information for each card type. The four diagnostic methods used to obtain information in CM, i.e., observation, auscultation and olfaction, inquiry, and pulse diagnosis, can be characterized by these parameters, which is consistent with CM theory.

ViCoMo: visual context modeling for scene understanding in video surveillance

NASA Astrophysics Data System (ADS)

Creusen, Ivo M.; Javanbakhti, Solmaz; Loomans, Marijn J. H.; Hazelhoff, Lykele B.; Roubtsova, Nadejda; Zinger, Svitlana; de With, Peter H. N.

2013-10-01

The use of contextual information can significantly aid scene understanding of surveillance video. Just detecting people and tracking them does not provide sufficient information to detect situations that require operator attention. We propose a proof-of-concept system that uses several sources of contextual information to improve scene understanding in surveillance video. The focus is on two scenarios that represent common video surveillance situations, parking lot surveillance and crowd monitoring. In the first scenario, a pan-tilt-zoom (PTZ) camera tracking system is developed for parking lot surveillance. Context is provided by the traffic sign recognition system to localize regular and handicapped parking spot signs as well as license plates. The PTZ algorithm has the ability to selectively detect and track persons based on scene context. In the second scenario, a group analysis algorithm is introduced to detect groups of people. Contextual information is provided by traffic sign recognition and region labeling algorithms and exploited for behavior understanding. In both scenarios, decision engines are used to interpret and classify the output of the subsystems and if necessary raise operator alerts. We show that using context information enables the automated analysis of complicated scenarios that were previously not possible using conventional moving object classification techniques.

Stable orthogonal local discriminant embedding for linear dimensionality reduction.

PubMed

Gao, Quanxue; Ma, Jingjie; Zhang, Hailin; Gao, Xinbo; Liu, Yamin

2013-07-01

Manifold learning is widely used in machine learning and pattern recognition. However, manifold learning only considers the similarity of samples belonging to the same class and ignores the within-class variation of data, which will impair the generalization and stableness of the algorithms. For this purpose, we construct an adjacency graph to model the intraclass variation that characterizes the most important properties, such as diversity of patterns, and then incorporate the diversity into the discriminant objective function for linear dimensionality reduction. Finally, we introduce the orthogonal constraint for the basis vectors and propose an orthogonal algorithm called stable orthogonal local discriminate embedding. Experimental results on several standard image databases demonstrate the effectiveness of the proposed dimensionality reduction approach.

Real-time polarization imaging algorithm for camera-based polarization navigation sensors.

PubMed

Lu, Hao; Zhao, Kaichun; You, Zheng; Huang, Kaoli

2017-04-10

Biologically inspired polarization navigation is a promising approach due to its autonomous nature, high precision, and robustness. Many researchers have built point source-based and camera-based polarization navigation prototypes in recent years. Camera-based prototypes can benefit from their high spatial resolution but incur a heavy computation load. The pattern recognition algorithm in most polarization imaging algorithms involves several nonlinear calculations that impose a significant computation burden. In this paper, the polarization imaging and pattern recognition algorithms are optimized through reduction to several linear calculations by exploiting the orthogonality of the Stokes parameters without affecting precision according to the features of the solar meridian and the patterns of the polarized skylight. The algorithm contains a pattern recognition algorithm with a Hough transform as well as orientation measurement algorithms. The algorithm was loaded and run on a digital signal processing system to test its computational complexity. The test showed that the running time decreased to several tens of milliseconds from several thousand milliseconds. Through simulations and experiments, it was found that the algorithm can measure orientation without reducing precision. It can hence satisfy the practical demands of low computational load and high precision for use in embedded systems.

Adjustment of gripping force by optical systems

NASA Astrophysics Data System (ADS)

Jalba, C. K.; Barz, C.

2018-01-01

With increasing automation, robotics also requires ever more intelligent solutions in the handling of various tasks. In this context, many grippers must also be re-designed. For this, they must always be adapted for different requirements. The equipment of the gripper systems with sensors should help to make the gripping process more intelligent. In order to achieve such objectives, optical systems can also be used. This work analyzes how the gripping force can be adjusted by means of an optical recognition. The result of this work is the creation of a connection between optical recognition, tolerances, gripping force and real-time control. In this way, algorithms can be created, with the aid of which robot grippers as well as other gripping systems become more intelligent.

3D abnormal behavior recognition in power generation

NASA Astrophysics Data System (ADS)

Wei, Zhenhua; Li, Xuesen; Su, Jie; Lin, Jie

2011-06-01

So far most research of human behavior recognition focus on simple individual behavior, such as wave, crouch, jump and bend. This paper will focus on abnormal behavior with objects carrying in power generation. Such as using mobile communication device in main control room, taking helmet off during working and lying down in high place. Taking account of the color and shape are fixed, we adopted edge detecting by color tracking to recognize object in worker. This paper introduces a method, which using geometric character of skeleton and its angle to express sequence of three-dimensional human behavior data. Then adopting Semi-join critical step Hidden Markov Model, weighing probability of critical steps' output to reduce the computational complexity. Training model for every behavior, mean while select some skeleton frames from 3D behavior sample to form a critical step set. This set is a bridge linking 2D observation behavior with 3D human joints feature. The 3D reconstruction is not required during the 2D behavior recognition phase. In the beginning of recognition progress, finding the best match for every frame of 2D observed sample in 3D skeleton set. After that, 2D observed skeleton frames sample will be identified as a specifically 3D behavior by behavior-classifier. The effectiveness of the proposed algorithm is demonstrated with experiments in similar power generation environment.

Detecting Inspection Objects of Power Line from Cable Inspection Robot LiDAR Data

PubMed Central

Qin, Xinyan; Wu, Gongping; Fan, Fei

2018-01-01

Power lines are extending to complex environments (e.g., lakes and forests), and the distribution of power lines in a tower is becoming complicated (e.g., multi-loop and multi-bundle). Additionally, power line inspection is becoming heavier and more difficult. Advanced LiDAR technology is increasingly being used to solve these difficulties. Based on precise cable inspection robot (CIR) LiDAR data and the distinctive position and orientation system (POS) data, we propose a novel methodology to detect inspection objects surrounding power lines. The proposed method mainly includes four steps: firstly, the original point cloud is divided into single-span data as a processing unit; secondly, the optimal elevation threshold is constructed to remove ground points without the existing filtering algorithm, improving data processing efficiency and extraction accuracy; thirdly, a single power line and its surrounding data can be respectively extracted by a structured partition based on a POS data (SPPD) algorithm from “layer” to “block” according to power line distribution; finally, a partition recognition method is proposed based on the distribution characteristics of inspection objects, highlighting the feature information and improving the recognition effect. The local neighborhood statistics and the 3D region growing method are used to recognize different inspection objects surrounding power lines in a partition. Three datasets were collected by two CIR LIDAR systems in our study. The experimental results demonstrate that an average 90.6% accuracy and average 98.2% precision at the point cloud level can be achieved. The successful extraction indicates that the proposed method is feasible and promising. Our study can be used to obtain precise dimensions of fittings for modeling, as well as automatic detection and location of security risks, so as to improve the intelligence level of power line inspection. PMID:29690560

Detecting Inspection Objects of Power Line from Cable Inspection Robot LiDAR Data.

PubMed

Qin, Xinyan; Wu, Gongping; Lei, Jin; Fan, Fei; Ye, Xuhui

2018-04-22

Power lines are extending to complex environments (e.g., lakes and forests), and the distribution of power lines in a tower is becoming complicated (e.g., multi-loop and multi-bundle). Additionally, power line inspection is becoming heavier and more difficult. Advanced LiDAR technology is increasingly being used to solve these difficulties. Based on precise cable inspection robot (CIR) LiDAR data and the distinctive position and orientation system (POS) data, we propose a novel methodology to detect inspection objects surrounding power lines. The proposed method mainly includes four steps: firstly, the original point cloud is divided into single-span data as a processing unit; secondly, the optimal elevation threshold is constructed to remove ground points without the existing filtering algorithm, improving data processing efficiency and extraction accuracy; thirdly, a single power line and its surrounding data can be respectively extracted by a structured partition based on a POS data (SPPD) algorithm from "layer" to "block" according to power line distribution; finally, a partition recognition method is proposed based on the distribution characteristics of inspection objects, highlighting the feature information and improving the recognition effect. The local neighborhood statistics and the 3D region growing method are used to recognize different inspection objects surrounding power lines in a partition. Three datasets were collected by two CIR LIDAR systems in our study. The experimental results demonstrate that an average 90.6% accuracy and average 98.2% precision at the point cloud level can be achieved. The successful extraction indicates that the proposed method is feasible and promising. Our study can be used to obtain precise dimensions of fittings for modeling, as well as automatic detection and location of security risks, so as to improve the intelligence level of power line inspection.

Foliage penetration by using 4-D point cloud data

NASA Astrophysics Data System (ADS)

Méndez Rodríguez, Javier; Sánchez-Reyes, Pedro J.; Cruz-Rivera, Sol M.

2012-06-01

Real-time awareness and rapid target detection are critical for the success of military missions. New technologies capable of detecting targets concealed in forest areas are needed in order to track and identify possible threats. Currently, LAser Detection And Ranging (LADAR) systems are capable of detecting obscured targets; however, tracking capabilities are severely limited. Now, a new LADAR-derived technology is under development to generate 4-D datasets (3-D video in a point cloud format). As such, there is a new need for algorithms that are able to process data in real time. We propose an algorithm capable of removing vegetation and other objects that may obfuscate concealed targets in a real 3-D environment. The algorithm is based on wavelets and can be used as a pre-processing step in a target recognition algorithm. Applications of the algorithm in a real-time 3-D system could help make pilots aware of high risk hidden targets such as tanks and weapons, among others. We will be using a 4-D simulated point cloud data to demonstrate the capabilities of our algorithm.

Approximated mutual information training for speech recognition using myoelectric signals.

PubMed

Guo, Hua J; Chan, A D C

2006-01-01

A new training algorithm called the approximated maximum mutual information (AMMI) is proposed to improve the accuracy of myoelectric speech recognition using hidden Markov models (HMMs). Previous studies have demonstrated that automatic speech recognition can be performed using myoelectric signals from articulatory muscles of the face. Classification of facial myoelectric signals can be performed using HMMs that are trained using the maximum likelihood (ML) algorithm; however, this algorithm maximizes the likelihood of the observations in the training sequence, which is not directly associated with optimal classification accuracy. The AMMI training algorithm attempts to maximize the mutual information, thereby training the HMMs to optimize their parameters for discrimination. Our results show that AMMI training consistently reduces the error rates compared to these by the ML training, increasing the accuracy by approximately 3% on average.

a Review on State-Of Face Recognition Approaches

NASA Astrophysics Data System (ADS)

Mahmood, Zahid; Muhammad, Nazeer; Bibi, Nargis; Ali, Tauseef

Automatic Face Recognition (FR) presents a challenging task in the field of pattern recognition and despite the huge research in the past several decades; it still remains an open research problem. This is primarily due to the variability in the facial images, such as non-uniform illuminations, low resolution, occlusion, and/or variation in poses. Due to its non-intrusive nature, the FR is an attractive biometric modality and has gained a lot of attention in the biometric research community. Driven by the enormous number of potential application domains, many algorithms have been proposed for the FR. This paper presents an overview of the state-of-the-art FR algorithms, focusing their performances on publicly available databases. We highlight the conditions of the image databases with regard to the recognition rate of each approach. This is useful as a quick research overview and for practitioners as well to choose an algorithm for their specified FR application. To provide a comprehensive survey, the paper divides the FR algorithms into three categories: (1) intensity-based, (2) video-based, and (3) 3D based FR algorithms. In each category, the most commonly used algorithms and their performance is reported on standard face databases and a brief critical discussion is carried out.

Machine vision system for inspecting characteristics of hybrid rice seed

NASA Astrophysics Data System (ADS)

Cheng, Fang; Ying, Yibin

2004-03-01

Obtaining clear images advantaged of improving the classification accuracy involves many factors, light source, lens extender and background were discussed in this paper. The analysis of rice seed reflectance curves showed that the wavelength of light source for discrimination of the diseased seeds from normal rice seeds in the monochromic image recognition mode was about 815nm for jinyou402 and shanyou10. To determine optimizing conditions for acquiring digital images of rice seed using a computer vision system, an adjustable color machine vision system was developed. The machine vision system with 20mm to 25mm lens extender produce close-up images which made it easy to object recognition of characteristics in hybrid rice seeds. White background was proved to be better than black background for inspecting rice seeds infected by disease and using the algorithms based on shape. Experimental results indicated good classification for most of the characteristics with the machine vision system. The same algorithm yielded better results in optimizing condition for quality inspection of rice seed. Specifically, the image processing can correct for details such as fine fissure with the machine vision system.

Sensor fusion II: Human and machine strategies; Proceedings of the Meeting, Philadelphia, PA, Nov. 6-9, 1989

NASA Technical Reports Server (NTRS)

Schenker, Paul S. (Editor)

1990-01-01

Various papers on human and machine strategies in sensor fusion are presented. The general topics addressed include: active vision, measurement and analysis of visual motion, decision models for sensor fusion, implementation of sensor fusion algorithms, applying sensor fusion to image analysis, perceptual modules and their fusion, perceptual organization and object recognition, planning and the integration of high-level knowledge with perception, using prior knowledge and context in sensor fusion.

Evaluation of Image Segmentation and Object Recognition Algorithms for Image Parsing

DTIC Science & Technology

2013-09-01

generation of the features from the key points. OpenCV uses Euclidean distance to match the key points and has the option to use Manhattan distance...feature vector includes polarity and intensity information. Final step is matching the key points. In OpenCV , Euclidean distance or Manhattan...the code below is one way and OpenCV offers the function radiusMatch (a pair must have a distance less than a given maximum distance). OpenCV’s

An Autonomous Star Identification Algorithm Based on One-Dimensional Vector Pattern for Star Sensors

PubMed Central

Luo, Liyan; Xu, Luping; Zhang, Hua

2015-01-01

In order to enhance the robustness and accelerate the recognition speed of star identification, an autonomous star identification algorithm for star sensors is proposed based on the one-dimensional vector pattern (one_DVP). In the proposed algorithm, the space geometry information of the observed stars is used to form the one-dimensional vector pattern of the observed star. The one-dimensional vector pattern of the same observed star remains unchanged when the stellar image rotates, so the problem of star identification is simplified as the comparison of the two feature vectors. The one-dimensional vector pattern is adopted to build the feature vector of the star pattern, which makes it possible to identify the observed stars robustly. The characteristics of the feature vector and the proposed search strategy for the matching pattern make it possible to achieve the recognition result as quickly as possible. The simulation results demonstrate that the proposed algorithm can effectively accelerate the star identification. Moreover, the recognition accuracy and robustness by the proposed algorithm are better than those by the pyramid algorithm, the modified grid algorithm, and the LPT algorithm. The theoretical analysis and experimental results show that the proposed algorithm outperforms the other three star identification algorithms. PMID:26198233

An Autonomous Star Identification Algorithm Based on One-Dimensional Vector Pattern for Star Sensors.

PubMed

Luo, Liyan; Xu, Luping; Zhang, Hua

2015-07-07

In order to enhance the robustness and accelerate the recognition speed of star identification, an autonomous star identification algorithm for star sensors is proposed based on the one-dimensional vector pattern (one_DVP). In the proposed algorithm, the space geometry information of the observed stars is used to form the one-dimensional vector pattern of the observed star. The one-dimensional vector pattern of the same observed star remains unchanged when the stellar image rotates, so the problem of star identification is simplified as the comparison of the two feature vectors. The one-dimensional vector pattern is adopted to build the feature vector of the star pattern, which makes it possible to identify the observed stars robustly. The characteristics of the feature vector and the proposed search strategy for the matching pattern make it possible to achieve the recognition result as quickly as possible. The simulation results demonstrate that the proposed algorithm can effectively accelerate the star identification. Moreover, the recognition accuracy and robustness by the proposed algorithm are better than those by the pyramid algorithm, the modified grid algorithm, and the LPT algorithm. The theoretical analysis and experimental results show that the proposed algorithm outperforms the other three star identification algorithms.

Automatic image orientation detection via confidence-based integration of low-level and semantic cues.

PubMed

Luo, Jiebo; Boutell, Matthew

2005-05-01

Automatic image orientation detection for natural images is a useful, yet challenging research topic. Humans use scene context and semantic object recognition to identify the correct image orientation. However, it is difficult for a computer to perform the task in the same way because current object recognition algorithms are extremely limited in their scope and robustness. As a result, existing orientation detection methods were built upon low-level vision features such as spatial distributions of color and texture. Discrepant detection rates have been reported for these methods in the literature. We have developed a probabilistic approach to image orientation detection via confidence-based integration of low-level and semantic cues within a Bayesian framework. Our current accuracy is 90 percent for unconstrained consumer photos, impressive given the findings of a psychophysical study conducted recently. The proposed framework is an attempt to bridge the gap between computer and human vision systems and is applicable to other problems involving semantic scene content understanding.

On the Application of Pattern Recognition and AI Technique to the Cytoscreening of Vaginal Smears by Computer

NASA Astrophysics Data System (ADS)

Bow, Sing T.; Wang, Xia-Fang

1989-05-01

In this paper the concepts of pattern recognition, image processing and artificial intelligence are applied to the development of an intelligent cytoscreening system to differentiate the abnormal cytological objects from the normal ones in vaginal smears. To achieve this goal,work listed below are involved: 1. Enhancement of the microscopic images of the smears; 2. Elevation of the qualitative differentiation under the microscope by cytologists to a quantitative differentiation plateau on the epithelial cells, ciliated cells, vacuolated cells, foreign-body-giant cells, plasma cells, lymph cells, white blood cells, red blood cells, etc. These knowledges are to be inputted into our intelligent cyto-screening system to ameliorate machine differentiation; 3. Selection of a set of effective features to characterize the cytological objects onto various regions of the multiclustered by computer algorithms; and 4. Systematical summarization of the knowledge that a gynecologist has and the way he/she follows when dealing with a case.

A new selective developmental deficit: Impaired object recognition with normal face recognition.

PubMed

Germine, Laura; Cashdollar, Nathan; Düzel, Emrah; Duchaine, Bradley

2011-05-01

Studies of developmental deficits in face recognition, or developmental prosopagnosia, have shown that individuals who have not suffered brain damage can show face recognition impairments coupled with normal object recognition (Duchaine and Nakayama, 2005; Duchaine et al., 2006; Nunn et al., 2001). However, no developmental cases with the opposite dissociation - normal face recognition with impaired object recognition - have been reported. The existence of a case of non-face developmental visual agnosia would indicate that the development of normal face recognition mechanisms does not rely on the development of normal object recognition mechanisms. To see whether a developmental variant of non-face visual object agnosia exists, we conducted a series of web-based object and face recognition tests to screen for individuals showing object recognition memory impairments but not face recognition impairments. Through this screening process, we identified AW, an otherwise normal 19-year-old female, who was then tested in the lab on face and object recognition tests. AW's performance was impaired in within-class visual recognition memory across six different visual categories (guns, horses, scenes, tools, doors, and cars). In contrast, she scored normally on seven tests of face recognition, tests of memory for two other object categories (houses and glasses), and tests of recall memory for visual shapes. Testing confirmed that her impairment was not related to a general deficit in lower-level perception, object perception, basic-level recognition, or memory. AW's results provide the first neuropsychological evidence that recognition memory for non-face visual object categories can be selectively impaired in individuals without brain damage or other memory impairment. These results indicate that the development of recognition memory for faces does not depend on intact object recognition memory and provide further evidence for category-specific dissociations in visual recognition. Copyright © 2010 Elsevier Srl. All rights reserved.

An effective approach for iris recognition using phase-based image matching.

PubMed

Miyazawa, Kazuyuki; Ito, Koichi; Aoki, Takafumi; Kobayashi, Koji; Nakajima, Hiroshi

2008-10-01

This paper presents an efficient algorithm for iris recognition using phase-based image matching--an image matching technique using phase components in 2D Discrete Fourier Transforms (DFTs) of given images. Experimental evaluation using CASIA iris image databases (versions 1.0 and 2.0) and Iris Challenge Evaluation (ICE) 2005 database clearly demonstrates that the use of phase components of iris images makes possible to achieve highly accurate iris recognition with a simple matching algorithm. This paper also discusses major implementation issues of our algorithm. In order to reduce the size of iris data and to prevent the visibility of iris images, we introduce the idea of 2D Fourier Phase Code (FPC) for representing iris information. The 2D FPC is particularly useful for implementing compact iris recognition devices using state-of-the-art Digital Signal Processing (DSP) technology.

Analysis of an algorithm for distributed recognition and accountability

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

Ko, C.; Frincke, D.A.; Goan, T. Jr.

1993-08-01

Computer and network systems are available to attacks. Abandoning the existing huge infrastructure of possibly-insecure computer and network systems is impossible, and replacing them by totally secure systems may not be feasible or cost effective. A common element in many attacks is that a single user will often attempt to intrude upon multiple resources throughout a network. Detecting the attack can become significantly easier by compiling and integrating evidence of such intrusion attempts across the network rather than attempting to assess the situation from the vantage point of only a single host. To solve this problem, we suggest an approachmore » for distributed recognition and accountability (DRA), which consists of algorithms which ``process,`` at a central location, distributed and asynchronous ``reports`` generated by computers (or a subset thereof) throughout the network. Our highest-priority objectives are to observe ways by which an individual moves around in a network of computers, including changing user names to possibly hide his/her true identity, and to associate all activities of multiple instance of the same individual to the same network-wide user. We present the DRA algorithm and a sketch of its proof under an initial set of simplifying albeit realistic assumptions. Later, we relax these assumptions to accommodate pragmatic aspects such as missing or delayed ``reports,`` clock slew, tampered ``reports,`` etc. We believe that such algorithms will have widespread applications in the future, particularly in intrusion-detection system.« less

Theoretical Aspects of the Patterns Recognition Statistical Theory Used for Developing the Diagnosis Algorithms for Complicated Technical Systems

NASA Astrophysics Data System (ADS)

Obozov, A. A.; Serpik, I. N.; Mihalchenko, G. S.; Fedyaeva, G. A.

2017-01-01

In the article, the problem of application of the pattern recognition (a relatively young area of engineering cybernetics) for analysis of complicated technical systems is examined. It is shown that the application of a statistical approach for hard distinguishable situations could be the most effective. The different recognition algorithms are based on Bayes approach, which estimates posteriori probabilities of a certain event and an assumed error. Application of the statistical approach to pattern recognition is possible for solving the problem of technical diagnosis complicated systems and particularly big powered marine diesel engines.

Iris recognition based on key image feature extraction.

PubMed

Ren, X; Tian, Q; Zhang, J; Wu, S; Zeng, Y

2008-01-01

In iris recognition, feature extraction can be influenced by factors such as illumination and contrast, and thus the features extracted may be unreliable, which can cause a high rate of false results in iris pattern recognition. In order to obtain stable features, an algorithm was proposed in this paper to extract key features of a pattern from multiple images. The proposed algorithm built an iris feature template by extracting key features and performed iris identity enrolment. Simulation results showed that the selected key features have high recognition accuracy on the CASIA Iris Set, where both contrast and illumination variance exist.

Automatic speech recognition research at NASA-Ames Research Center

NASA Technical Reports Server (NTRS)

Coler, Clayton R.; Plummer, Robert P.; Huff, Edward M.; Hitchcock, Myron H.

1977-01-01

A trainable acoustic pattern recognizer manufactured by Scope Electronics is presented. The voice command system VCS encodes speech by sampling 16 bandpass filters with center frequencies in the range from 200 to 5000 Hz. Variations in speaking rate are compensated for by a compression algorithm that subdivides each utterance into eight subintervals in such a way that the amount of spectral change within each subinterval is the same. The recorded filter values within each subinterval are then reduced to a 15-bit representation, giving a 120-bit encoding for each utterance. The VCS incorporates a simple recognition algorithm that utilizes five training samples of each word in a vocabulary of up to 24 words. The recognition rate of approximately 85 percent correct for untrained speakers and 94 percent correct for trained speakers was not considered adequate for flight systems use. Therefore, the built-in recognition algorithm was disabled, and the VCS was modified to transmit 120-bit encodings to an external computer for recognition.

Mandarin Chinese Tone Identification in Cochlear Implants: Predictions from Acoustic Models

PubMed Central

Morton, Kenneth D.; Torrione, Peter A.; Throckmorton, Chandra S.; Collins, Leslie M.

2015-01-01

It has been established that current cochlear implants do not supply adequate spectral information for perception of tonal languages. Comprehension of a tonal language, such as Mandarin Chinese, requires recognition of lexical tones. New strategies of cochlear stimulation such as variable stimulation rate and current steering may provide the means of delivering more spectral information and thus may provide the auditory fine structure required for tone recognition. Several cochlear implant signal processing strategies are examined in this study, the continuous interleaved sampling (CIS) algorithm, the frequency amplitude modulation encoding (FAME) algorithm, and the multiple carrier frequency algorithm (MCFA). These strategies provide different types and amounts of spectral information. Pattern recognition techniques can be applied to data from Mandarin Chinese tone recognition tasks using acoustic models as a means of testing the abilities of these algorithms to transmit the changes in fundamental frequency indicative of the four lexical tones. The ability of processed Mandarin Chinese tones to be correctly classified may predict trends in the effectiveness of different signal processing algorithms in cochlear implants. The proposed techniques can predict trends in performance of the signal processing techniques in quiet conditions but fail to do so in noise. PMID:18706497

Sparse and redundant representations for inverse problems and recognition

NASA Astrophysics Data System (ADS)

Patel, Vishal M.

Sparse and redundant representation of data enables the description of signals as linear combinations of a few atoms from a dictionary. In this dissertation, we study applications of sparse and redundant representations in inverse problems and object recognition. Furthermore, we propose two novel imaging modalities based on the recently introduced theory of Compressed Sensing (CS). This dissertation consists of four major parts. In the first part of the dissertation, we study a new type of deconvolution algorithm that is based on estimating the image from a shearlet decomposition. Shearlets provide a multi-directional and multi-scale decomposition that has been mathematically shown to represent distributed discontinuities such as edges better than traditional wavelets. We develop a deconvolution algorithm that allows for the approximation inversion operator to be controlled on a multi-scale and multi-directional basis. Furthermore, we develop a method for the automatic determination of the threshold values for the noise shrinkage for each scale and direction without explicit knowledge of the noise variance using a generalized cross validation method. In the second part of the dissertation, we study a reconstruction method that recovers highly undersampled images assumed to have a sparse representation in a gradient domain by using partial measurement samples that are collected in the Fourier domain. Our method makes use of a robust generalized Poisson solver that greatly aids in achieving a significantly improved performance over similar proposed methods. We will demonstrate by experiments that this new technique is more flexible to work with either random or restricted sampling scenarios better than its competitors. In the third part of the dissertation, we introduce a novel Synthetic Aperture Radar (SAR) imaging modality which can provide a high resolution map of the spatial distribution of targets and terrain using a significantly reduced number of needed transmitted and/or received electromagnetic waveforms. We demonstrate that this new imaging scheme, requires no new hardware components and allows the aperture to be compressed. Also, it presents many new applications and advantages which include strong resistance to countermesasures and interception, imaging much wider swaths and reduced on-board storage requirements. The last part of the dissertation deals with object recognition based on learning dictionaries for simultaneous sparse signal approximations and feature extraction. A dictionary is learned for each object class based on given training examples which minimize the representation error with a sparseness constraint. A novel test image is then projected onto the span of the atoms in each learned dictionary. The residual vectors along with the coefficients are then used for recognition. Applications to illumination robust face recognition and automatic target recognition are presented.

3D automatic anatomy segmentation based on iterative graph-cut-ASM.

PubMed

Chen, Xinjian; Bagci, Ulas

2011-08-01

This paper studies the feasibility of developing an automatic anatomy segmentation (AAS) system in clinical radiology and demonstrates its operation on clinical 3D images. The AAS system, the authors are developing consists of two main parts: object recognition and object delineation. As for recognition, a hierarchical 3D scale-based multiobject method is used for the multiobject recognition task, which incorporates intensity weighted ball-scale (b-scale) information into the active shape model (ASM). For object delineation, an iterative graph-cut-ASM (IGCASM) algorithm is proposed, which effectively combines the rich statistical shape information embodied in ASM with the globally optimal delineation capability of the GC method. The presented IGCASM algorithm is a 3D generalization of the 2D GC-ASM method that they proposed previously in Chen et al. [Proc. SPIE, 7259, 72590C1-72590C-8 (2009)]. The proposed methods are tested on two datasets comprised of images obtained from 20 patients (10 male and 10 female) of clinical abdominal CT scans, and 11 foot magnetic resonance imaging (MRI) scans. The test is for four organs (liver, left and right kidneys, and spleen) segmentation, five foot bones (calcaneus, tibia, cuboid, talus, and navicular). The recognition and delineation accuracies were evaluated separately. The recognition accuracy was evaluated in terms of translation, rotation, and scale (size) error. The delineation accuracy was evaluated in terms of true and false positive volume fractions (TPVF, FPVF). The efficiency of the delineation method was also evaluated on an Intel Pentium IV PC with a 3.4 GHZ CPU machine. The recognition accuracies in terms of translation, rotation, and scale error over all organs are about 8 mm, 10 degrees and 0.03, and over all foot bones are about 3.5709 mm, 0.35 degrees and 0.025, respectively. The accuracy of delineation over all organs for all subjects as expressed in TPVF and FPVF is 93.01% and 0.22%, and all foot bones for all subjects are 93.75% and 0.28%, respectively. While the delineations for the four organs can be accomplished quite rapidly with average of 78 s, the delineations for the five foot bones can be accomplished with average of 70 s. The experimental results showed the feasibility and efficacy of the proposed automatic anatomy segmentation system: (a) the incorporation of shape priors into the GC framework is feasible in 3D as demonstrated previously for 2D images; (b) our results in 3D confirm the accuracy behavior observed in 2D. The hybrid strategy IGCASM seems to be more robust and accurate than ASM and GC individually; and (c) delineations within body regions and foot bones of clinical importance can be accomplished quite rapidly within 1.5 min.

CIFAR10-DVS: An Event-Stream Dataset for Object Classification

PubMed Central

Li, Hongmin; Liu, Hanchao; Ji, Xiangyang; Li, Guoqi; Shi, Luping

2017-01-01

Neuromorphic vision research requires high-quality and appropriately challenging event-stream datasets to support continuous improvement of algorithms and methods. However, creating event-stream datasets is a time-consuming task, which needs to be recorded using the neuromorphic cameras. Currently, there are limited event-stream datasets available. In this work, by utilizing the popular computer vision dataset CIFAR-10, we converted 10,000 frame-based images into 10,000 event streams using a dynamic vision sensor (DVS), providing an event-stream dataset of intermediate difficulty in 10 different classes, named as “CIFAR10-DVS.” The conversion of event-stream dataset was implemented by a repeated closed-loop smooth (RCLS) movement of frame-based images. Unlike the conversion of frame-based images by moving the camera, the image movement is more realistic in respect of its practical applications. The repeated closed-loop image movement generates rich local intensity changes in continuous time which are quantized by each pixel of the DVS camera to generate events. Furthermore, a performance benchmark in event-driven object classification is provided based on state-of-the-art classification algorithms. This work provides a large event-stream dataset and an initial benchmark for comparison, which may boost algorithm developments in even-driven pattern recognition and object classification. PMID:28611582

Aspects of image recognition in Vivid Technologies' dual-energy x-ray system for explosives detection

NASA Astrophysics Data System (ADS)

Eilbert, Richard F.; Krug, Kristoph D.

1993-04-01

The Vivid Rapid Explosives Detection Systems is a true dual energy x-ray machine employing precision x-ray data acquisition in combination with unique algorithms and massive computation capability. Data from the system's 960 detectors is digitally stored and processed by powerful supermicro-computers organized as an expandable array of parallel processors. The algorithms operate on the dual energy attenuation image data to recognize and define objects in the milieu of the baggage contents. Each object is then systematically examined for a match to a specific effective atomic number, density, and mass threshold. Material properties are determined by comparing the relative attenuations of the 75 kVp and 150 kVp beams and electronically separating the object from its local background. Other heuristic algorithms search for specific configurations and provide additional information. The machine automatically detects explosive materials and identifies bomb components in luggage with high specificity and throughput, X-ray dose is comparable to that of current airport x-ray machines. The machine is also configured to find heroin, cocaine, and US currency by selecting appropriate settings on-site. Since January 1992, production units have been operationally deployed at U.S. and European airports for improved screening of checked baggage.

CIFAR10-DVS: An Event-Stream Dataset for Object Classification.

PubMed

Li, Hongmin; Liu, Hanchao; Ji, Xiangyang; Li, Guoqi; Shi, Luping

2017-01-01

Neuromorphic vision research requires high-quality and appropriately challenging event-stream datasets to support continuous improvement of algorithms and methods. However, creating event-stream datasets is a time-consuming task, which needs to be recorded using the neuromorphic cameras. Currently, there are limited event-stream datasets available. In this work, by utilizing the popular computer vision dataset CIFAR-10, we converted 10,000 frame-based images into 10,000 event streams using a dynamic vision sensor (DVS), providing an event-stream dataset of intermediate difficulty in 10 different classes, named as "CIFAR10-DVS." The conversion of event-stream dataset was implemented by a repeated closed-loop smooth (RCLS) movement of frame-based images. Unlike the conversion of frame-based images by moving the camera, the image movement is more realistic in respect of its practical applications. The repeated closed-loop image movement generates rich local intensity changes in continuous time which are quantized by each pixel of the DVS camera to generate events. Furthermore, a performance benchmark in event-driven object classification is provided based on state-of-the-art classification algorithms. This work provides a large event-stream dataset and an initial benchmark for comparison, which may boost algorithm developments in even-driven pattern recognition and object classification.

SU-D-201-05: On the Automatic Recognition of Patient Safety Hazards in a Radiotherapy Setup Using a Novel 3D Camera System and a Deep Learning Framework

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

Santhanam, A; Min, Y; Beron, P

Purpose: Patient safety hazards such as a wrong patient/site getting treated can lead to catastrophic results. The purpose of this project is to automatically detect potential patient safety hazards during the radiotherapy setup and alert the therapist before the treatment is initiated. Methods: We employed a set of co-located and co-registered 3D cameras placed inside the treatment room. Each camera provided a point-cloud of fraxels (fragment pixels with 3D depth information). Each of the cameras were calibrated using a custom-built calibration target to provide 3D information with less than 2 mm error in the 500 mm neighborhood around the isocenter.more » To identify potential patient safety hazards, the treatment room components and the patient’s body needed to be identified and tracked in real-time. For feature recognition purposes, we used a graph-cut based feature recognition with principal component analysis (PCA) based feature-to-object correlation to segment the objects in real-time. Changes in the object’s position were tracked using the CamShift algorithm. The 3D object information was then stored for each classified object (e.g. gantry, couch). A deep learning framework was then used to analyze all the classified objects in both 2D and 3D and was then used to fine-tune a convolutional network for object recognition. The number of network layers were optimized to identify the tracked objects with >95% accuracy. Results: Our systematic analyses showed that, the system was effectively able to recognize wrong patient setups and wrong patient accessories. The combined usage of 2D camera information (color + depth) enabled a topology-preserving approach to verify patient safety hazards in an automatic manner and even in scenarios where the depth information is partially available. Conclusion: By utilizing the 3D cameras inside the treatment room and a deep learning based image classification, potential patient safety hazards can be effectively avoided.« less

A New Method of Facial Expression Recognition Based on SPE Plus SVM

NASA Astrophysics Data System (ADS)

Ying, Zilu; Huang, Mingwei; Wang, Zhen; Wang, Zhewei

A novel method of facial expression recognition (FER) is presented, which uses stochastic proximity embedding (SPE) for data dimension reduction, and support vector machine (SVM) for expression classification. The proposed algorithm is applied to Japanese Female Facial Expression (JAFFE) database for FER, better performance is obtained compared with some traditional algorithms, such as PCA and LDA etc.. The result have further proved the effectiveness of the proposed algorithm.

Objective research of auscultation signals in Traditional Chinese Medicine based on wavelet packet energy and support vector machine.

PubMed

Yan, Jianjun; Shen, Xiaojing; Wang, Yiqin; Li, Fufeng; Xia, Chunming; Guo, Rui; Chen, Chunfeng; Shen, Qingwei

2010-01-01

This study aims at utilising Wavelet Packet Transform (WPT) and Support Vector Machine (SVM) algorithm to make objective analysis and quantitative research for the auscultation in Traditional Chinese Medicine (TCM) diagnosis. First, Wavelet Packet Decomposition (WPD) at level 6 was employed to split more elaborate frequency bands of the auscultation signals. Then statistic analysis was made based on the extracted Wavelet Packet Energy (WPE) features from WPD coefficients. Furthermore, the pattern recognition was used to distinguish mixed subjects' statistical feature values of sample groups through SVM. Finally, the experimental results showed that the classification accuracies were at a high level.

Container-code recognition system based on computer vision and deep neural networks

NASA Astrophysics Data System (ADS)

Liu, Yi; Li, Tianjian; Jiang, Li; Liang, Xiaoyao

2018-04-01

Automatic container-code recognition system becomes a crucial requirement for ship transportation industry in recent years. In this paper, an automatic container-code recognition system based on computer vision and deep neural networks is proposed. The system consists of two modules, detection module and recognition module. The detection module applies both algorithms based on computer vision and neural networks, and generates a better detection result through combination to avoid the drawbacks of the two methods. The combined detection results are also collected for online training of the neural networks. The recognition module exploits both character segmentation and end-to-end recognition, and outputs the recognition result which passes the verification. When the recognition module generates false recognition, the result will be corrected and collected for online training of the end-to-end recognition sub-module. By combining several algorithms, the system is able to deal with more situations, and the online training mechanism can improve the performance of the neural networks at runtime. The proposed system is able to achieve 93% of overall recognition accuracy.

A comparison of algorithms for inference and learning in probabilistic graphical models.

PubMed

Frey, Brendan J; Jojic, Nebojsa

2005-09-01

Research into methods for reasoning under uncertainty is currently one of the most exciting areas of artificial intelligence, largely because it has recently become possible to record, store, and process large amounts of data. While impressive achievements have been made in pattern classification problems such as handwritten character recognition, face detection, speaker identification, and prediction of gene function, it is even more exciting that researchers are on the verge of introducing systems that can perform large-scale combinatorial analyses of data, decomposing the data into interacting components. For example, computational methods for automatic scene analysis are now emerging in the computer vision community. These methods decompose an input image into its constituent objects, lighting conditions, motion patterns, etc. Two of the main challenges are finding effective representations and models in specific applications and finding efficient algorithms for inference and learning in these models. In this paper, we advocate the use of graph-based probability models and their associated inference and learning algorithms. We review exact techniques and various approximate, computationally efficient techniques, including iterated conditional modes, the expectation maximization (EM) algorithm, Gibbs sampling, the mean field method, variational techniques, structured variational techniques and the sum-product algorithm ("loopy" belief propagation). We describe how each technique can be applied in a vision model of multiple, occluding objects and contrast the behaviors and performances of the techniques using a unifying cost function, free energy.

Flexible methods for segmentation evaluation: Results from CT-based luggage screening

PubMed Central

Karimi, Seemeen; Jiang, Xiaoqian; Cosman, Pamela; Martz, Harry

2017-01-01

BACKGROUND Imaging systems used in aviation security include segmentation algorithms in an automatic threat recognition pipeline. The segmentation algorithms evolve in response to emerging threats and changing performance requirements. Analysis of segmentation algorithms’ behavior, including the nature of errors and feature recovery, facilitates their development. However, evaluation methods from the literature provide limited characterization of the segmentation algorithms. OBJECTIVE To develop segmentation evaluation methods that measure systematic errors such as oversegmentation and undersegmentation, outliers, and overall errors. The methods must measure feature recovery and allow us to prioritize segments. METHODS We developed two complementary evaluation methods using statistical techniques and information theory. We also created a semi-automatic method to define ground truth from 3D images. We applied our methods to evaluate five segmentation algorithms developed for CT luggage screening. We validated our methods with synthetic problems and an observer evaluation. RESULTS Both methods selected the same best segmentation algorithm. Human evaluation confirmed the findings. The measurement of systematic errors and prioritization helped in understanding the behavior of each segmentation algorithm. CONCLUSIONS Our evaluation methods allow us to measure and explain the accuracy of segmentation algorithms. PMID:24699346

Clinical implications of word recognition differences in earphone and aided conditions

PubMed Central

McRackan, Theodore R.; Ahlstrom, Jayne B.; Clinkscales, William B.; Meyer, Ted A.; Dubno, Judy R

2017-01-01

Objective To compare word recognition scores for adults with hearing loss measured using earphones and in the sound field without and with hearing aids (HA) Study design Independent review of pre-surgical audiological data from an active middle ear implant (MEI) FDA clinical trial Setting Multicenter prospective FDA clinical trial Patients Ninety-four adult HA users Interventions/Main outcomes measured Pre-operative earphone, unaided and aided pure tone thresholds, word recognition scores, and speech intelligibility index. Results We performed an independent review of pre-surgical audiological data from a MEI FDA trial and compared unaided and aided word recognition scores with participants’ HAs fit according to the NAL-R algorithm. For 52 participants (55.3%), differences in scores between earphone and aided conditions were >10%; for 33 participants (35.1%), earphone scores were higher by 10% or more than aided scores. These participants had significantly higher pure tone thresholds at 250 Hz, 500 Hz, and 1000 Hz), higher pure tone averages, higher speech recognition thresholds, (and higher earphone speech levels (p=0.002). No significant correlation was observed between word recognition scores measured with earphones and with hearing aids (r=.14; p=0.16), whereas a moderately high positive correlation was observed between unaided and aided word recognition (r=0.68; p<0.001). Conclusion Results of the these analyses do not support the common clinical practice of using word recognition scores measured with earphones to predict aided word recognition or hearing aid benefit. Rather, these results provide evidence supporting the measurement of aided word recognition in patients who are considering hearing aids. PMID:27631832

Surface registration technique for close-range mapping applications

NASA Astrophysics Data System (ADS)

Habib, Ayman F.; Cheng, Rita W. T.

2006-08-01

Close-range mapping applications such as cultural heritage restoration, virtual reality modeling for the entertainment industry, and anatomical feature recognition for medical activities require 3D data that is usually acquired by high resolution close-range laser scanners. Since these datasets are typically captured from different viewpoints and/or at different times, accurate registration is a crucial procedure for 3D modeling of mapped objects. Several registration techniques are available that work directly with the raw laser points or with extracted features from the point cloud. Some examples include the commonly known Iterative Closest Point (ICP) algorithm and a recently proposed technique based on matching spin-images. This research focuses on developing a surface matching algorithm that is based on the Modified Iterated Hough Transform (MIHT) and ICP to register 3D data. The proposed algorithm works directly with the raw 3D laser points and does not assume point-to-point correspondence between two laser scans. The algorithm can simultaneously establish correspondence between two surfaces and estimates the transformation parameters relating them. Experiment with two partially overlapping laser scans of a small object is performed with the proposed algorithm and shows successful registration. A high quality of fit between the two scans is achieved and improvement is found when compared to the results obtained using the spin-image technique. The results demonstrate the feasibility of the proposed algorithm for registering 3D laser scanning data in close-range mapping applications to help with the generation of complete 3D models.

Membership-degree preserving discriminant analysis with applications to face recognition.

PubMed

Yang, Zhangjing; Liu, Chuancai; Huang, Pu; Qian, Jianjun

2013-01-01

In pattern recognition, feature extraction techniques have been widely employed to reduce the dimensionality of high-dimensional data. In this paper, we propose a novel feature extraction algorithm called membership-degree preserving discriminant analysis (MPDA) based on the fisher criterion and fuzzy set theory for face recognition. In the proposed algorithm, the membership degree of each sample to particular classes is firstly calculated by the fuzzy k-nearest neighbor (FKNN) algorithm to characterize the similarity between each sample and class centers, and then the membership degree is incorporated into the definition of the between-class scatter and the within-class scatter. The feature extraction criterion via maximizing the ratio of the between-class scatter to the within-class scatter is applied. Experimental results on the ORL, Yale, and FERET face databases demonstrate the effectiveness of the proposed algorithm.

The program complex for vocal recognition

NASA Astrophysics Data System (ADS)

Konev, Anton; Kostyuchenko, Evgeny; Yakimuk, Alexey

2017-01-01

This article discusses the possibility of applying the algorithm of determining the pitch frequency for the note recognition problems. Preliminary study of programs-analogues were carried out for programs with function “recognition of the music”. The software package based on the algorithm for pitch frequency calculation was implemented and tested. It was shown that the algorithm allows recognizing the notes in the vocal performance of the user. A single musical instrument, a set of musical instruments, and a human voice humming a tune can be the sound source. The input file is initially presented in the .wav format or is recorded in this format from a microphone. Processing is performed by sequentially determining the pitch frequency and conversion of its values to the note. According to test results, modification of algorithms used in the complex was planned.

Comparison of Neural Networks and Tabular Nearest Neighbor Encoding for Hyperspectral Signature Classification in Unresolved Object Detection

NASA Astrophysics Data System (ADS)

Schmalz, M.; Ritter, G.; Key, R.

Accurate and computationally efficient spectral signature classification is a crucial step in the nonimaging detection and recognition of spaceborne objects. In classical hyperspectral recognition applications using linear mixing models, signature classification accuracy depends on accurate spectral endmember discrimination [1]. If the endmembers cannot be classified correctly, then the signatures cannot be classified correctly, and object recognition from hyperspectral data will be inaccurate. In practice, the number of endmembers accurately classified often depends linearly on the number of inputs. This can lead to potentially severe classification errors in the presence of noise or densely interleaved signatures. In this paper, we present an comparison of emerging technologies for nonimaging spectral signature classfication based on a highly accurate, efficient search engine called Tabular Nearest Neighbor Encoding (TNE) [3,4] and a neural network technology called Morphological Neural Networks (MNNs) [5]. Based on prior results, TNE can optimize its classifier performance to track input nonergodicities, as well as yield measures of confidence or caution for evaluation of classification results. Unlike neural networks, TNE does not have a hidden intermediate data structure (e.g., the neural net weight matrix). Instead, TNE generates and exploits a user-accessible data structure called the agreement map (AM), which can be manipulated by Boolean logic operations to effect accurate classifier refinement algorithms. The open architecture and programmability of TNE's agreement map processing allows a TNE programmer or user to determine classification accuracy, as well as characterize in detail the signatures for which TNE did not obtain classification matches, and why such mis-matches occurred. In this study, we will compare TNE and MNN based endmember classification, using performance metrics such as probability of correct classification (Pd) and rate of false detections (Rfa). As proof of principle, we analyze classification of multiple closely spaced signatures from a NASA database of space material signatures. Additional analysis pertains to computational complexity and noise sensitivity, which are superior to Bayesian techniques based on classical neural networks. [1] Winter, M.E. "Fast autonomous spectral end-member determination in hyperspectral data," in Proceedings of the 13th International Conference On Applied Geologic Remote Sensing, Vancouver, B.C., Canada, pp. 337-44 (1999). [2] N. Keshava, "A survey of spectral unmixing algorithms," Lincoln Laboratory Journal 14:55-78 (2003). [3] Key, G., M.S. SCHMALZ, F.M. Caimi, and G.X. Ritter. "Performance analysis of tabular nearest neighbor encoding algorithm for joint compression and ATR", in Proceedings SPIE 3814:115-126 (1999). [4] Schmalz, M.S. and G. Key. "Algorithms for hyperspectral signature classification in unresolved object detection using tabular nearest neighbor encoding" in Proceedings of the 2007 AMOS Conference, Maui HI (2007). [5] Ritter, G.X., G. Urcid, and M.S. Schmalz. "Autonomous single-pass endmember approximation using lattice auto-associative memories", Neurocomputing (Elsevier), accepted (June 2008).

CNN universal machine as classificaton platform: an art-like clustering algorithm.

PubMed

Bálya, David

2003-12-01

Fast and robust classification of feature vectors is a crucial task in a number of real-time systems. A cellular neural/nonlinear network universal machine (CNN-UM) can be very efficient as a feature detector. The next step is to post-process the results for object recognition. This paper shows how a robust classification scheme based on adaptive resonance theory (ART) can be mapped to the CNN-UM. Moreover, this mapping is general enough to include different types of feed-forward neural networks. The designed analogic CNN algorithm is capable of classifying the extracted feature vectors keeping the advantages of the ART networks, such as robust, plastic and fault-tolerant behaviors. An analogic algorithm is presented for unsupervised classification with tunable sensitivity and automatic new class creation. The algorithm is extended for supervised classification. The presented binary feature vector classification is implemented on the existing standard CNN-UM chips for fast classification. The experimental evaluation shows promising performance after 100% accuracy on the training set.

A Linked List-Based Algorithm for Blob Detection on Embedded Vision-Based Sensors.

PubMed

Acevedo-Avila, Ricardo; Gonzalez-Mendoza, Miguel; Garcia-Garcia, Andres

2016-05-28

Blob detection is a common task in vision-based applications. Most existing algorithms are aimed at execution on general purpose computers; while very few can be adapted to the computing restrictions present in embedded platforms. This paper focuses on the design of an algorithm capable of real-time blob detection that minimizes system memory consumption. The proposed algorithm detects objects in one image scan; it is based on a linked-list data structure tree used to label blobs depending on their shape and node information. An example application showing the results of a blob detection co-processor has been built on a low-powered field programmable gate array hardware as a step towards developing a smart video surveillance system. The detection method is intended for general purpose application. As such, several test cases focused on character recognition are also examined. The results obtained present a fair trade-off between accuracy and memory requirements; and prove the validity of the proposed approach for real-time implementation on resource-constrained computing platforms.

Research on gait-based human identification

NASA Astrophysics Data System (ADS)

Li, Youguo

Gait recognition refers to automatic identification of individual based on his/her style of walking. This paper proposes a gait recognition method based on Continuous Hidden Markov Model with Mixture of Gaussians(G-CHMM). First, we initialize a Gaussian mix model for training image sequence with K-means algorithm, then train the HMM parameters using a Baum-Welch algorithm. These gait feature sequences can be trained and obtain a Continuous HMM for every person, therefore, the 7 key frames and the obtained HMM can represent each person's gait sequence. Finally, the recognition is achieved by Front algorithm. The experiments made on CASIA gait databases obtain comparatively high correction identification ratio and comparatively strong robustness for variety of bodily angle.

Artificial intelligence tools for pattern recognition

NASA Astrophysics Data System (ADS)

Acevedo, Elena; Acevedo, Antonio; Felipe, Federico; Avilés, Pedro

2017-06-01

In this work, we present a system for pattern recognition that combines the power of genetic algorithms for solving problems and the efficiency of the morphological associative memories. We use a set of 48 tire prints divided into 8 brands of tires. The images have dimensions of 200 x 200 pixels. We applied Hough transform to obtain lines as main features. The number of lines obtained is 449. The genetic algorithm reduces the number of features to ten suitable lines that give thus the 100% of recognition. Morphological associative memories were used as evaluation function. The selection algorithms were Tournament and Roulette wheel. For reproduction, we applied one-point, two-point and uniform crossover.

Exercise recognition for Kinect-based telerehabilitation.

PubMed

Antón, D; Goñi, A; Illarramendi, A

2015-01-01

An aging population and people's higher survival to diseases and traumas that leave physical consequences are challenging aspects in the context of an efficient health management. This is why telerehabilitation systems are being developed, to allow monitoring and support of physiotherapy sessions at home, which could reduce healthcare costs while also improving the quality of life of the users. Our goal is the development of a Kinect-based algorithm that provides a very accurate real-time monitoring of physical rehabilitation exercises and that also provides a friendly interface oriented both to users and physiotherapists. The two main constituents of our algorithm are the posture classification method and the exercises recognition method. The exercises consist of series of movements. Each movement is composed of an initial posture, a final posture and the angular trajectories of the limbs involved in the movement. The algorithm was designed and tested with datasets of real movements performed by volunteers. We also explain in the paper how we obtained the optimal values for the trade-off values for posture and trajectory recognition. Two relevant aspects of the algorithm were evaluated in our tests, classification accuracy and real-time data processing. We achieved 91.9% accuracy in posture classification and 93.75% accuracy in trajectory recognition. We also checked whether the algorithm was able to process the data in real-time. We found that our algorithm could process more than 20,000 postures per second and all the required trajectory data-series in real-time, which in practice guarantees no perceptible delays. Later on, we carried out two clinical trials with real patients that suffered shoulder disorders. We obtained an exercise monitoring accuracy of 95.16%. We present an exercise recognition algorithm that handles the data provided by Kinect efficiently. The algorithm has been validated in a real scenario where we have verified its suitability. Moreover, we have received a positive feedback from both users and the physiotherapists who took part in the tests.

SU-F-T-20: Novel Catheter Lumen Recognition Algorithm for Rapid Digitization

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

Dise, J; McDonald, D; Ashenafi, M

Purpose: Manual catheter recognition remains a time-consuming aspect of high-dose-rate brachytherapy (HDR) treatment planning. In this work, a novel catheter lumen recognition algorithm was created for accurate and rapid digitization. Methods: MatLab v8.5 was used to create the catheter recognition algorithm. Initially, the algorithm searches the patient CT dataset using an intensity based k-means filter designed to locate catheters. Once the catheters have been located, seed points are manually selected to initialize digitization of each catheter. From each seed point, the algorithm searches locally in order to automatically digitize the remaining catheter. This digitization is accomplished by finding pixels withmore » similar image curvature and divergence parameters compared to the seed pixel. Newly digitized pixels are treated as new seed positions, and hessian image analysis is used to direct the algorithm toward neighboring catheter pixels, and to make the algorithm insensitive to adjacent catheters that are unresolvable on CT, air pockets, and high Z artifacts. The algorithm was tested using 11 HDR treatment plans, including the Syed template, tandem and ovoid applicator, and multi-catheter lung brachytherapy. Digitization error was calculated by comparing manually determined catheter positions to those determined by the algorithm. Results: he digitization error was 0.23 mm ± 0.14 mm axially and 0.62 mm ± 0.13 mm longitudinally at the tip. The time of digitization, following initial seed placement was less than 1 second per catheter. The maximum total time required to digitize all tested applicators was 4 minutes (Syed template with 15 needles). Conclusion: This algorithm successfully digitizes HDR catheters for a variety of applicators with or without CT markers. The minimal axial error demonstrates the accuracy of the algorithm, and its insensitivity to image artifacts and challenging catheter positioning. Future work to automatically place initial seed positions would improve the algorithm speed.« less

Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes

PubMed Central

Sheng, Weihua; Junior, Francisco Erivaldo Fernandes; Li, Shaobo

2018-01-01

Recent research has shown that the ubiquitous use of cameras and voice monitoring equipment in a home environment can raise privacy concerns and affect human mental health. This can be a major obstacle to the deployment of smart home systems for elderly or disabled care. This study uses a social robot to detect embarrassing situations. Firstly, we designed an improved neural network structure based on the You Only Look Once (YOLO) model to obtain feature information. By focusing on reducing area redundancy and computation time, we proposed a bounding-box merging algorithm based on region proposal networks (B-RPN), to merge the areas that have similar features and determine the borders of the bounding box. Thereafter, we designed a feature extraction algorithm based on our improved YOLO and B-RPN, called F-YOLO, for our training datasets, and then proposed a real-time object detection algorithm based on F-YOLO (RODA-FY). We implemented RODA-FY and compared models on our MAT social robot. Secondly, we considered six types of situations in smart homes, and developed training and validation datasets, containing 2580 and 360 images, respectively. Meanwhile, we designed three types of experiments with four types of test datasets composed of 960 sample images. Thirdly, we analyzed how a different number of training iterations affects our prediction estimation, and then we explored the relationship between recognition accuracy and learning rates. Our results show that our proposed privacy detection system can recognize designed situations in the smart home with an acceptable recognition accuracy of 94.48%. Finally, we compared the results among RODA-FY, Inception V3, and YOLO, which indicate that our proposed RODA-FY outperforms the other comparison models in recognition accuracy. PMID:29757211

Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes.

PubMed

Yang, Guanci; Yang, Jing; Sheng, Weihua; Junior, Francisco Erivaldo Fernandes; Li, Shaobo

2018-05-12

Recent research has shown that the ubiquitous use of cameras and voice monitoring equipment in a home environment can raise privacy concerns and affect human mental health. This can be a major obstacle to the deployment of smart home systems for elderly or disabled care. This study uses a social robot to detect embarrassing situations. Firstly, we designed an improved neural network structure based on the You Only Look Once (YOLO) model to obtain feature information. By focusing on reducing area redundancy and computation time, we proposed a bounding-box merging algorithm based on region proposal networks (B-RPN), to merge the areas that have similar features and determine the borders of the bounding box. Thereafter, we designed a feature extraction algorithm based on our improved YOLO and B-RPN, called F-YOLO, for our training datasets, and then proposed a real-time object detection algorithm based on F-YOLO (RODA-FY). We implemented RODA-FY and compared models on our MAT social robot. Secondly, we considered six types of situations in smart homes, and developed training and validation datasets, containing 2580 and 360 images, respectively. Meanwhile, we designed three types of experiments with four types of test datasets composed of 960 sample images. Thirdly, we analyzed how a different number of training iterations affects our prediction estimation, and then we explored the relationship between recognition accuracy and learning rates. Our results show that our proposed privacy detection system can recognize designed situations in the smart home with an acceptable recognition accuracy of 94.48%. Finally, we compared the results among RODA-FY, Inception V3, and YOLO, which indicate that our proposed RODA-FY outperforms the other comparison models in recognition accuracy.

Facial Emotions Recognition using Gabor Transform and Facial Animation Parameters with Neural Networks

NASA Astrophysics Data System (ADS)

Harit, Aditya; Joshi, J. C., Col; Gupta, K. K.

2018-03-01

The paper proposed an automatic facial emotion recognition algorithm which comprises of two main components: feature extraction and expression recognition. The algorithm uses a Gabor filter bank on fiducial points to find the facial expression features. The resulting magnitudes of Gabor transforms, along with 14 chosen FAPs (Facial Animation Parameters), compose the feature space. There are two stages: the training phase and the recognition phase. Firstly, for the present 6 different emotions, the system classifies all training expressions in 6 different classes (one for each emotion) in the training stage. In the recognition phase, it recognizes the emotion by applying the Gabor bank to a face image, then finds the fiducial points, and then feeds it to the trained neural architecture.

Face recognition algorithm based on Gabor wavelet and locality preserving projections

NASA Astrophysics Data System (ADS)

Liu, Xiaojie; Shen, Lin; Fan, Honghui

2017-07-01

In order to solve the effects of illumination changes and differences of personal features on the face recognition rate, this paper presents a new face recognition algorithm based on Gabor wavelet and Locality Preserving Projections (LPP). The problem of the Gabor filter banks with high dimensions was solved effectively, and also the shortcoming of the LPP on the light illumination changes was overcome. Firstly, the features of global image information were achieved, which used the good spatial locality and orientation selectivity of Gabor wavelet filters. Then the dimensions were reduced by utilizing the LPP, which well-preserved the local information of the image. The experimental results shown that this algorithm can effectively extract the features relating to facial expressions, attitude and other information. Besides, it can reduce influence of the illumination changes and the differences in personal features effectively, which improves the face recognition rate to 99.2%.

A star recognition method based on the Adaptive Ant Colony algorithm for star sensors.

PubMed

Quan, Wei; Fang, Jiancheng

2010-01-01

A new star recognition method based on the Adaptive Ant Colony (AAC) algorithm has been developed to increase the star recognition speed and success rate for star sensors. This method draws circles, with the center of each one being a bright star point and the radius being a special angular distance, and uses the parallel processing ability of the AAC algorithm to calculate the angular distance of any pair of star points in the circle. The angular distance of two star points in the circle is solved as the path of the AAC algorithm, and the path optimization feature of the AAC is employed to search for the optimal (shortest) path in the circle. This optimal path is used to recognize the stellar map and enhance the recognition success rate and speed. The experimental results show that when the position error is about 50″, the identification success rate of this method is 98% while the Delaunay identification method is only 94%. The identification time of this method is up to 50 ms.

A Hierarchical Approach to Target Recognition and Tracking. Summary of Results for the Period April 1, 1989-November 30, 1989

DTIC Science & Technology

1990-02-07

performance assessment, human intervention, or operator training. Algorithms on different levels are allowed to deal with the world with different degrees...have on the decisions made by the driver are a complex combination of human factors, driving experience, mission objectives, tactics, etc., and...motion. The distinction here is that the decision making program may I 12 1 I not necessarily make its decisions based on the same factors as the human

Leader/Follower Behaviour Using the SIFT Algorithm for Object Recognition

DTIC Science & Technology

2006-06-01

opérations de convoiement plus complexes qui utiliseraient une vision artificielle basée sur la détection d’un chef. Les travaux futurs : Étant donné la...Systems: A Virtual Trailer Link Model, In Proceedings of IEEE/RSJ Conference on Intelligent Robots and Systems. [4] Hong, P., Sahli, H., Colon, E., and... Intelligent Robots and Systems. [6] Nguyen, H., Kogut, G., Barua, R., and Burmeister, A. (2004), A Segway RMP-based Robotic Transport System, In In

GPU-based real-time trinocular stereo vision

NASA Astrophysics Data System (ADS)

Yao, Yuanbin; Linton, R. J.; Padir, Taskin

2013-01-01

Most stereovision applications are binocular which uses information from a 2-camera array to perform stereo matching and compute the depth image. Trinocular stereovision with a 3-camera array has been proved to provide higher accuracy in stereo matching which could benefit applications like distance finding, object recognition, and detection. This paper presents a real-time stereovision algorithm implemented on a GPGPU (General-purpose graphics processing unit) using a trinocular stereovision camera array. Algorithm employs a winner-take-all method applied to perform fusion of disparities in different directions following various image processing techniques to obtain the depth information. The goal of the algorithm is to achieve real-time processing speed with the help of a GPGPU involving the use of Open Source Computer Vision Library (OpenCV) in C++ and NVidia CUDA GPGPU Solution. The results are compared in accuracy and speed to verify the improvement.

Exploration of available feature detection and identification systems and their performance on radiographs

NASA Astrophysics Data System (ADS)

Wantuch, Andrew C.; Vita, Joshua A.; Jimenez, Edward S.; Bray, Iliana E.

2016-10-01

Despite object detection, recognition, and identification being very active areas of computer vision research, many of the available tools to aid in these processes are designed with only photographs in mind. Although some algorithms used specifically for feature detection and identification may not take explicit advantage of the colors available in the image, they still under-perform on radiographs, which are grayscale images. We are especially interested in the robustness of these algorithms, specifically their performance on a preexisting database of X-ray radiographs in compressed JPEG form, with multiple ways of describing pixel information. We will review various aspects of the performance of available feature detection and identification systems, including MATLABs Computer Vision toolbox, VLFeat, and OpenCV on our non-ideal database. In the process, we will explore possible reasons for the algorithms' lessened ability to detect and identify features from the X-ray radiographs.

Simulated Prosthetic Vision: The Benefits of Computer-Based Object Recognition and Localization.

PubMed

Macé, Marc J-M; Guivarch, Valérian; Denis, Grégoire; Jouffrais, Christophe

2015-07-01

Clinical trials with blind patients implanted with a visual neuroprosthesis showed that even the simplest tasks were difficult to perform with the limited vision restored with current implants. Simulated prosthetic vision (SPV) is a powerful tool to investigate the putative functions of the upcoming generations of visual neuroprostheses. Recent studies based on SPV showed that several generations of implants will be required before usable vision is restored. However, none of these studies relied on advanced image processing. High-level image processing could significantly reduce the amount of information required to perform visual tasks and help restore visuomotor behaviors, even with current low-resolution implants. In this study, we simulated a prosthetic vision device based on object localization in the scene. We evaluated the usability of this device for object recognition, localization, and reaching. We showed that a very low number of electrodes (e.g., nine) are sufficient to restore visually guided reaching movements with fair timing (10 s) and high accuracy. In addition, performance, both in terms of accuracy and speed, was comparable with 9 and 100 electrodes. Extraction of high level information (object recognition and localization) from video images could drastically enhance the usability of current visual neuroprosthesis. We suggest that this method-that is, localization of targets of interest in the scene-may restore various visuomotor behaviors. This method could prove functional on current low-resolution implants. The main limitation resides in the reliability of the vision algorithms, which are improving rapidly. Copyright © 2015 International Center for Artificial Organs and Transplantation and Wiley Periodicals, Inc.

A fingerprint classification algorithm based on combination of local and global information

NASA Astrophysics Data System (ADS)

Liu, Chongjin; Fu, Xiang; Bian, Junjie; Feng, Jufu

2011-12-01

Fingerprint recognition is one of the most important technologies in biometric identification and has been wildly applied in commercial and forensic areas. Fingerprint classification, as the fundamental procedure in fingerprint recognition, can sharply decrease the quantity for fingerprint matching and improve the efficiency of fingerprint recognition. Most fingerprint classification algorithms are based on the number and position of singular points. Because the singular points detecting method only considers the local information commonly, the classification algorithms are sensitive to noise. In this paper, we propose a novel fingerprint classification algorithm combining the local and global information of fingerprint. Firstly we use local information to detect singular points and measure their quality considering orientation structure and image texture in adjacent areas. Furthermore the global orientation model is adopted to measure the reliability of singular points group. Finally the local quality and global reliability is weighted to classify fingerprint. Experiments demonstrate the accuracy and effectivity of our algorithm especially for the poor quality fingerprint images.

Face recognition using total margin-based adaptive fuzzy support vector machines.

PubMed

Liu, Yi-Hung; Chen, Yen-Ting

2007-01-01

This paper presents a new classifier called total margin-based adaptive fuzzy support vector machines (TAF-SVM) that deals with several problems that may occur in support vector machines (SVMs) when applied to the face recognition. The proposed TAF-SVM not only solves the overfitting problem resulted from the outlier with the approach of fuzzification of the penalty, but also corrects the skew of the optimal separating hyperplane due to the very imbalanced data sets by using different cost algorithm. In addition, by introducing the total margin algorithm to replace the conventional soft margin algorithm, a lower generalization error bound can be obtained. Those three functions are embodied into the traditional SVM so that the TAF-SVM is proposed and reformulated in both linear and nonlinear cases. By using two databases, the Chung Yuan Christian University (CYCU) multiview and the facial recognition technology (FERET) face databases, and using the kernel Fisher's discriminant analysis (KFDA) algorithm to extract discriminating face features, experimental results show that the proposed TAF-SVM is superior to SVM in terms of the face-recognition accuracy. The results also indicate that the proposed TAF-SVM can achieve smaller error variances than SVM over a number of tests such that better recognition stability can be obtained.

Task-oriented situation recognition

NASA Astrophysics Data System (ADS)

Bauer, Alexander; Fischer, Yvonne

2010-04-01

From the advances in computer vision methods for the detection, tracking and recognition of objects in video streams, new opportunities for video surveillance arise: In the future, automated video surveillance systems will be able to detect critical situations early enough to enable an operator to take preventive actions, instead of using video material merely for forensic investigations. However, problems such as limited computational resources, privacy regulations and a constant change in potential threads have to be addressed by a practical automated video surveillance system. In this paper, we show how these problems can be addressed using a task-oriented approach. The system architecture of the task-oriented video surveillance system NEST and an algorithm for the detection of abnormal behavior as part of the system are presented and illustrated for the surveillance of guests inside a video-monitored building.

Multispectral iris recognition based on group selection and game theory

NASA Astrophysics Data System (ADS)

Ahmad, Foysal; Roy, Kaushik

2017-05-01

A commercially available iris recognition system uses only a narrow band of the near infrared spectrum (700-900 nm) while iris images captured in the wide range of 405 nm to 1550 nm offer potential benefits to enhance recognition performance of an iris biometric system. The novelty of this research is that a group selection algorithm based on coalition game theory is explored to select the best patch subsets. In this algorithm, patches are divided into several groups based on their maximum contribution in different groups. Shapley values are used to evaluate the contribution of patches in different groups. Results show that this group selection based iris recognition

Wavelet decomposition based principal component analysis for face recognition using MATLAB

NASA Astrophysics Data System (ADS)

Sharma, Mahesh Kumar; Sharma, Shashikant; Leeprechanon, Nopbhorn; Ranjan, Aashish

2016-03-01

For the realization of face recognition systems in the static as well as in the real time frame, algorithms such as principal component analysis, independent component analysis, linear discriminate analysis, neural networks and genetic algorithms are used for decades. This paper discusses an approach which is a wavelet decomposition based principal component analysis for face recognition. Principal component analysis is chosen over other algorithms due to its relative simplicity, efficiency, and robustness features. The term face recognition stands for identifying a person from his facial gestures and having resemblance with factor analysis in some sense, i.e. extraction of the principal component of an image. Principal component analysis is subjected to some drawbacks, mainly the poor discriminatory power and the large computational load in finding eigenvectors, in particular. These drawbacks can be greatly reduced by combining both wavelet transform decomposition for feature extraction and principal component analysis for pattern representation and classification together, by analyzing the facial gestures into space and time domain, where, frequency and time are used interchangeably. From the experimental results, it is envisaged that this face recognition method has made a significant percentage improvement in recognition rate as well as having a better computational efficiency.

Bag-of-visual-phrases and hierarchical deep models for traffic sign detection and recognition in mobile laser scanning data

NASA Astrophysics Data System (ADS)

Yu, Yongtao; Li, Jonathan; Wen, Chenglu; Guan, Haiyan; Luo, Huan; Wang, Cheng

2016-03-01

This paper presents a novel algorithm for detection and recognition of traffic signs in mobile laser scanning (MLS) data for intelligent transportation-related applications. The traffic sign detection task is accomplished based on 3-D point clouds by using bag-of-visual-phrases representations; whereas the recognition task is achieved based on 2-D images by using a Gaussian-Bernoulli deep Boltzmann machine-based hierarchical classifier. To exploit high-order feature encodings of feature regions, a deep Boltzmann machine-based feature encoder is constructed. For detecting traffic signs in 3-D point clouds, the proposed algorithm achieves an average recall, precision, quality, and F-score of 0.956, 0.946, 0.907, and 0.951, respectively, on the four selected MLS datasets. For on-image traffic sign recognition, a recognition accuracy of 97.54% is achieved by using the proposed hierarchical classifier. Comparative studies with the existing traffic sign detection and recognition methods demonstrate that our algorithm obtains promising, reliable, and high performance in both detecting traffic signs in 3-D point clouds and recognizing traffic signs on 2-D images.

Improving iris recognition performance using segmentation, quality enhancement, match score fusion, and indexing.

PubMed

Vatsa, Mayank; Singh, Richa; Noore, Afzel

2008-08-01

This paper proposes algorithms for iris segmentation, quality enhancement, match score fusion, and indexing to improve both the accuracy and the speed of iris recognition. A curve evolution approach is proposed to effectively segment a nonideal iris image using the modified Mumford-Shah functional. Different enhancement algorithms are concurrently applied on the segmented iris image to produce multiple enhanced versions of the iris image. A support-vector-machine-based learning algorithm selects locally enhanced regions from each globally enhanced image and combines these good-quality regions to create a single high-quality iris image. Two distinct features are extracted from the high-quality iris image. The global textural feature is extracted using the 1-D log polar Gabor transform, and the local topological feature is extracted using Euler numbers. An intelligent fusion algorithm combines the textural and topological matching scores to further improve the iris recognition performance and reduce the false rejection rate, whereas an indexing algorithm enables fast and accurate iris identification. The verification and identification performance of the proposed algorithms is validated and compared with other algorithms using the CASIA Version 3, ICE 2005, and UBIRIS iris databases.

Cross-label Suppression: a Discriminative and Fast Dictionary Learning with Group Regularization.

PubMed

Wang, Xiudong; Gu, Yuantao

2017-05-10

This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose crosslabel suppression constraint to enlarge the difference among representations for different classes. Meanwhile, we introduce group regularization to enforce representations to preserve label properties of original samples, meaning the representations for the same class are encouraged to be similar. Upon the cross-label suppression, we don't resort to frequently-used `0-norm or `1- norm for coding, and obtain computational efficiency without losing the discriminative power for categorization. Moreover, two simple classification schemes are also developed to take full advantage of the learnt dictionary. Extensive experiments on six data sets including face recognition, object categorization, scene classification, texture recognition and sport action categorization are conducted, and the results show that the proposed approach can outperform lots of recently presented dictionary algorithms on both recognition accuracy and computational efficiency.

Medical image segmentation by combining graph cuts and oriented active appearance models.

PubMed

Chen, Xinjian; Udupa, Jayaram K; Bagci, Ulas; Zhuge, Ying; Yao, Jianhua

2012-04-01

In this paper, we propose a novel method based on a strategic combination of the active appearance model (AAM), live wire (LW), and graph cuts (GCs) for abdominal 3-D organ segmentation. The proposed method consists of three main parts: model building, object recognition, and delineation. In the model building part, we construct the AAM and train the LW cost function and GC parameters. In the recognition part, a novel algorithm is proposed for improving the conventional AAM matching method, which effectively combines the AAM and LW methods, resulting in the oriented AAM (OAAM). A multiobject strategy is utilized to help in object initialization. We employ a pseudo-3-D initialization strategy and segment the organs slice by slice via a multiobject OAAM method. For the object delineation part, a 3-D shape-constrained GC method is proposed. The object shape generated from the initialization step is integrated into the GC cost computation, and an iterative GC-OAAM method is used for object delineation. The proposed method was tested in segmenting the liver, kidneys, and spleen on a clinical CT data set and also on the MICCAI 2007 Grand Challenge liver data set. The results show the following: 1) The overall segmentation accuracy of true positive volume fraction TPVF > 94.3% and false positive volume fraction can be achieved; 2) the initialization performance can be improved by combining the AAM and LW; 3) the multiobject strategy greatly facilitates initialization; 4) compared with the traditional 3-D AAM method, the pseudo-3-D OAAM method achieves comparable performance while running 12 times faster; and 5) the performance of the proposed method is comparable to state-of-the-art liver segmentation algorithm. The executable version of the 3-D shape-constrained GC method with a user interface can be downloaded from http://xinjianchen.wordpress.com/research/.

Probabilistic Open Set Recognition

NASA Astrophysics Data System (ADS)

Jain, Lalit Prithviraj

Real-world tasks in computer vision, pattern recognition and machine learning often touch upon the open set recognition problem: multi-class recognition with incomplete knowledge of the world and many unknown inputs. An obvious way to approach such problems is to develop a recognition system that thresholds probabilities to reject unknown classes. Traditional rejection techniques are not about the unknown; they are about the uncertain boundary and rejection around that boundary. Thus traditional techniques only represent the "known unknowns". However, a proper open set recognition algorithm is needed to reduce the risk from the "unknown unknowns". This dissertation examines this concept and finds existing probabilistic multi-class recognition approaches are ineffective for true open set recognition. We hypothesize the cause is due to weak adhoc assumptions combined with closed-world assumptions made by existing calibration techniques. Intuitively, if we could accurately model just the positive data for any known class without overfitting, we could reject the large set of unknown classes even under this assumption of incomplete class knowledge. For this, we formulate the problem as one of modeling positive training data by invoking statistical extreme value theory (EVT) near the decision boundary of positive data with respect to negative data. We provide a new algorithm called the PI-SVM for estimating the unnormalized posterior probability of class inclusion. This dissertation also introduces a new open set recognition model called Compact Abating Probability (CAP), where the probability of class membership decreases in value (abates) as points move from known data toward open space. We show that CAP models improve open set recognition for multiple algorithms. Leveraging the CAP formulation, we go on to describe the novel Weibull-calibrated SVM (W-SVM) algorithm, which combines the useful properties of statistical EVT for score calibration with one-class and binary support vector machines. Building from the success of statistical EVT based recognition methods such as PI-SVM and W-SVM on the open set problem, we present a new general supervised learning algorithm for multi-class classification and multi-class open set recognition called the Extreme Value Local Basis (EVLB). The design of this algorithm is motivated by the observation that extrema from known negative class distributions are the closest negative points to any positive sample during training, and thus should be used to define the parameters of a probabilistic decision model. In the EVLB, the kernel distribution for each positive training sample is estimated via an EVT distribution fit over the distances to the separating hyperplane between positive training sample and closest negative samples, with a subset of the overall positive training data retained to form a probabilistic decision boundary. Using this subset as a frame of reference, the probability of a sample at test time decreases as it moves away from the positive class. Possessing this property, the EVLB is well-suited to open set recognition problems where samples from unknown or novel classes are encountered at test. Our experimental evaluation shows that the EVLB provides a substantial improvement in scalability compared to standard radial basis function kernel machines, as well as P I-SVM and W-SVM, with improved accuracy in many cases. We evaluate our algorithm on open set variations of the standard visual learning benchmarks, as well as with an open subset of classes from Caltech 256 and ImageNet. Our experiments show that PI-SVM, WSVM and EVLB provide significant advances over the previous state-of-the-art solutions for the same tasks.

Classification of physical activities based on body-segments coordination.

PubMed

Fradet, Laetitia; Marin, Frederic

2016-09-01

Numerous innovations based on connected objects and physical activity (PA) monitoring have been proposed. However, recognition of PAs requires robust algorithm and methodology. The current study presents an innovative approach for PA recognition. It is based on the heuristic definition of postures and the use of body-segments coordination obtained through external sensors. The first part of this study presents the methodology required to define the set of accelerations which is the most appropriate to represent the particular body-segments coordination involved in the chosen PAs (here walking, running, and cycling). For that purpose, subjects of different ages and heterogeneous physical conditions walked, ran, cycled, and performed daily activities at different paces. From the 3D motion capture, vertical and horizontal accelerations of 8 anatomical landmarks representative of the body were computed. Then, the 680 combinations from up to 3 accelerations were compared to identify the most appropriate set of acceleration to discriminate the PAs in terms of body segment coordinations. The discrimination was based on the maximal Hausdorff Distance obtained between the different set of accelerations. The vertical accelerations of both knees demonstrated the best PAs discrimination. The second step was the proof of concept, implementing the proposed algorithm to classify PAs of new group of subjects. The originality of the proposed algorithm is the possibility to use the subject's specific measures as reference data. With the proposed algorithm, 94% of the trials were correctly classified. In conclusion, our study proposed a flexible and extendable methodology. At the current stage, the algorithm has been shown to be valid for heterogeneous subjects, which suggests that it could be deployed in clinical or health-related applications regardless of the subjects' physical abilities or characteristics. Copyright © 2016 Elsevier Ltd. All rights reserved.

3-D Object Recognition from Point Cloud Data

NASA Astrophysics Data System (ADS)

Smith, W.; Walker, A. S.; Zhang, B.

2011-09-01

The market for real-time 3-D mapping includes not only traditional geospatial applications but also navigation of unmanned autonomous vehicles (UAVs). Massively parallel processes such as graphics processing unit (GPU) computing make real-time 3-D object recognition and mapping achievable. Geospatial technologies such as digital photogrammetry and GIS offer advanced capabilities to produce 2-D and 3-D static maps using UAV data. The goal is to develop real-time UAV navigation through increased automation. It is challenging for a computer to identify a 3-D object such as a car, a tree or a house, yet automatic 3-D object recognition is essential to increasing the productivity of geospatial data such as 3-D city site models. In the past three decades, researchers have used radiometric properties to identify objects in digital imagery with limited success, because these properties vary considerably from image to image. Consequently, our team has developed software that recognizes certain types of 3-D objects within 3-D point clouds. Although our software is developed for modeling, simulation and visualization, it has the potential to be valuable in robotics and UAV applications. The locations and shapes of 3-D objects such as buildings and trees are easily recognizable by a human from a brief glance at a representation of a point cloud such as terrain-shaded relief. The algorithms to extract these objects have been developed and require only the point cloud and minimal human inputs such as a set of limits on building size and a request to turn on a squaring option. The algorithms use both digital surface model (DSM) and digital elevation model (DEM), so software has also been developed to derive the latter from the former. The process continues through the following steps: identify and group 3-D object points into regions; separate buildings and houses from trees; trace region boundaries; regularize and simplify boundary polygons; construct complex roofs. Several case studies have been conducted using a variety of point densities, terrain types and building densities. The results have been encouraging. More work is required for better processing of, for example, forested areas, buildings with sides that are not at right angles or are not straight, and single trees that impinge on buildings. Further work may also be required to ensure that the buildings extracted are of fully cartographic quality. A first version will be included in production software later in 2011. In addition to the standard geospatial applications and the UAV navigation, the results have a further advantage: since LiDAR data tends to be accurately georeferenced, the building models extracted can be used to refine image metadata whenever the same buildings appear in imagery for which the GPS/IMU values are poorer than those for the LiDAR.

Recognizing Age-Separated Face Images: Humans and Machines

PubMed Central

Yadav, Daksha; Singh, Richa; Vatsa, Mayank; Noore, Afzel

2014-01-01

Humans utilize facial appearance, gender, expression, aging pattern, and other ancillary information to recognize individuals. It is interesting to observe how humans perceive facial age. Analyzing these properties can help in understanding the phenomenon of facial aging and incorporating the findings can help in designing effective algorithms. Such a study has two components - facial age estimation and age-separated face recognition. Age estimation involves predicting the age of an individual given his/her facial image. On the other hand, age-separated face recognition consists of recognizing an individual given his/her age-separated images. In this research, we investigate which facial cues are utilized by humans for estimating the age of people belonging to various age groups along with analyzing the effect of one's gender, age, and ethnicity on age estimation skills. We also analyze how various facial regions such as binocular and mouth regions influence age estimation and recognition capabilities. Finally, we propose an age-invariant face recognition algorithm that incorporates the knowledge learned from these observations. Key observations of our research are: (1) the age group of newborns and toddlers is easiest to estimate, (2) gender and ethnicity do not affect the judgment of age group estimation, (3) face as a global feature, is essential to achieve good performance in age-separated face recognition, and (4) the proposed algorithm yields improved recognition performance compared to existing algorithms and also outperforms a commercial system in the young image as probe scenario. PMID:25474200

Recognizing age-separated face images: humans and machines.

PubMed

Yadav, Daksha; Singh, Richa; Vatsa, Mayank; Noore, Afzel

2014-01-01

Humans utilize facial appearance, gender, expression, aging pattern, and other ancillary information to recognize individuals. It is interesting to observe how humans perceive facial age. Analyzing these properties can help in understanding the phenomenon of facial aging and incorporating the findings can help in designing effective algorithms. Such a study has two components--facial age estimation and age-separated face recognition. Age estimation involves predicting the age of an individual given his/her facial image. On the other hand, age-separated face recognition consists of recognizing an individual given his/her age-separated images. In this research, we investigate which facial cues are utilized by humans for estimating the age of people belonging to various age groups along with analyzing the effect of one's gender, age, and ethnicity on age estimation skills. We also analyze how various facial regions such as binocular and mouth regions influence age estimation and recognition capabilities. Finally, we propose an age-invariant face recognition algorithm that incorporates the knowledge learned from these observations. Key observations of our research are: (1) the age group of newborns and toddlers is easiest to estimate, (2) gender and ethnicity do not affect the judgment of age group estimation, (3) face as a global feature, is essential to achieve good performance in age-separated face recognition, and (4) the proposed algorithm yields improved recognition performance compared to existing algorithms and also outperforms a commercial system in the young image as probe scenario.

Autoregressive statistical pattern recognition algorithms for damage detection in civil structures

NASA Astrophysics Data System (ADS)

Yao, Ruigen; Pakzad, Shamim N.

2012-08-01

Statistical pattern recognition has recently emerged as a promising set of complementary methods to system identification for automatic structural damage assessment. Its essence is to use well-known concepts in statistics for boundary definition of different pattern classes, such as those for damaged and undamaged structures. In this paper, several statistical pattern recognition algorithms using autoregressive models, including statistical control charts and hypothesis testing, are reviewed as potentially competitive damage detection techniques. To enhance the performance of statistical methods, new feature extraction techniques using model spectra and residual autocorrelation, together with resampling-based threshold construction methods, are proposed. Subsequently, simulated acceleration data from a multi degree-of-freedom system is generated to test and compare the efficiency of the existing and proposed algorithms. Data from laboratory experiments conducted on a truss and a large-scale bridge slab model are then used to further validate the damage detection methods and demonstrate the superior performance of proposed algorithms.

Spatially Invariant Vector Quantization: A pattern matching algorithm for multiple classes of image subject matter including pathology.

PubMed

Hipp, Jason D; Cheng, Jerome Y; Toner, Mehmet; Tompkins, Ronald G; Balis, Ulysses J

2011-02-26

HISTORICALLY, EFFECTIVE CLINICAL UTILIZATION OF IMAGE ANALYSIS AND PATTERN RECOGNITION ALGORITHMS IN PATHOLOGY HAS BEEN HAMPERED BY TWO CRITICAL LIMITATIONS: 1) the availability of digital whole slide imagery data sets and 2) a relative domain knowledge deficit in terms of application of such algorithms, on the part of practicing pathologists. With the advent of the recent and rapid adoption of whole slide imaging solutions, the former limitation has been largely resolved. However, with the expectation that it is unlikely for the general cohort of contemporary pathologists to gain advanced image analysis skills in the short term, the latter problem remains, thus underscoring the need for a class of algorithm that has the concurrent properties of image domain (or organ system) independence and extreme ease of use, without the need for specialized training or expertise. In this report, we present a novel, general case pattern recognition algorithm, Spatially Invariant Vector Quantization (SIVQ), that overcomes the aforementioned knowledge deficit. Fundamentally based on conventional Vector Quantization (VQ) pattern recognition approaches, SIVQ gains its superior performance and essentially zero-training workflow model from its use of ring vectors, which exhibit continuous symmetry, as opposed to square or rectangular vectors, which do not. By use of the stochastic matching properties inherent in continuous symmetry, a single ring vector can exhibit as much as a millionfold improvement in matching possibilities, as opposed to conventional VQ vectors. SIVQ was utilized to demonstrate rapid and highly precise pattern recognition capability in a broad range of gross and microscopic use-case settings. With the performance of SIVQ observed thus far, we find evidence that indeed there exist classes of image analysis/pattern recognition algorithms suitable for deployment in settings where pathologists alone can effectively incorporate their use into clinical workflow, as a turnkey solution. We anticipate that SIVQ, and other related class-independent pattern recognition algorithms, will become part of the overall armamentarium of digital image analysis approaches that are immediately available to practicing pathologists, without the need for the immediate availability of an image analysis expert.

Improving Efficiency of Passive RFID Tag Anti-Collision Protocol Using Dynamic Frame Adjustment and Optimal Splitting.

PubMed

Memon, Muhammad Qasim; He, Jingsha; Yasir, Mirza Ammar; Memon, Aasma

2018-04-12

Radio frequency identification is a wireless communication technology, which enables data gathering and identifies recognition from any tagged object. The number of collisions produced during wireless communication would lead to a variety of problems including unwanted number of iterations and reader-induced idle slots, computational complexity in terms of estimation as well as recognition of the number of tags. In this work, dynamic frame adjustment and optimal splitting are employed together in the proposed algorithm. In the dynamic frame adjustment method, the length of frames is based on the quantity of tags to yield optimal efficiency. The optimal splitting method is conceived with smaller duration of idle slots using an optimal value for splitting level M o p t , where (M > 2), to vary slot sizes to get the minimal identification time for the idle slots. The application of the proposed algorithm offers the advantages of not going for the cumbersome estimation of the quantity of tags incurred and the size (number) of tags has no effect on its performance efficiency. Our experiment results show that using the proposed algorithm, the efficiency curve remains constant as the number of tags varies from 50 to 450, resulting in an overall theoretical gain in the efficiency of 0.032 compared to system efficiency of 0.441 and thus outperforming both dynamic binary tree slotted ALOHA (DBTSA) and binary splitting protocols.

Statistical detection of geographic clusters of resistant Escherichia coli in a regional network with WHONET and SaTScan

PubMed Central

Park, Rachel; O'Brien, Thomas F.; Huang, Susan S.; Baker, Meghan A.; Yokoe, Deborah S.; Kulldorff, Martin; Barrett, Craig; Swift, Jamie; Stelling, John

2016-01-01

Objectives While antimicrobial resistance threatens the prevention, treatment, and control of infectious diseases, systematic analysis of routine microbiology laboratory test results worldwide can alert new threats and promote timely response. This study explores statistical algorithms for recognizing geographic clustering of multi-resistant microbes within a healthcare network and monitoring the dissemination of new strains over time. Methods Escherichia coli antimicrobial susceptibility data from a three-year period stored in WHONET were analyzed across ten facilities in a healthcare network utilizing SaTScan's spatial multinomial model with two models for defining geographic proximity. We explored geographic clustering of multi-resistance phenotypes within the network and changes in clustering over time. Results Geographic clustering identified from both latitude/longitude and non-parametric facility groupings geographic models were similar, while the latter was offers greater flexibility and generalizability. Iterative application of the clustering algorithms suggested the possible recognition of the initial appearance of invasive E. coli ST131 in the clinical database of a single hospital and subsequent dissemination to others. Conclusion Systematic analysis of routine antimicrobial resistance susceptibility test results supports the recognition of geographic clustering of microbial phenotypic subpopulations with WHONET and SaTScan, and iterative application of these algorithms can detect the initial appearance in and dissemination across a region prompting early investigation, response, and containment measures. PMID:27530311

Improved Object Detection Using a Robotic Sensing Antenna with Vibration Damping Control

PubMed Central

Feliu-Batlle, Vicente; Feliu-Talegon, Daniel; Castillo-Berrio, Claudia Fernanda

2017-01-01

Some insects or mammals use antennae or whiskers to detect by the sense of touch obstacles or recognize objects in environments in which other senses like vision cannot work. Artificial flexible antennae can be used in robotics to mimic this sense of touch in these recognition tasks. We have designed and built a two-degree of freedom (2DOF) flexible antenna sensor device to perform robot navigation tasks. This device is composed of a flexible beam, two servomotors that drive the beam and a load cell sensor that detects the contact of the beam with an object. It is found that the efficiency of such a device strongly depends on the speed and accuracy achieved by the antenna positioning system. These issues are severely impaired by the vibrations that appear in the antenna during its movement. However, these antennae are usually moved without taking care of these undesired vibrations. This article proposes a new closed-loop control schema that cancels vibrations and improves the free movements of the antenna. Moreover, algorithms to estimate the 3D beam position and the instant and point of contact with an object are proposed. Experiments are reported that illustrate the efficiency of these proposed algorithms and the improvements achieved in object detection tasks using a control system that cancels beam vibrations. PMID:28406449

Improved Object Detection Using a Robotic Sensing Antenna with Vibration Damping Control.

PubMed

Feliu-Batlle, Vicente; Feliu-Talegon, Daniel; Castillo-Berrio, Claudia Fernanda

2017-04-13

Some insects or mammals use antennae or whiskers to detect by the sense of touch obstacles or recognize objects in environments in which other senses like vision cannot work. Artificial flexible antennae can be used in robotics to mimic this sense of touch in these recognition tasks. We have designed and built a two-degree of freedom (2DOF) flexible antenna sensor device to perform robot navigation tasks. This device is composed of a flexible beam, two servomotors that drive the beam and a load cell sensor that detects the contact of the beam with an object. It is found that the efficiency of such a device strongly depends on the speed and accuracy achieved by the antenna positioning system. These issues are severely impaired by the vibrations that appear in the antenna during its movement. However, these antennae are usually moved without taking care of these undesired vibrations. This article proposes a new closed-loop control schema that cancels vibrations and improves the free movements of the antenna. Moreover, algorithms to estimate the 3D beam position and the instant and point of contact with an object are proposed. Experiments are reported that illustrate the efficiency of these proposed algorithms and the improvements achieved in object detection tasks using a control system that cancels beam vibrations.

Aided target recognition processing of MUDSS sonar data

NASA Astrophysics Data System (ADS)

Lau, Brian; Chao, Tien-Hsin

1998-09-01

The Mobile Underwater Debris Survey System (MUDSS) is a collaborative effort by the Navy and the Jet Propulsion Lab to demonstrate multi-sensor, real-time, survey of underwater sites for ordnance and explosive waste (OEW). We describe the sonar processing algorithm, a novel target recognition algorithm incorporating wavelets, morphological image processing, expansion by Hermite polynomials, and neural networks. This algorithm has found all planted targets in MUDSS tests and has achieved spectacular success upon another Coastal Systems Station (CSS) sonar image database.

Classifier dependent feature preprocessing methods

NASA Astrophysics Data System (ADS)

Rodriguez, Benjamin M., II; Peterson, Gilbert L.

2008-04-01

In mobile applications, computational complexity is an issue that limits sophisticated algorithms from being implemented on these devices. This paper provides an initial solution to applying pattern recognition systems on mobile devices by combining existing preprocessing algorithms for recognition. In pattern recognition systems, it is essential to properly apply feature preprocessing tools prior to training classification models in an attempt to reduce computational complexity and improve the overall classification accuracy. The feature preprocessing tools extended for the mobile environment are feature ranking, feature extraction, data preparation and outlier removal. Most desktop systems today are capable of processing a majority of the available classification algorithms without concern of processing while the same is not true on mobile platforms. As an application of pattern recognition for mobile devices, the recognition system targets the problem of steganalysis, determining if an image contains hidden information. The measure of performance shows that feature preprocessing increases the overall steganalysis classification accuracy by an average of 22%. The methods in this paper are tested on a workstation and a Nokia 6620 (Symbian operating system) camera phone with similar results.

Recognition of plant parts with problem-specific algorithms

NASA Astrophysics Data System (ADS)

Schwanke, Joerg; Brendel, Thorsten; Jensch, Peter F.; Megnet, Roland

1994-06-01

Automatic micropropagation is necessary to produce cost-effective high amounts of biomass. Juvenile plants are dissected in clean- room environment on particular points on the stem or the leaves. A vision-system detects possible cutting points and controls a specialized robot. This contribution is directed to the pattern- recognition algorithms to detect structural parts of the plant.

Enhanced facial texture illumination normalization for face recognition.

PubMed

Luo, Yong; Guan, Ye-Peng

2015-08-01

An uncontrolled lighting condition is one of the most critical challenges for practical face recognition applications. An enhanced facial texture illumination normalization method is put forward to resolve this challenge. An adaptive relighting algorithm is developed to improve the brightness uniformity of face images. Facial texture is extracted by using an illumination estimation difference algorithm. An anisotropic histogram-stretching algorithm is proposed to minimize the intraclass distance of facial skin and maximize the dynamic range of facial texture distribution. Compared with the existing methods, the proposed method can more effectively eliminate the redundant information of facial skin and illumination. Extensive experiments show that the proposed method has superior performance in normalizing illumination variation and enhancing facial texture features for illumination-insensitive face recognition.

Standard object recognition memory and "what" and "where" components: Improvement by post-training epinephrine in highly habituated rats.

PubMed

Jurado-Berbel, Patricia; Costa-Miserachs, David; Torras-Garcia, Meritxell; Coll-Andreu, Margalida; Portell-Cortés, Isabel

2010-02-11

The present work examined whether post-training systemic epinephrine (EPI) is able to modulate short-term (3h) and long-term (24 h and 48 h) memory of standard object recognition, as well as long-term (24 h) memory of separate "what" (object identity) and "where" (object location) components of object recognition. Although object recognition training is associated to low arousal levels, all the animals received habituation to the training box in order to further reduce emotional arousal. Post-training EPI improved long-term (24 h and 48 h), but not short-term (3 h), memory in the standard object recognition task, as well as 24 h memory for both object identity and object location. These data indicate that post-training epinephrine: (1) facilitates long-term memory for standard object recognition; (2) exerts separate facilitatory effects on "what" (object identity) and "where" (object location) components of object recognition; and (3) is capable of improving memory for a low arousing task even in highly habituated rats.

Computer Recognition of Facial Profiles

DTIC Science & Technology

1974-08-01

facial recognition 20. ABSTRACT (Continue on reverse side It necessary and Identify by block number) A system for the recognition of human faces from...21 2.6 Classification Algorithms ........... ... 32 III FACIAL RECOGNITION AND AUTOMATIC TRAINING . . . 37 3.1 Facial Profile Recognition...provide a fair test of the classification system. The work of Goldstein, Harmon, and Lesk [81 indicates, however, that for facial recognition , a ten class

Experience moderates overlap between object and face recognition, suggesting a common ability

PubMed Central

Gauthier, Isabel; McGugin, Rankin W.; Richler, Jennifer J.; Herzmann, Grit; Speegle, Magen; Van Gulick, Ana E.

2014-01-01

Some research finds that face recognition is largely independent from the recognition of other objects; a specialized and innate ability to recognize faces could therefore have little or nothing to do with our ability to recognize objects. We propose a new framework in which recognition performance for any category is the product of domain-general ability and category-specific experience. In Experiment 1, we show that the overlap between face and object recognition depends on experience with objects. In 256 subjects we measured face recognition, object recognition for eight categories, and self-reported experience with these categories. Experience predicted neither face recognition nor object recognition but moderated their relationship: Face recognition performance is increasingly similar to object recognition performance with increasing object experience. If a subject has a lot of experience with objects and is found to perform poorly, they also prove to have a low ability with faces. In a follow-up survey, we explored the dimensions of experience with objects that may have contributed to self-reported experience in Experiment 1. Different dimensions of experience appear to be more salient for different categories, with general self-reports of expertise reflecting judgments of verbal knowledge about a category more than judgments of visual performance. The complexity of experience and current limitations in its measurement support the importance of aggregating across multiple categories. Our findings imply that both face and object recognition are supported by a common, domain-general ability expressed through experience with a category and best measured when accounting for experience. PMID:24993021

Experience moderates overlap between object and face recognition, suggesting a common ability.

PubMed

Gauthier, Isabel; McGugin, Rankin W; Richler, Jennifer J; Herzmann, Grit; Speegle, Magen; Van Gulick, Ana E

2014-07-03

Some research finds that face recognition is largely independent from the recognition of other objects; a specialized and innate ability to recognize faces could therefore have little or nothing to do with our ability to recognize objects. We propose a new framework in which recognition performance for any category is the product of domain-general ability and category-specific experience. In Experiment 1, we show that the overlap between face and object recognition depends on experience with objects. In 256 subjects we measured face recognition, object recognition for eight categories, and self-reported experience with these categories. Experience predicted neither face recognition nor object recognition but moderated their relationship: Face recognition performance is increasingly similar to object recognition performance with increasing object experience. If a subject has a lot of experience with objects and is found to perform poorly, they also prove to have a low ability with faces. In a follow-up survey, we explored the dimensions of experience with objects that may have contributed to self-reported experience in Experiment 1. Different dimensions of experience appear to be more salient for different categories, with general self-reports of expertise reflecting judgments of verbal knowledge about a category more than judgments of visual performance. The complexity of experience and current limitations in its measurement support the importance of aggregating across multiple categories. Our findings imply that both face and object recognition are supported by a common, domain-general ability expressed through experience with a category and best measured when accounting for experience. © 2014 ARVO.

Research on Palmprint Identification Method Based on Quantum Algorithms

PubMed Central

Zhang, Zhanzhan

2014-01-01

Quantum image recognition is a technology by using quantum algorithm to process the image information. It can obtain better effect than classical algorithm. In this paper, four different quantum algorithms are used in the three stages of palmprint recognition. First, quantum adaptive median filtering algorithm is presented in palmprint filtering processing. Quantum filtering algorithm can get a better filtering result than classical algorithm through the comparison. Next, quantum Fourier transform (QFT) is used to extract pattern features by only one operation due to quantum parallelism. The proposed algorithm exhibits an exponential speed-up compared with discrete Fourier transform in the feature extraction. Finally, quantum set operations and Grover algorithm are used in palmprint matching. According to the experimental results, quantum algorithm only needs to apply square of N operations to find out the target palmprint, but the traditional method needs N times of calculation. At the same time, the matching accuracy of quantum algorithm is almost 100%. PMID:25105165

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.

Improving Pattern Recognition and Neural Network Algorithms with Applications to Solar Panel Energy Optimization

NASA Astrophysics Data System (ADS)

Zamora Ramos, Ernesto

Artificial Intelligence is a big part of automation and with today's technological advances, artificial intelligence has taken great strides towards positioning itself as the technology of the future to control, enhance and perfect automation. Computer vision includes pattern recognition and classification and machine learning. Computer vision is at the core of decision making and it is a vast and fruitful branch of artificial intelligence. In this work, we expose novel algorithms and techniques built upon existing technologies to improve pattern recognition and neural network training, initially motivated by a multidisciplinary effort to build a robot that helps maintain and optimize solar panel energy production. Our contributions detail an improved non-linear pre-processing technique to enhance poorly illuminated images based on modifications to the standard histogram equalization for an image. While the original motivation was to improve nocturnal navigation, the results have applications in surveillance, search and rescue, medical imaging enhancing, and many others. We created a vision system for precise camera distance positioning motivated to correctly locate the robot for capture of solar panel images for classification. The classification algorithm marks solar panels as clean or dirty for later processing. Our algorithm extends past image classification and, based on historical and experimental data, it identifies the optimal moment in which to perform maintenance on marked solar panels as to minimize the energy and profit loss. In order to improve upon the classification algorithm, we delved into feedforward neural networks because of their recent advancements, proven universal approximation and classification capabilities, and excellent recognition rates. We explore state-of-the-art neural network training techniques offering pointers and insights, culminating on the implementation of a complete library with support for modern deep learning architectures, multilayer percepterons and convolutional neural networks. Our research with neural networks has encountered a great deal of difficulties regarding hyperparameter estimation for good training convergence rate and accuracy. Most hyperparameters, including architecture, learning rate, regularization, trainable parameters (or weights) initialization, and so on, are chosen via a trial and error process with some educated guesses. However, we developed the first quantitative method to compare weight initialization strategies, a critical hyperparameter choice during training, to estimate among a group of candidate strategies which would make the network converge to the highest classification accuracy faster with high probability. Our method provides a quick, objective measure to compare initialization strategies to select the best possible among them beforehand without having to complete multiple training sessions for each candidate strategy to compare final results.

Evolutionary Design of Convolutional Neural Networks for Human Activity Recognition in Sensor-Rich Environments.

PubMed

Baldominos, Alejandro; Saez, Yago; Isasi, Pedro

2018-04-23

Human activity recognition is a challenging problem for context-aware systems and applications. It is gaining interest due to the ubiquity of different sensor sources, wearable smart objects, ambient sensors, etc. This task is usually approached as a supervised machine learning problem, where a label is to be predicted given some input data, such as the signals retrieved from different sensors. For tackling the human activity recognition problem in sensor network environments, in this paper we propose the use of deep learning (convolutional neural networks) to perform activity recognition using the publicly available OPPORTUNITY dataset. Instead of manually choosing a suitable topology, we will let an evolutionary algorithm design the optimal topology in order to maximize the classification F1 score. After that, we will also explore the performance of committees of the models resulting from the evolutionary process. Results analysis indicates that the proposed model was able to perform activity recognition within a heterogeneous sensor network environment, achieving very high accuracies when tested with new sensor data. Based on all conducted experiments, the proposed neuroevolutionary system has proved to be able to systematically find a classification model which is capable of outperforming previous results reported in the state-of-the-art, showing that this approach is useful and improves upon previously manually-designed architectures.

Evolutionary Design of Convolutional Neural Networks for Human Activity Recognition in Sensor-Rich Environments

PubMed Central

2018-01-01

Human activity recognition is a challenging problem for context-aware systems and applications. It is gaining interest due to the ubiquity of different sensor sources, wearable smart objects, ambient sensors, etc. This task is usually approached as a supervised machine learning problem, where a label is to be predicted given some input data, such as the signals retrieved from different sensors. For tackling the human activity recognition problem in sensor network environments, in this paper we propose the use of deep learning (convolutional neural networks) to perform activity recognition using the publicly available OPPORTUNITY dataset. Instead of manually choosing a suitable topology, we will let an evolutionary algorithm design the optimal topology in order to maximize the classification F1 score. After that, we will also explore the performance of committees of the models resulting from the evolutionary process. Results analysis indicates that the proposed model was able to perform activity recognition within a heterogeneous sensor network environment, achieving very high accuracies when tested with new sensor data. Based on all conducted experiments, the proposed neuroevolutionary system has proved to be able to systematically find a classification model which is capable of outperforming previous results reported in the state-of-the-art, showing that this approach is useful and improves upon previously manually-designed architectures. PMID:29690587

Face Recognition Using Local Quantized Patterns and Gabor Filters

NASA Astrophysics Data System (ADS)

Khryashchev, V.; Priorov, A.; Stepanova, O.; Nikitin, A.

2015-05-01

The problem of face recognition in a natural or artificial environment has received a great deal of researchers' attention over the last few years. A lot of methods for accurate face recognition have been proposed. Nevertheless, these methods often fail to accurately recognize the person in difficult scenarios, e.g. low resolution, low contrast, pose variations, etc. We therefore propose an approach for accurate and robust face recognition by using local quantized patterns and Gabor filters. The estimation of the eye centers is used as a preprocessing stage. The evaluation of our algorithm on different samples from a standardized FERET database shows that our method is invariant to the general variations of lighting, expression, occlusion and aging. The proposed approach allows about 20% correct recognition accuracy increase compared with the known face recognition algorithms from the OpenCV library. The additional use of Gabor filters can significantly improve the robustness to changes in lighting conditions.

A Lightweight Hierarchical Activity Recognition Framework Using Smartphone Sensors

PubMed Central

Han, Manhyung; Bang, Jae Hun; Nugent, Chris; McClean, Sally; Lee, Sungyoung

2014-01-01

Activity recognition for the purposes of recognizing a user's intentions using multimodal sensors is becoming a widely researched topic largely based on the prevalence of the smartphone. Previous studies have reported the difficulty in recognizing life-logs by only using a smartphone due to the challenges with activity modeling and real-time recognition. In addition, recognizing life-logs is difficult due to the absence of an established framework which enables the use of different sources of sensor data. In this paper, we propose a smartphone-based Hierarchical Activity Recognition Framework which extends the Naïve Bayes approach for the processing of activity modeling and real-time activity recognition. The proposed algorithm demonstrates higher accuracy than the Naïve Bayes approach and also enables the recognition of a user's activities within a mobile environment. The proposed algorithm has the ability to classify fifteen activities with an average classification accuracy of 92.96%. PMID:25184486

Generalization between canonical and non-canonical views in object recognition

PubMed Central

Ghose, Tandra; Liu, Zili

2013-01-01

Viewpoint generalization in object recognition is the process that allows recognition of a given 3D object from many different viewpoints despite variations in its 2D projections. We used the canonical view effects as a foundation to empirically test the validity of a major theory in object recognition, the view-approximation model (Poggio & Edelman, 1990). This model predicts that generalization should be better when an object is first seen from a non-canonical view and then a canonical view than when seen in the reversed order. We also manipulated object similarity to study the degree to which this view generalization was constrained by shape details and task instructions (object vs. image recognition). Old-new recognition performance for basic and subordinate level objects was measured in separate blocks. We found that for object recognition, view generalization between canonical and non-canonical views was comparable for basic level objects. For subordinate level objects, recognition performance was more accurate from non-canonical to canonical views than the other way around. When the task was changed from object recognition to image recognition, the pattern of the results reversed. Interestingly, participants responded “old” to “new” images of “old” objects with a substantially higher rate than to “new” objects, despite instructions to the contrary, thereby indicating involuntary view generalization. Our empirical findings are incompatible with the prediction of the view-approximation theory, and argue against the hypothesis that views are stored independently. PMID:23283692

Approach to recognition of flexible form for credit card expiration date recognition as example

NASA Astrophysics Data System (ADS)

Sheshkus, Alexander; Nikolaev, Dmitry P.; Ingacheva, Anastasia; Skoryukina, Natalya

2015-12-01

In this paper we consider a task of finding information fields within document with flexible form for credit card expiration date field as example. We discuss main difficulties and suggest possible solutions. In our case this task is to be solved on mobile devices therefore computational complexity has to be as low as possible. In this paper we provide results of the analysis of suggested algorithm. Error distribution of the recognition system shows that suggested algorithm solves the task with required accuracy.

Comparison of crisp and fuzzy character networks in handwritten word recognition

NASA Technical Reports Server (NTRS)

Gader, Paul; Mohamed, Magdi; Chiang, Jung-Hsien

1992-01-01

Experiments involving handwritten word recognition on words taken from images of handwritten address blocks from the United States Postal Service mailstream are described. The word recognition algorithm relies on the use of neural networks at the character level. The neural networks are trained using crisp and fuzzy desired outputs. The fuzzy outputs were defined using a fuzzy k-nearest neighbor algorithm. The crisp networks slightly outperformed the fuzzy networks at the character level but the fuzzy networks outperformed the crisp networks at the word level.

[Galaxy/quasar classification based on nearest neighbor method].

PubMed

Li, Xiang-Ru; Lu, Yu; Zhou, Jian-Ming; Wang, Yong-Jun

2011-09-01

With the wide application of high-quality CCD in celestial spectrum imagery and the implementation of many large sky survey programs (e. g., Sloan Digital Sky Survey (SDSS), Two-degree-Field Galaxy Redshift Survey (2dF), Spectroscopic Survey Telescope (SST), Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) program and Large Synoptic Survey Telescope (LSST) program, etc.), celestial observational data are coming into the world like torrential rain. Therefore, to utilize them effectively and fully, research on automated processing methods for celestial data is imperative. In the present work, we investigated how to recognizing galaxies and quasars from spectra based on nearest neighbor method. Galaxies and quasars are extragalactic objects, they are far away from earth, and their spectra are usually contaminated by various noise. Therefore, it is a typical problem to recognize these two types of spectra in automatic spectra classification. Furthermore, the utilized method, nearest neighbor, is one of the most typical, classic, mature algorithms in pattern recognition and data mining, and often is used as a benchmark in developing novel algorithm. For applicability in practice, it is shown that the recognition ratio of nearest neighbor method (NN) is comparable to the best results reported in the literature based on more complicated methods, and the superiority of NN is that this method does not need to be trained, which is useful in incremental learning and parallel computation in mass spectral data processing. In conclusion, the results in this work are helpful for studying galaxies and quasars spectra classification.

Fusion of Visible and Thermal Descriptors Using Genetic Algorithms for Face Recognition Systems.

PubMed

Hermosilla, Gabriel; Gallardo, Francisco; Farias, Gonzalo; San Martin, Cesar

2015-07-23

The aim of this article is to present a new face recognition system based on the fusion of visible and thermal features obtained from the most current local matching descriptors by maximizing face recognition rates through the use of genetic algorithms. The article considers a comparison of the performance of the proposed fusion methodology against five current face recognition methods and classic fusion techniques used commonly in the literature. These were selected by considering their performance in face recognition. The five local matching methods and the proposed fusion methodology are evaluated using the standard visible/thermal database, the Equinox database, along with a new database, the PUCV-VTF, designed for visible-thermal studies in face recognition and described for the first time in this work. The latter is created considering visible and thermal image sensors with different real-world conditions, such as variations in illumination, facial expression, pose, occlusion, etc. The main conclusions of this article are that two variants of the proposed fusion methodology surpass current face recognition methods and the classic fusion techniques reported in the literature, attaining recognition rates of over 97% and 99% for the Equinox and PUCV-VTF databases, respectively. The fusion methodology is very robust to illumination and expression changes, as it combines thermal and visible information efficiently by using genetic algorithms, thus allowing it to choose optimal face areas where one spectrum is more representative than the other.

Study on recognition algorithm for paper currency numbers based on neural network

NASA Astrophysics Data System (ADS)

Li, Xiuyan; Liu, Tiegen; Li, Yuanyao; Zhang, Zhongchuan; Deng, Shichao

2008-12-01

Based on the unique characteristic, the paper currency numbers can be put into record and the automatic identification equipment for paper currency numbers is supplied to currency circulation market in order to provide convenience for financial sectors to trace the fiduciary circulation socially and provide effective supervision on paper currency. Simultaneously it is favorable for identifying forged notes, blacklisting the forged notes numbers and solving the major social problems, such as armor cash carrier robbery, money laundering. For the purpose of recognizing the paper currency numbers, a recognition algorithm based on neural network is presented in the paper. Number lines in original paper currency images can be draw out through image processing, such as image de-noising, skew correction, segmentation, and image normalization. According to the different characteristics between digits and letters in serial number, two kinds of classifiers are designed. With the characteristics of associative memory, optimization-compute and rapid convergence, the Discrete Hopfield Neural Network (DHNN) is utilized to recognize the letters; with the characteristics of simple structure, quick learning and global optimum, the Radial-Basis Function Neural Network (RBFNN) is adopted to identify the digits. Then the final recognition results are obtained by combining the two kinds of recognition results in regular sequence. Through the simulation tests, it is confirmed by simulation results that the recognition algorithm of combination of two kinds of recognition methods has such advantages as high recognition rate and faster recognition simultaneously, which is worthy of broad application prospect.

Fusion of Visible and Thermal Descriptors Using Genetic Algorithms for Face Recognition Systems

PubMed Central

Hermosilla, Gabriel; Gallardo, Francisco; Farias, Gonzalo; San Martin, Cesar

2015-01-01

The aim of this article is to present a new face recognition system based on the fusion of visible and thermal features obtained from the most current local matching descriptors by maximizing face recognition rates through the use of genetic algorithms. The article considers a comparison of the performance of the proposed fusion methodology against five current face recognition methods and classic fusion techniques used commonly in the literature. These were selected by considering their performance in face recognition. The five local matching methods and the proposed fusion methodology are evaluated using the standard visible/thermal database, the Equinox database, along with a new database, the PUCV-VTF, designed for visible-thermal studies in face recognition and described for the first time in this work. The latter is created considering visible and thermal image sensors with different real-world conditions, such as variations in illumination, facial expression, pose, occlusion, etc. The main conclusions of this article are that two variants of the proposed fusion methodology surpass current face recognition methods and the classic fusion techniques reported in the literature, attaining recognition rates of over 97% and 99% for the Equinox and PUCV-VTF databases, respectively. The fusion methodology is very robust to illumination and expression changes, as it combines thermal and visible information efficiently by using genetic algorithms, thus allowing it to choose optimal face areas where one spectrum is more representative than the other. PMID:26213932

Basics of identification measurement technology

NASA Astrophysics Data System (ADS)

Klikushin, Yu N.; Kobenko, V. Yu; Stepanov, P. P.

2018-01-01

All available algorithms and suitable for pattern recognition do not give 100% guarantee, therefore there is a field of scientific night activity in this direction, studies are relevant. It is proposed to develop existing technologies for pattern recognition in the form of application of identification measurements. The purpose of the study is to identify the possibility of recognizing images using identification measurement technologies. In solving problems of pattern recognition, neural networks and hidden Markov models are mainly used. A fundamentally new approach to the solution of problems of pattern recognition based on the technology of identification signal measurements (IIS) is proposed. The essence of IIS technology is the quantitative evaluation of the shape of images using special tools and algorithms.

A study of speech emotion recognition based on hybrid algorithm

NASA Astrophysics Data System (ADS)

Zhu, Ju-xia; Zhang, Chao; Lv, Zhao; Rao, Yao-quan; Wu, Xiao-pei

2011-10-01

To effectively improve the recognition accuracy of the speech emotion recognition system, a hybrid algorithm which combines Continuous Hidden Markov Model (CHMM), All-Class-in-One Neural Network (ACON) and Support Vector Machine (SVM) is proposed. In SVM and ACON methods, some global statistics are used as emotional features, while in CHMM method, instantaneous features are employed. The recognition rate by the proposed method is 92.25%, with the rejection rate to be 0.78%. Furthermore, it obtains the relative increasing of 8.53%, 4.69% and 0.78% compared with ACON, CHMM and SVM methods respectively. The experiment result confirms the efficiency of distinguishing anger, happiness, neutral and sadness emotional states.

Automatic detection and recognition of traffic signs in stereo images based on features and probabilistic neural networks

NASA Astrophysics Data System (ADS)

Sheng, Yehua; Zhang, Ka; Ye, Chun; Liang, Cheng; Li, Jian

2008-04-01

Considering the problem of automatic traffic sign detection and recognition in stereo images captured under motion conditions, a new algorithm for traffic sign detection and recognition based on features and probabilistic neural networks (PNN) is proposed in this paper. Firstly, global statistical color features of left image are computed based on statistics theory. Then for red, yellow and blue traffic signs, left image is segmented to three binary images by self-adaptive color segmentation method. Secondly, gray-value projection and shape analysis are used to confirm traffic sign regions in left image. Then stereo image matching is used to locate the homonymy traffic signs in right image. Thirdly, self-adaptive image segmentation is used to extract binary inner core shapes of detected traffic signs. One-dimensional feature vectors of inner core shapes are computed by central projection transformation. Fourthly, these vectors are input to the trained probabilistic neural networks for traffic sign recognition. Lastly, recognition results in left image are compared with recognition results in right image. If results in stereo images are identical, these results are confirmed as final recognition results. The new algorithm is applied to 220 real images of natural scenes taken by the vehicle-borne mobile photogrammetry system in Nanjing at different time. Experimental results show a detection and recognition rate of over 92%. So the algorithm is not only simple, but also reliable and high-speed on real traffic sign detection and recognition. Furthermore, it can obtain geometrical information of traffic signs at the same time of recognizing their types.

Identification of Alfalfa Leaf Diseases Using Image Recognition Technology

PubMed Central

Qin, Feng; Liu, Dongxia; Sun, Bingda; Ruan, Liu; Ma, Zhanhong; Wang, Haiguang

2016-01-01

Common leaf spot (caused by Pseudopeziza medicaginis), rust (caused by Uromyces striatus), Leptosphaerulina leaf spot (caused by Leptosphaerulina briosiana) and Cercospora leaf spot (caused by Cercospora medicaginis) are the four common types of alfalfa leaf diseases. Timely and accurate diagnoses of these diseases are critical for disease management, alfalfa quality control and the healthy development of the alfalfa industry. In this study, the identification and diagnosis of the four types of alfalfa leaf diseases were investigated using pattern recognition algorithms based on image-processing technology. A sub-image with one or multiple typical lesions was obtained by artificial cutting from each acquired digital disease image. Then the sub-images were segmented using twelve lesion segmentation methods integrated with clustering algorithms (including K_means clustering, fuzzy C-means clustering and K_median clustering) and supervised classification algorithms (including logistic regression analysis, Naive Bayes algorithm, classification and regression tree, and linear discriminant analysis). After a comprehensive comparison, the segmentation method integrating the K_median clustering algorithm and linear discriminant analysis was chosen to obtain lesion images. After the lesion segmentation using this method, a total of 129 texture, color and shape features were extracted from the lesion images. Based on the features selected using three methods (ReliefF, 1R and correlation-based feature selection), disease recognition models were built using three supervised learning methods, including the random forest, support vector machine (SVM) and K-nearest neighbor methods. A comparison of the recognition results of the models was conducted. The results showed that when the ReliefF method was used for feature selection, the SVM model built with the most important 45 features (selected from a total of 129 features) was the optimal model. For this SVM model, the recognition accuracies of the training set and the testing set were 97.64% and 94.74%, respectively. Semi-supervised models for disease recognition were built based on the 45 effective features that were used for building the optimal SVM model. For the optimal semi-supervised models built with three ratios of labeled to unlabeled samples in the training set, the recognition accuracies of the training set and the testing set were both approximately 80%. The results indicated that image recognition of the four alfalfa leaf diseases can be implemented with high accuracy. This study provides a feasible solution for lesion image segmentation and image recognition of alfalfa leaf disease. PMID:27977767

Identification of Alfalfa Leaf Diseases Using Image Recognition Technology.

PubMed

Qin, Feng; Liu, Dongxia; Sun, Bingda; Ruan, Liu; Ma, Zhanhong; Wang, Haiguang

2016-01-01

Common leaf spot (caused by Pseudopeziza medicaginis), rust (caused by Uromyces striatus), Leptosphaerulina leaf spot (caused by Leptosphaerulina briosiana) and Cercospora leaf spot (caused by Cercospora medicaginis) are the four common types of alfalfa leaf diseases. Timely and accurate diagnoses of these diseases are critical for disease management, alfalfa quality control and the healthy development of the alfalfa industry. In this study, the identification and diagnosis of the four types of alfalfa leaf diseases were investigated using pattern recognition algorithms based on image-processing technology. A sub-image with one or multiple typical lesions was obtained by artificial cutting from each acquired digital disease image. Then the sub-images were segmented using twelve lesion segmentation methods integrated with clustering algorithms (including K_means clustering, fuzzy C-means clustering and K_median clustering) and supervised classification algorithms (including logistic regression analysis, Naive Bayes algorithm, classification and regression tree, and linear discriminant analysis). After a comprehensive comparison, the segmentation method integrating the K_median clustering algorithm and linear discriminant analysis was chosen to obtain lesion images. After the lesion segmentation using this method, a total of 129 texture, color and shape features were extracted from the lesion images. Based on the features selected using three methods (ReliefF, 1R and correlation-based feature selection), disease recognition models were built using three supervised learning methods, including the random forest, support vector machine (SVM) and K-nearest neighbor methods. A comparison of the recognition results of the models was conducted. The results showed that when the ReliefF method was used for feature selection, the SVM model built with the most important 45 features (selected from a total of 129 features) was the optimal model. For this SVM model, the recognition accuracies of the training set and the testing set were 97.64% and 94.74%, respectively. Semi-supervised models for disease recognition were built based on the 45 effective features that were used for building the optimal SVM model. For the optimal semi-supervised models built with three ratios of labeled to unlabeled samples in the training set, the recognition accuracies of the training set and the testing set were both approximately 80%. The results indicated that image recognition of the four alfalfa leaf diseases can be implemented with high accuracy. This study provides a feasible solution for lesion image segmentation and image recognition of alfalfa leaf disease.

Use of the recognition heuristic depends on the domain's recognition validity, not on the recognition validity of selected sets of objects.

PubMed

Pohl, Rüdiger F; Michalkiewicz, Martha; Erdfelder, Edgar; Hilbig, Benjamin E

2017-07-01

According to the recognition-heuristic theory, decision makers solve paired comparisons in which one object is recognized and the other not by recognition alone, inferring that recognized objects have higher criterion values than unrecognized ones. However, success-and thus usefulness-of this heuristic depends on the validity of recognition as a cue, and adaptive decision making, in turn, requires that decision makers are sensitive to it. To this end, decision makers could base their evaluation of the recognition validity either on the selected set of objects (the set's recognition validity), or on the underlying domain from which the objects were drawn (the domain's recognition validity). In two experiments, we manipulated the recognition validity both in the selected set of objects and between domains from which the sets were drawn. The results clearly show that use of the recognition heuristic depends on the domain's recognition validity, not on the set's recognition validity. In other words, participants treat all sets as roughly representative of the underlying domain and adjust their decision strategy adaptively (only) with respect to the more general environment rather than the specific items they are faced with.

Human action recognition based on point context tensor shape descriptor

NASA Astrophysics Data System (ADS)

Li, Jianjun; Mao, Xia; Chen, Lijiang; Wang, Lan

2017-07-01

Motion trajectory recognition is one of the most important means to determine the identity of a moving object. A compact and discriminative feature representation method can improve the trajectory recognition accuracy. This paper presents an efficient framework for action recognition using a three-dimensional skeleton kinematic joint model. First, we put forward a rotation-scale-translation-invariant shape descriptor based on point context (PC) and the normal vector of hypersurface to jointly characterize local motion and shape information. Meanwhile, an algorithm for extracting the key trajectory based on the confidence coefficient is proposed to reduce the randomness and computational complexity. Second, to decrease the eigenvalue decomposition time complexity, a tensor shape descriptor (TSD) based on PC that can globally capture the spatial layout and temporal order to preserve the spatial information of each frame is proposed. Then, a multilinear projection process is achieved by tensor dynamic time warping to map the TSD to a low-dimensional tensor subspace of the same size. Experimental results show that the proposed shape descriptor is effective and feasible, and the proposed approach obtains considerable performance improvement over the state-of-the-art approaches with respect to accuracy on a public action dataset.

Improving a HMM-based off-line handwriting recognition system using MME-PSO optimization

NASA Astrophysics Data System (ADS)

Hamdani, Mahdi; El Abed, Haikal; Hamdani, Tarek M.; Märgner, Volker; Alimi, Adel M.

2011-01-01

One of the trivial steps in the development of a classifier is the design of its architecture. This paper presents a new algorithm, Multi Models Evolvement (MME) using Particle Swarm Optimization (PSO). This algorithm is a modified version of the basic PSO, which is used to the unsupervised design of Hidden Markov Model (HMM) based architectures. For instance, the proposed algorithm is applied to an Arabic handwriting recognizer based on discrete probability HMMs. After the optimization of their architectures, HMMs are trained with the Baum- Welch algorithm. The validation of the system is based on the IfN/ENIT database. The performance of the developed approach is compared to the participating systems at the 2005 competition organized on Arabic handwriting recognition on the International Conference on Document Analysis and Recognition (ICDAR). The final system is a combination between an optimized HMM with 6 other HMMs obtained by a simple variation of the number of states. An absolute improvement of 6% of word recognition rate with about 81% is presented. This improvement is achieved comparing to the basic system (ARAB-IfN). The proposed recognizer outperforms also most of the known state-of-the-art systems.

Design of compactly supported wavelet to match singularities in medical images

NASA Astrophysics Data System (ADS)

Fung, Carrson C.; Shi, Pengcheng

2002-11-01

Analysis and understanding of medical images has important clinical values for patient diagnosis and treatment, as well as technical implications for computer vision and pattern recognition. One of the most fundamental issues is the detection of object boundaries or singularities, which is often the basis for further processes such as organ/tissue recognition, image registration, motion analysis, measurement of anatomical and physiological parameters, etc. The focus of this work involved taking a correlation based approach toward edge detection, by exploiting some of desirable properties of wavelet analysis. This leads to the possibility of constructing a bank of detectors, consisting of multiple wavelet basis functions of different scales which are optimal for specific types of edges, in order to optimally detect all the edges in an image. Our work involved developing a set of wavelet functions which matches the shape of the ramp and pulse edges. The matching algorithm used focuses on matching the edges in the frequency domain. It was proven that this technique could create matching wavelets applicable at all scales. Results have shown that matching wavelets can be obtained for the pulse edge while the ramp edge requires another matching algorithm.

What does voice-processing technology support today?

PubMed Central

Nakatsu, R; Suzuki, Y

1995-01-01

This paper describes the state of the art in applications of voice-processing technologies. In the first part, technologies concerning the implementation of speech recognition and synthesis algorithms are described. Hardware technologies such as microprocessors and DSPs (digital signal processors) are discussed. Software development environment, which is a key technology in developing applications software, ranging from DSP software to support software also is described. In the second part, the state of the art of algorithms from the standpoint of applications is discussed. Several issues concerning evaluation of speech recognition/synthesis algorithms are covered, as well as issues concerning the robustness of algorithms in adverse conditions. Images Fig. 3 PMID:7479720

Eye movements during object recognition in visual agnosia.

PubMed

Charles Leek, E; Patterson, Candy; Paul, Matthew A; Rafal, Robert; Cristino, Filipe

2012-07-01

This paper reports the first ever detailed study about eye movement patterns during single object recognition in visual agnosia. Eye movements were recorded in a patient with an integrative agnosic deficit during two recognition tasks: common object naming and novel object recognition memory. The patient showed normal directional biases in saccades and fixation dwell times in both tasks and was as likely as controls to fixate within object bounding contour regardless of recognition accuracy. In contrast, following initial saccades of similar amplitude to controls, the patient showed a bias for short saccades. In object naming, but not in recognition memory, the similarity of the spatial distributions of patient and control fixations was modulated by recognition accuracy. The study provides new evidence about how eye movements can be used to elucidate the functional impairments underlying object recognition deficits. We argue that the results reflect a breakdown in normal functional processes involved in the integration of shape information across object structure during the visual perception of shape. Copyright © 2012 Elsevier Ltd. All rights reserved.

Multi-source feature extraction and target recognition in wireless sensor networks based on adaptive distributed wavelet compression algorithms

NASA Astrophysics Data System (ADS)

Hortos, William S.

2008-04-01

Proposed distributed wavelet-based algorithms are a means to compress sensor data received at the nodes forming a wireless sensor network (WSN) by exchanging information between neighboring sensor nodes. Local collaboration among nodes compacts the measurements, yielding a reduced fused set with equivalent information at far fewer nodes. Nodes may be equipped with multiple sensor types, each capable of sensing distinct phenomena: thermal, humidity, chemical, voltage, or image signals with low or no frequency content as well as audio, seismic or video signals within defined frequency ranges. Compression of the multi-source data through wavelet-based methods, distributed at active nodes, reduces downstream processing and storage requirements along the paths to sink nodes; it also enables noise suppression and more energy-efficient query routing within the WSN. Targets are first detected by the multiple sensors; then wavelet compression and data fusion are applied to the target returns, followed by feature extraction from the reduced data; feature data are input to target recognition/classification routines; targets are tracked during their sojourns through the area monitored by the WSN. Algorithms to perform these tasks are implemented in a distributed manner, based on a partition of the WSN into clusters of nodes. In this work, a scheme of collaborative processing is applied for hierarchical data aggregation and decorrelation, based on the sensor data itself and any redundant information, enabled by a distributed, in-cluster wavelet transform with lifting that allows multiple levels of resolution. The wavelet-based compression algorithm significantly decreases RF bandwidth and other resource use in target processing tasks. Following wavelet compression, features are extracted. The objective of feature extraction is to maximize the probabilities of correct target classification based on multi-source sensor measurements, while minimizing the resource expenditures at participating nodes. Therefore, the feature-extraction method based on the Haar DWT is presented that employs a maximum-entropy measure to determine significant wavelet coefficients. Features are formed by calculating the energy of coefficients grouped around the competing clusters. A DWT-based feature extraction algorithm used for vehicle classification in WSNs can be enhanced by an added rule for selecting the optimal number of resolution levels to improve the correct classification rate and reduce energy consumption expended in local algorithm computations. Published field trial data for vehicular ground targets, measured with multiple sensor types, are used to evaluate the wavelet-assisted algorithms. Extracted features are used in established target recognition routines, e.g., the Bayesian minimum-error-rate classifier, to compare the effects on the classification performance of the wavelet compression. Simulations of feature sets and recognition routines at different resolution levels in target scenarios indicate the impact on classification rates, while formulas are provided to estimate reduction in resource use due to distributed compression.

Exploiting passive polarimetric imagery for remote sensing applications

NASA Astrophysics Data System (ADS)

Vimal Thilak Krishna, Thilakam

Polarization is a property of light or electromagnetic radiation that conveys information about the orientation of the transverse electric and magnetic fields. The polarization of reflected light complements other electromagnetic radiation attributes such as intensity, frequency, or spectral characteristics. A passive polarization based imaging system records the polarization state of light reflected by objects that are illuminated with an unpolarized and generally uncontrolled source. The polarization due to surface reflections from such objects contains information about the targets that can be exploited in remote sensing applications such as target detection, target classification, object recognition and shape extraction/recognition. In recent years, there has been renewed interest in the use of passive polarization information in remote sensing applications. The goal of our research is to design image processing algorithms for remote sensing applications by utilizing physics-based models that describe the polarization imparted by optical scattering from an object. In this dissertation, we present a method to estimate the complex index of refraction and reflection angle from multiple polarization measurements. This method employs a polarimetric bidirectional reflectance distribution function (pBRDF) that accounts for polarization due to specular scattering. The parameters of interest are derived by utilizing a nonlinear least squares estimation algorithm, and computer simulation results show that the estimation accuracy generally improves with an increasing number of source position measurements. Furthermore, laboratory results indicate that the proposed method is effective for recovering the reflection angle and that the estimated index of refraction provides a feature vector that is robust to the reflection angle. We also study the use of extracted index of refraction as a feature vector in designing two important image processing applications, namely image segmentation and material classification so that the resulting systems are largely invariant to illumination source location. This is in contrast to most passive polarization-based image processing algorithms proposed in the literature that employ quantities such as Stokes vectors and the degree of polarization and which are not robust to changes in illumination conditions. The estimated index of refraction, on the other hand, is invariant to illumination conditions and hence can be used as an input to image processing algorithms. The proposed estimation framework also is extended to the case where the position of the observer (camera) moves between measurements while that of the source remains fixed. Finally, we explore briefly the topic of parameter estimation for a generalized model that accounts for both specular and volumetric scattering. A combination of simulation and experimental results are provided to evaluate the effectiveness of the above methods.

The role of color information on object recognition: a review and meta-analysis.

PubMed

Bramão, Inês; Reis, Alexandra; Petersson, Karl Magnus; Faísca, Luís

2011-09-01

In this study, we systematically review the scientific literature on the effect of color on object recognition. Thirty-five independent experiments, comprising 1535 participants, were included in a meta-analysis. We found a moderate effect of color on object recognition (d=0.28). Specific effects of moderator variables were analyzed and we found that color diagnosticity is the factor with the greatest moderator effect on the influence of color in object recognition; studies using color diagnostic objects showed a significant color effect (d=0.43), whereas a marginal color effect was found in studies that used non-color diagnostic objects (d=0.18). The present study did not permit the drawing of specific conclusions about the moderator effect of the object recognition task; while the meta-analytic review showed that color information improves object recognition mainly in studies using naming tasks (d=0.36), the literature review revealed a large body of evidence showing positive effects of color information on object recognition in studies using a large variety of visual recognition tasks. We also found that color is important for the ability to recognize artifacts and natural objects, to recognize objects presented as types (line-drawings) or as tokens (photographs), and to recognize objects that are presented without surface details, such as texture or shadow. Taken together, the results of the meta-analysis strongly support the contention that color plays a role in object recognition. This suggests that the role of color should be taken into account in models of visual object recognition. Copyright © 2011 Elsevier B.V. All rights reserved.

The role of perceptual load in object recognition.

PubMed

Lavie, Nilli; Lin, Zhicheng; Zokaei, Nahid; Thoma, Volker

2009-10-01

Predictions from perceptual load theory (Lavie, 1995, 2005) regarding object recognition across the same or different viewpoints were tested. Results showed that high perceptual load reduces distracter recognition levels despite always presenting distracter objects from the same view. They also showed that the levels of distracter recognition were unaffected by a change in the distracter object view under conditions of low perceptual load. These results were found both with repetition priming measures of distracter recognition and with performance on a surprise recognition memory test. The results support load theory proposals that distracter recognition critically depends on the level of perceptual load. The implications for the role of attention in object recognition theories are discussed. PsycINFO Database Record (c) 2009 APA, all rights reserved.

A multifaceted independent performance analysis of facial subspace recognition algorithms.

PubMed

Bajwa, Usama Ijaz; Taj, Imtiaz Ahmad; Anwar, Muhammad Waqas; Wang, Xuan

2013-01-01

Face recognition has emerged as the fastest growing biometric technology and has expanded a lot in the last few years. Many new algorithms and commercial systems have been proposed and developed. Most of them use Principal Component Analysis (PCA) as a base for their techniques. Different and even conflicting results have been reported by researchers comparing these algorithms. The purpose of this study is to have an independent comparative analysis considering both performance and computational complexity of six appearance based face recognition algorithms namely PCA, 2DPCA, A2DPCA, (2D)(2)PCA, LPP and 2DLPP under equal working conditions. This study was motivated due to the lack of unbiased comprehensive comparative analysis of some recent subspace methods with diverse distance metric combinations. For comparison with other studies, FERET, ORL and YALE databases have been used with evaluation criteria as of FERET evaluations which closely simulate real life scenarios. A comparison of results with previous studies is performed and anomalies are reported. An important contribution of this study is that it presents the suitable performance conditions for each of the algorithms under consideration.

An evolution based biosensor receptor DNA sequence generation algorithm.

PubMed

Kim, Eungyeong; Lee, Malrey; Gatton, Thomas M; Lee, Jaewan; Zang, Yupeng

2010-01-01

A biosensor is composed of a bioreceptor, an associated recognition molecule, and a signal transducer that can selectively detect target substances for analysis. DNA based biosensors utilize receptor molecules that allow hybridization with the target analyte. However, most DNA biosensor research uses oligonucleotides as the target analytes and does not address the potential problems of real samples. The identification of recognition molecules suitable for real target analyte samples is an important step towards further development of DNA biosensors. This study examines the characteristics of DNA used as bioreceptors and proposes a hybrid evolution-based DNA sequence generating algorithm, based on DNA computing, to identify suitable DNA bioreceptor recognition molecules for stable hybridization with real target substances. The Traveling Salesman Problem (TSP) approach is applied in the proposed algorithm to evaluate the safety and fitness of the generated DNA sequences. This approach improves efficiency and stability for enhanced and variable-length DNA sequence generation and allows extension to generation of variable-length DNA sequences with diverse receptor recognition requirements.

Gabor filter based fingerprint image enhancement

NASA Astrophysics Data System (ADS)

Wang, Jin-Xiang

2013-03-01

Fingerprint recognition technology has become the most reliable biometric technology due to its uniqueness and invariance, which has been most convenient and most reliable technique for personal authentication. The development of Automated Fingerprint Identification System is an urgent need for modern information security. Meanwhile, fingerprint preprocessing algorithm of fingerprint recognition technology has played an important part in Automatic Fingerprint Identification System. This article introduces the general steps in the fingerprint recognition technology, namely the image input, preprocessing, feature recognition, and fingerprint image enhancement. As the key to fingerprint identification technology, fingerprint image enhancement affects the accuracy of the system. It focuses on the characteristics of the fingerprint image, Gabor filters algorithm for fingerprint image enhancement, the theoretical basis of Gabor filters, and demonstration of the filter. The enhancement algorithm for fingerprint image is in the windows XP platform with matlab.65 as a development tool for the demonstration. The result shows that the Gabor filter is effective in fingerprint image enhancement technology.

3D automatic anatomy segmentation based on iterative graph-cut-ASM

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

Chen, Xinjian; Bagci, Ulas; Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Building 10 Room 1C515, Bethesda, Maryland 20892-1182

2011-08-15

Purpose: This paper studies the feasibility of developing an automatic anatomy segmentation (AAS) system in clinical radiology and demonstrates its operation on clinical 3D images. Methods: The AAS system, the authors are developing consists of two main parts: object recognition and object delineation. As for recognition, a hierarchical 3D scale-based multiobject method is used for the multiobject recognition task, which incorporates intensity weighted ball-scale (b-scale) information into the active shape model (ASM). For object delineation, an iterative graph-cut-ASM (IGCASM) algorithm is proposed, which effectively combines the rich statistical shape information embodied in ASM with the globally optimal delineation capability ofmore » the GC method. The presented IGCASM algorithm is a 3D generalization of the 2D GC-ASM method that they proposed previously in Chen et al.[Proc. SPIE, 7259, 72590C1-72590C-8 (2009)]. The proposed methods are tested on two datasets comprised of images obtained from 20 patients (10 male and 10 female) of clinical abdominal CT scans, and 11 foot magnetic resonance imaging (MRI) scans. The test is for four organs (liver, left and right kidneys, and spleen) segmentation, five foot bones (calcaneus, tibia, cuboid, talus, and navicular). The recognition and delineation accuracies were evaluated separately. The recognition accuracy was evaluated in terms of translation, rotation, and scale (size) error. The delineation accuracy was evaluated in terms of true and false positive volume fractions (TPVF, FPVF). The efficiency of the delineation method was also evaluated on an Intel Pentium IV PC with a 3.4 GHZ CPU machine. Results: The recognition accuracies in terms of translation, rotation, and scale error over all organs are about 8 mm, 10 deg. and 0.03, and over all foot bones are about 3.5709 mm, 0.35 deg. and 0.025, respectively. The accuracy of delineation over all organs for all subjects as expressed in TPVF and FPVF is 93.01% and 0.22%, and all foot bones for all subjects are 93.75% and 0.28%, respectively. While the delineations for the four organs can be accomplished quite rapidly with average of 78 s, the delineations for the five foot bones can be accomplished with average of 70 s. Conclusions: The experimental results showed the feasibility and efficacy of the proposed automatic anatomy segmentation system: (a) the incorporation of shape priors into the GC framework is feasible in 3D as demonstrated previously for 2D images; (b) our results in 3D confirm the accuracy behavior observed in 2D. The hybrid strategy IGCASM seems to be more robust and accurate than ASM and GC individually; and (c) delineations within body regions and foot bones of clinical importance can be accomplished quite rapidly within 1.5 min.« less

3D automatic anatomy segmentation based on iterative graph-cut-ASM

PubMed Central

Chen, Xinjian; Bagci, Ulas

2011-01-01

Purpose: This paper studies the feasibility of developing an automatic anatomy segmentation (AAS) system in clinical radiology and demonstrates its operation on clinical 3D images.Methods: The AAS system, the authors are developing consists of two main parts: object recognition and object delineation. As for recognition, a hierarchical 3D scale-based multiobject method is used for the multiobject recognition task, which incorporates intensity weighted ball-scale (b-scale) information into the active shape model (ASM). For object delineation, an iterative graph-cut-ASM (IGCASM) algorithm is proposed, which effectively combines the rich statistical shape information embodied in ASM with the globally optimal delineation capability of the GC method. The presented IGCASM algorithm is a 3D generalization of the 2D GC-ASM method that they proposed previously in Chen et al. [Proc. SPIE, 7259, 72590C1–72590C-8 (2009)]. The proposed methods are tested on two datasets comprised of images obtained from 20 patients (10 male and 10 female) of clinical abdominal CT scans, and 11 foot magnetic resonance imaging (MRI) scans. The test is for four organs (liver, left and right kidneys, and spleen) segmentation, five foot bones (calcaneus, tibia, cuboid, talus, and navicular). The recognition and delineation accuracies were evaluated separately. The recognition accuracy was evaluated in terms of translation, rotation, and scale (size) error. The delineation accuracy was evaluated in terms of true and false positive volume fractions (TPVF, FPVF). The efficiency of the delineation method was also evaluated on an Intel Pentium IV PC with a 3.4 GHZ CPU machine.Results: The recognition accuracies in terms of translation, rotation, and scale error over all organs are about 8 mm, 10° and 0.03, and over all foot bones are about 3.5709 mm, 0.35° and 0.025, respectively. The accuracy of delineation over all organs for all subjects as expressed in TPVF and FPVF is 93.01% and 0.22%, and all foot bones for all subjects are 93.75% and 0.28%, respectively. While the delineations for the four organs can be accomplished quite rapidly with average of 78 s, the delineations for the five foot bones can be accomplished with average of 70 s.Conclusions: The experimental results showed the feasibility and efficacy of the proposed automatic anatomy segmentation system: (a) the incorporation of shape priors into the GC framework is feasible in 3D as demonstrated previously for 2D images; (b) our results in 3D confirm the accuracy behavior observed in 2D. The hybrid strategy IGCASM seems to be more robust and accurate than ASM and GC individually; and (c) delineations within body regions and foot bones of clinical importance can be accomplished quite rapidly within 1.5 min. PMID:21928634

SigVox - A 3D feature matching algorithm for automatic street object recognition in mobile laser scanning point clouds

NASA Astrophysics Data System (ADS)

Wang, Jinhu; Lindenbergh, Roderik; Menenti, Massimo

2017-06-01

Urban road environments contain a variety of objects including different types of lamp poles and traffic signs. Its monitoring is traditionally conducted by visual inspection, which is time consuming and expensive. Mobile laser scanning (MLS) systems sample the road environment efficiently by acquiring large and accurate point clouds. This work proposes a methodology for urban road object recognition from MLS point clouds. The proposed method uses, for the first time, shape descriptors of complete objects to match repetitive objects in large point clouds. To do so, a novel 3D multi-scale shape descriptor is introduced, that is embedded in a workflow that efficiently and automatically identifies different types of lamp poles and traffic signs. The workflow starts by tiling the raw point clouds along the scanning trajectory and by identifying non-ground points. After voxelization of the non-ground points, connected voxels are clustered to form candidate objects. For automatic recognition of lamp poles and street signs, a 3D significant eigenvector based shape descriptor using voxels (SigVox) is introduced. The 3D SigVox descriptor is constructed by first subdividing the points with an octree into several levels. Next, significant eigenvectors of the points in each voxel are determined by principal component analysis (PCA) and mapped onto the appropriate triangle of a sphere approximating icosahedron. This step is repeated for different scales. By determining the similarity of 3D SigVox descriptors between candidate point clusters and training objects, street furniture is automatically identified. The feasibility and quality of the proposed method is verified on two point clouds obtained in opposite direction of a stretch of road of 4 km. 6 types of lamp pole and 4 types of road sign were selected as objects of interest. Ground truth validation showed that the overall accuracy of the ∼170 automatically recognized objects is approximately 95%. The results demonstrate that the proposed method is able to recognize street furniture in a practical scenario. Remaining difficult cases are touching objects, like a lamp pole close to a tree.

GPU-based relative fuzzy connectedness image segmentation.

PubMed

Zhuge, Ying; Ciesielski, Krzysztof C; Udupa, Jayaram K; Miller, Robert W

2013-01-01

Recently, clinical radiological research and practice are becoming increasingly quantitative. Further, images continue to increase in size and volume. For quantitative radiology to become practical, it is crucial that image segmentation algorithms and their implementations are rapid and yield practical run time on very large data sets. The purpose of this paper is to present a parallel version of an algorithm that belongs to the family of fuzzy connectedness (FC) algorithms, to achieve an interactive speed for segmenting large medical image data sets. The most common FC segmentations, optimizing an [script-l](∞)-based energy, are known as relative fuzzy connectedness (RFC) and iterative relative fuzzy connectedness (IRFC). Both RFC and IRFC objects (of which IRFC contains RFC) can be found via linear time algorithms, linear with respect to the image size. The new algorithm, P-ORFC (for parallel optimal RFC), which is implemented by using NVIDIA's Compute Unified Device Architecture (CUDA) platform, considerably improves the computational speed of the above mentioned CPU based IRFC algorithm. Experiments based on four data sets of small, medium, large, and super data size, achieved speedup factors of 32.8×, 22.9×, 20.9×, and 17.5×, correspondingly, on the NVIDIA Tesla C1060 platform. Although the output of P-ORFC need not precisely match that of IRFC output, it is very close to it and, as the authors prove, always lies between the RFC and IRFC objects. A parallel version of a top-of-the-line algorithm in the family of FC has been developed on the NVIDIA GPUs. An interactive speed of segmentation has been achieved, even for the largest medical image data set. Such GPU implementations may play a crucial role in automatic anatomy recognition in clinical radiology.

GPU-based relative fuzzy connectedness image segmentation

PubMed Central

Zhuge, Ying; Ciesielski, Krzysztof C.; Udupa, Jayaram K.; Miller, Robert W.

2013-01-01

Purpose: Recently, clinical radiological research and practice are becoming increasingly quantitative. Further, images continue to increase in size and volume. For quantitative radiology to become practical, it is crucial that image segmentation algorithms and their implementations are rapid and yield practical run time on very large data sets. The purpose of this paper is to present a parallel version of an algorithm that belongs to the family of fuzzy connectedness (FC) algorithms, to achieve an interactive speed for segmenting large medical image data sets. Methods: The most common FC segmentations, optimizing an ℓ∞-based energy, are known as relative fuzzy connectedness (RFC) and iterative relative fuzzy connectedness (IRFC). Both RFC and IRFC objects (of which IRFC contains RFC) can be found via linear time algorithms, linear with respect to the image size. The new algorithm, P-ORFC (for parallel optimal RFC), which is implemented by using NVIDIA’s Compute Unified Device Architecture (CUDA) platform, considerably improves the computational speed of the above mentioned CPU based IRFC algorithm. Results: Experiments based on four data sets of small, medium, large, and super data size, achieved speedup factors of 32.8×, 22.9×, 20.9×, and 17.5×, correspondingly, on the NVIDIA Tesla C1060 platform. Although the output of P-ORFC need not precisely match that of IRFC output, it is very close to it and, as the authors prove, always lies between the RFC and IRFC objects. Conclusions: A parallel version of a top-of-the-line algorithm in the family of FC has been developed on the NVIDIA GPUs. An interactive speed of segmentation has been achieved, even for the largest medical image data set. Such GPU implementations may play a crucial role in automatic anatomy recognition in clinical radiology. PMID:23298094

Improving activity recognition using a wearable barometric pressure sensor in mobility-impaired stroke patients.

PubMed

Massé, Fabien; Gonzenbach, Roman R; Arami, Arash; Paraschiv-Ionescu, Anisoara; Luft, Andreas R; Aminian, Kamiar

2015-08-25

Stroke survivors often suffer from mobility deficits. Current clinical evaluation methods, including questionnaires and motor function tests, cannot provide an objective measure of the patients' mobility in daily life. Physical activity performance in daily-life can be assessed using unobtrusive monitoring, for example with a single sensor module fixed on the trunk. Existing approaches based on inertial sensors have limited performance, particularly in detecting transitions between different activities and postures, due to the inherent inter-patient variability of kinematic patterns. To overcome these limitations, one possibility is to use additional information from a barometric pressure (BP) sensor. Our study aims at integrating BP and inertial sensor data into an activity classifier in order to improve the activity (sitting, standing, walking, lying) recognition and the corresponding body elevation (during climbing stairs or when taking an elevator). Taking into account the trunk elevation changes during postural transitions (sit-to-stand, stand-to-sit), we devised an event-driven activity classifier based on fuzzy-logic. Data were acquired from 12 stroke patients with impaired mobility, using a trunk-worn inertial and BP sensor. Events, including walking and lying periods and potential postural transitions, were first extracted. These events were then fed into a double-stage hierarchical Fuzzy Inference System (H-FIS). The first stage processed the events to infer activities and the second stage improved activity recognition by applying behavioral constraints. Finally, the body elevation was estimated using a pattern-enhancing algorithm applied on BP. The patients were videotaped for reference. The performance of the algorithm was estimated using the Correct Classification Rate (CCR) and F-score. The BP-based classification approach was benchmarked against a previously-published fuzzy-logic classifier (FIS-IMU) and a conventional epoch-based classifier (EPOCH). The algorithm performance for posture/activity detection, in terms of CCR was 90.4 %, with 3.3 % and 5.6 % improvements against FIS-IMU and EPOCH, respectively. The proposed classifier essentially benefits from a better recognition of standing activity (70.3 % versus 61.5 % [FIS-IMU] and 42.5 % [EPOCH]) with 98.2 % CCR for body elevation estimation. The monitoring and recognition of daily activities in mobility-impaired stoke patients can be significantly improved using a trunk-fixed sensor that integrates BP, inertial sensors, and an event-based activity classifier.

Unsupervised pattern recognition methods in ciders profiling based on GCE voltammetric signals.

PubMed

Jakubowska, Małgorzata; Sordoń, Wanda; Ciepiela, Filip

2016-07-15

This work presents a complete methodology of distinguishing between different brands of cider and ageing degrees, based on voltammetric signals, utilizing dedicated data preprocessing procedures and unsupervised multivariate analysis. It was demonstrated that voltammograms recorded on glassy carbon electrode in Britton-Robinson buffer at pH 2 are reproducible for each brand. By application of clustering algorithms and principal component analysis visible homogenous clusters were obtained. Advanced signal processing strategy which included automatic baseline correction, interval scaling and continuous wavelet transform with dedicated mother wavelet, was a key step in the correct recognition of the objects. The results show that voltammetry combined with optimized univariate and multivariate data processing is a sufficient tool to distinguish between ciders from various brands and to evaluate their freshness. Copyright © 2016 Elsevier Ltd. All rights reserved.

Quest Hierarchy for Hyperspectral Face Recognition

DTIC Science & Technology

2011-03-01

numerous face recognition algorithms available, several very good literature surveys are available that include Abate [29], Samal [110], Kong [18], Zou...Perception, Japan (January 1994). [110] Samal , Ashok and P. Iyengar, Automatic Recognition and Analysis of Human Faces and Facial Expressions: A Survey

Optimization of spectral bands for hyperspectral remote sensing of forest vegetation

NASA Astrophysics Data System (ADS)

Dmitriev, Egor V.; Kozoderov, Vladimir V.

2013-10-01

Optimization principles of accounting for the most informative spectral channels in hyperspectral remote sensing data processing serve to enhance the efficiency of the employed high-productive computers. The problem of pattern recognition of the remotely sensed land surface objects with the accent on the forests is outlined from the point of view of the spectral channels optimization on the processed hyperspectral images. The relevant computational procedures are tested using the images obtained by the produced in Russia hyperspectral camera that was installed on a gyro-stabilized platform to conduct the airborne flight campaigns. The Bayesian classifier is used for the pattern recognition of the forests with different tree species and age. The probabilistically optimal algorithm constructed on the basis of the maximum likelihood principle is described to minimize the probability of misclassification given by this classifier. The classification error is the major category to estimate the accuracy of the applied algorithm by the known holdout cross-validation method. Details of the related techniques are presented. Results are shown of selecting the spectral channels of the camera while processing the images having in mind radiometric distortions that diminish the classification accuracy. The spectral channels are selected of the obtained subclasses extracted from the proposed validation techniques and the confusion matrices are constructed that characterize the age composition of the classified pine species as well as the broad age-class recognition for the pine and birch species with the fully illuminated parts of their crowns.

It Takes Two–Skilled Recognition of Objects Engages Lateral Areas in Both Hemispheres

PubMed Central

Bilalić, Merim; Kiesel, Andrea; Pohl, Carsten; Erb, Michael; Grodd, Wolfgang

2011-01-01

Our object recognition abilities, a direct product of our experience with objects, are fine-tuned to perfection. Left temporal and lateral areas along the dorsal, action related stream, as well as left infero-temporal areas along the ventral, object related stream are engaged in object recognition. Here we show that expertise modulates the activity of dorsal areas in the recognition of man-made objects with clearly specified functions. Expert chess players were faster than chess novices in identifying chess objects and their functional relations. Experts' advantage was domain-specific as there were no differences between groups in a control task featuring geometrical shapes. The pattern of eye movements supported the notion that experts' extensive knowledge about domain objects and their functions enabled superior recognition even when experts were not directly fixating the objects of interest. Functional magnetic resonance imaging (fMRI) related exclusively the areas along the dorsal stream to chess specific object recognition. Besides the commonly involved left temporal and parietal lateral brain areas, we found that only in experts homologous areas on the right hemisphere were also engaged in chess specific object recognition. Based on these results, we discuss whether skilled object recognition does not only involve a more efficient version of the processes found in non-skilled recognition, but also qualitatively different cognitive processes which engage additional brain areas. PMID:21283683

Under what conditions is recognition spared relative to recall after selective hippocampal damage in humans?

PubMed

Holdstock, J S; Mayes, A R; Roberts, N; Cezayirli, E; Isaac, C L; O'Reilly, R C; Norman, K A

2002-01-01

The claim that recognition memory is spared relative to recall after focal hippocampal damage has been disputed in the literature. We examined this claim by investigating object and object-location recall and recognition memory in a patient, YR, who has adult-onset selective hippocampal damage. Our aim was to identify the conditions under which recognition was spared relative to recall in this patient. She showed unimpaired forced-choice object recognition but clearly impaired recall, even when her control subjects found the object recognition task to be numerically harder than the object recall task. However, on two other recognition tests, YR's performance was not relatively spared. First, she was clearly impaired at an equivalently difficult yes/no object recognition task, but only when targets and foils were very similar. Second, YR was clearly impaired at forced-choice recognition of object-location associations. This impairment was also unrelated to difficulty because this task was no more difficult than the forced-choice object recognition task for control subjects. The clear impairment of yes/no, but not of forced-choice, object recognition after focal hippocampal damage, when targets and foils are very similar, is predicted by the neural network-based Complementary Learning Systems model of recognition. This model postulates that recognition is mediated by hippocampally dependent recollection and cortically dependent familiarity; thus hippocampal damage should not impair item familiarity. The model postulates that familiarity is ineffective when very similar targets and foils are shown one at a time and subjects have to identify which items are old (yes/no recognition). In contrast, familiarity is effective in discriminating which of similar targets and foils, seen together, is old (forced-choice recognition). Independent evidence from the remember/know procedure also indicates that YR's familiarity is normal. The Complementary Learning Systems model can also accommodate the clear impairment of forced-choice object-location recognition memory if it incorporates the view that the most complete convergence of spatial and object information, represented in different cortical regions, occurs in the hippocampus.

Comparison of photo-matching algorithms commonly used for photographic capture-recapture studies.

PubMed

Matthé, Maximilian; Sannolo, Marco; Winiarski, Kristopher; Spitzen-van der Sluijs, Annemarieke; Goedbloed, Daniel; Steinfartz, Sebastian; Stachow, Ulrich

2017-08-01

Photographic capture-recapture is a valuable tool for obtaining demographic information on wildlife populations due to its noninvasive nature and cost-effectiveness. Recently, several computer-aided photo-matching algorithms have been developed to more efficiently match images of unique individuals in databases with thousands of images. However, the identification accuracy of these algorithms can severely bias estimates of vital rates and population size. Therefore, it is important to understand the performance and limitations of state-of-the-art photo-matching algorithms prior to implementation in capture-recapture studies involving possibly thousands of images. Here, we compared the performance of four photo-matching algorithms; Wild-ID, I3S Pattern+, APHIS, and AmphIdent using multiple amphibian databases of varying image quality. We measured the performance of each algorithm and evaluated the performance in relation to database size and the number of matching images in the database. We found that algorithm performance differed greatly by algorithm and image database, with recognition rates ranging from 100% to 22.6% when limiting the review to the 10 highest ranking images. We found that recognition rate degraded marginally with increased database size and could be improved considerably with a higher number of matching images in the database. In our study, the pixel-based algorithm of AmphIdent exhibited superior recognition rates compared to the other approaches. We recommend carefully evaluating algorithm performance prior to using it to match a complete database. By choosing a suitable matching algorithm, databases of sizes that are unfeasible to match "by eye" can be easily translated to accurate individual capture histories necessary for robust demographic estimates.

Autonomous intelligent assembly systems LDRD 105746 final report.

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

Anderson, Robert J.

2013-04-01

This report documents a three-year to develop technology that enables mobile robots to perform autonomous assembly tasks in unstructured outdoor environments. This is a multi-tier problem that requires an integration of a large number of different software technologies including: command and control, estimation and localization, distributed communications, object recognition, pose estimation, real-time scanning, and scene interpretation. Although ultimately unsuccessful in achieving a target brick stacking task autonomously, numerous important component technologies were nevertheless developed. Such technologies include: a patent-pending polygon snake algorithm for robust feature tracking, a color grid algorithm for uniquely identification and calibration, a command and control frameworkmore » for abstracting robot commands, a scanning capability that utilizes a compact robot portable scanner, and more. This report describes this project and these developed technologies.« less

Analysis of Variance in Statistical Image Processing

NASA Astrophysics Data System (ADS)

Kurz, Ludwik; Hafed Benteftifa, M.

1997-04-01

A key problem in practical image processing is the detection of specific features in a noisy image. Analysis of variance (ANOVA) techniques can be very effective in such situations, and this book gives a detailed account of the use of ANOVA in statistical image processing. The book begins by describing the statistical representation of images in the various ANOVA models. The authors present a number of computationally efficient algorithms and techniques to deal with such problems as line, edge, and object detection, as well as image restoration and enhancement. By describing the basic principles of these techniques, and showing their use in specific situations, the book will facilitate the design of new algorithms for particular applications. It will be of great interest to graduate students and engineers in the field of image processing and pattern recognition.

Higher-Order Neural Networks Applied to 2D and 3D Object Recognition

NASA Technical Reports Server (NTRS)

Spirkovska, Lilly; Reid, Max B.

1994-01-01

A Higher-Order Neural Network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous scaled, translated, and rotated views. Because the 2D object recognition task is a component of the 3D object recognition task, built-in 2D invariance also decreases the size of the training set required for 3D object recognition. We present results for 2D object recognition both in simulation and within a robotic vision experiment and for 3D object recognition in simulation. We also compare our method to other approaches and show that HONNs have distinct advantages for position, scale, and rotation-invariant object recognition. The major drawback of HONNs is that the size of the input field is limited due to the memory required for the large number of interconnections in a fully connected network. We present partial connectivity strategies and a coarse-coding technique for overcoming this limitation and increasing the input field to that required by practical object recognition problems.

A Genetic Algorithm That Exchanges Neighboring Centers for Fuzzy c-Means Clustering

ERIC Educational Resources Information Center

Chahine, Firas Safwan

2012-01-01

Clustering algorithms are widely used in pattern recognition and data mining applications. Due to their computational efficiency, partitional clustering algorithms are better suited for applications with large datasets than hierarchical clustering algorithms. K-means is among the most popular partitional clustering algorithm, but has a major…

Method and System for Object Recognition Search

NASA Technical Reports Server (NTRS)

Duong, Tuan A. (Inventor); Duong, Vu A. (Inventor); Stubberud, Allen R. (Inventor)

2012-01-01

A method for object recognition using shape and color features of the object to be recognized. An adaptive architecture is used to recognize and adapt the shape and color features for moving objects to enable object recognition.

Object memory effects on figure assignment: conscious object recognition is not necessary or sufficient.

PubMed

Peterson, M A; de Gelder, B; Rapcsak, S Z; Gerhardstein, P C; Bachoud-Lévi, A

2000-01-01

In three experiments we investigated whether conscious object recognition is necessary or sufficient for effects of object memories on figure assignment. In experiment 1, we examined a brain-damaged participant, AD, whose conscious object recognition is severely impaired. AD's responses about figure assignment do reveal effects from memories of object structure, indicating that conscious object recognition is not necessary for these effects, and identifying the figure-ground test employed here as a new implicit test of access to memories of object structure. In experiments 2 and 3, we tested a second brain-damaged participant, WG, for whom conscious object recognition was relatively spared. Nevertheless, effects from memories of object structure on figure assignment were not evident in WG's responses about figure assignment in experiment 2, indicating that conscious object recognition is not sufficient for effects of object memories on figure assignment. WG's performance sheds light on AD's performance, and has implications for the theoretical understanding of object memory effects on figure assignment.

Facial Emotion Recognition: A Survey and Real-World User Experiences in Mixed Reality

PubMed Central

Mehta, Dhwani; Siddiqui, Mohammad Faridul Haque

2018-01-01

Extensive possibilities of applications have made emotion recognition ineluctable and challenging in the field of computer science. The use of non-verbal cues such as gestures, body movement, and facial expressions convey the feeling and the feedback to the user. This discipline of Human–Computer Interaction places reliance on the algorithmic robustness and the sensitivity of the sensor to ameliorate the recognition. Sensors play a significant role in accurate detection by providing a very high-quality input, hence increasing the efficiency and the reliability of the system. Automatic recognition of human emotions would help in teaching social intelligence in the machines. This paper presents a brief study of the various approaches and the techniques of emotion recognition. The survey covers a succinct review of the databases that are considered as data sets for algorithms detecting the emotions by facial expressions. Later, mixed reality device Microsoft HoloLens (MHL) is introduced for observing emotion recognition in Augmented Reality (AR). A brief introduction of its sensors, their application in emotion recognition and some preliminary results of emotion recognition using MHL are presented. The paper then concludes by comparing results of emotion recognition by the MHL and a regular webcam. PMID:29389845

Facial Emotion Recognition: A Survey and Real-World User Experiences in Mixed Reality.

PubMed

Mehta, Dhwani; Siddiqui, Mohammad Faridul Haque; Javaid, Ahmad Y

2018-02-01

Extensive possibilities of applications have made emotion recognition ineluctable and challenging in the field of computer science. The use of non-verbal cues such as gestures, body movement, and facial expressions convey the feeling and the feedback to the user. This discipline of Human-Computer Interaction places reliance on the algorithmic robustness and the sensitivity of the sensor to ameliorate the recognition. Sensors play a significant role in accurate detection by providing a very high-quality input, hence increasing the efficiency and the reliability of the system. Automatic recognition of human emotions would help in teaching social intelligence in the machines. This paper presents a brief study of the various approaches and the techniques of emotion recognition. The survey covers a succinct review of the databases that are considered as data sets for algorithms detecting the emotions by facial expressions. Later, mixed reality device Microsoft HoloLens (MHL) is introduced for observing emotion recognition in Augmented Reality (AR). A brief introduction of its sensors, their application in emotion recognition and some preliminary results of emotion recognition using MHL are presented. The paper then concludes by comparing results of emotion recognition by the MHL and a regular webcam.

Fast neuromimetic object recognition using FPGA outperforms GPU implementations.

PubMed

Orchard, Garrick; Martin, Jacob G; Vogelstein, R Jacob; Etienne-Cummings, Ralph

2013-08-01

Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the most advanced computational vision approaches are unable to obtain performance equal to that of humans. This has led to the creation of many biologically inspired models of visual object recognition, among them the hierarchical model and X (HMAX) model. HMAX is traditionally known to achieve high accuracy in visual object recognition tasks at the expense of significant computational complexity. Increasing complexity, in turn, increases computation time, reducing the number of images that can be processed per unit time. In this paper we describe how the computationally intensive and biologically inspired HMAX model for visual object recognition can be modified for implementation on a commercial field-programmable aate Array, specifically the Xilinx Virtex 6 ML605 evaluation board with XC6VLX240T FPGA. We show that with minor modifications to the traditional HMAX model we can perform recognition on images of size 128 × 128 pixels at a rate of 190 images per second with a less than 1% loss in recognition accuracy in both binary and multiclass visual object recognition tasks.

A True-Color Sensor and Suitable Evaluation Algorithm for Plant Recognition

PubMed Central

Schmittmann, Oliver; Schulze Lammers, Peter

2017-01-01

Plant-specific herbicide application requires sensor systems for plant recognition and differentiation. A literature review reveals a lack of sensor systems capable of recognizing small weeds in early stages of development (in the two- or four-leaf stage) and crop plants, of making spraying decisions in real time and, in addition, are that are inexpensive and ready for practical use in sprayers. The system described in this work is based on free cascadable and programmable true-color sensors for real-time recognition and identification of individual weed and crop plants. The application of this type of sensor is suitable for municipal areas and farmland with and without crops to perform the site-specific application of herbicides. Initially, databases with reflection properties of plants, natural and artificial backgrounds were created. Crop and weed plants should be recognized by the use of mathematical algorithms and decision models based on these data. They include the characteristic color spectrum, as well as the reflectance characteristics of unvegetated areas and areas with organic material. The CIE-Lab color-space was chosen for color matching because it contains information not only about coloration (a- and b-channel), but also about luminance (L-channel), thus increasing accuracy. Four different decision making algorithms based on different parameters are explained: (i) color similarity (ΔE); (ii) color similarity split in ΔL, Δa and Δb; (iii) a virtual channel ‘d’ and (iv) statistical distribution of the differences of reflection backgrounds and plants. Afterwards, the detection success of the recognition system is described. Furthermore, the minimum weed/plant coverage of the measuring spot was calculated by a mathematical model. Plants with a size of 1–5% of the spot can be recognized, and weeds in the two-leaf stage can be identified with a measuring spot size of 5 cm. By choosing a decision model previously, the detection quality can be increased. Depending on the characteristics of the background, different models are suitable. Finally, the results of field trials on municipal areas (with models of plants), winter wheat fields (with artificial plants) and grassland (with dock) are shown. In each experimental variant, objects and weeds could be recognized. PMID:28786922

A True-Color Sensor and Suitable Evaluation Algorithm for Plant Recognition.

PubMed

Schmittmann, Oliver; Schulze Lammers, Peter

2017-08-08

Plant-specific herbicide application requires sensor systems for plant recognition and differentiation. A literature review reveals a lack of sensor systems capable of recognizing small weeds in early stages of development (in the two- or four-leaf stage) and crop plants, of making spraying decisions in real time and, in addition, are that are inexpensive and ready for practical use in sprayers. The system described in this work is based on free cascadable and programmable true-color sensors for real-time recognition and identification of individual weed and crop plants. The application of this type of sensor is suitable for municipal areas and farmland with and without crops to perform the site-specific application of herbicides. Initially, databases with reflection properties of plants, natural and artificial backgrounds were created. Crop and weed plants should be recognized by the use of mathematical algorithms and decision models based on these data. They include the characteristic color spectrum, as well as the reflectance characteristics of unvegetated areas and areas with organic material. The CIE-Lab color-space was chosen for color matching because it contains information not only about coloration (a- and b-channel), but also about luminance (L-channel), thus increasing accuracy. Four different decision making algorithms based on different parameters are explained: (i) color similarity (ΔE); (ii) color similarity split in ΔL, Δa and Δb; (iii) a virtual channel 'd' and (iv) statistical distribution of the differences of reflection backgrounds and plants. Afterwards, the detection success of the recognition system is described. Furthermore, the minimum weed/plant coverage of the measuring spot was calculated by a mathematical model. Plants with a size of 1-5% of the spot can be recognized, and weeds in the two-leaf stage can be identified with a measuring spot size of 5 cm. By choosing a decision model previously, the detection quality can be increased. Depending on the characteristics of the background, different models are suitable. Finally, the results of field trials on municipal areas (with models of plants), winter wheat fields (with artificial plants) and grassland (with dock) are shown. In each experimental variant, objects and weeds could be recognized.

Detection of circuit-board components with an adaptive multiclass correlation filter

NASA Astrophysics Data System (ADS)

Diaz-Ramirez, Victor H.; Kober, Vitaly

2008-08-01

A new method for reliable detection of circuit-board components is proposed. The method is based on an adaptive multiclass composite correlation filter. The filter is designed with the help of an iterative algorithm using complex synthetic discriminant functions. The impulse response of the filter contains information needed to localize and classify geometrically distorted circuit-board components belonging to different classes. Computer simulation results obtained with the proposed method are provided and compared with those of known multiclass correlation based techniques in terms of performance criteria for recognition and classification of objects.

Computer vision

NASA Technical Reports Server (NTRS)

Gennery, D.; Cunningham, R.; Saund, E.; High, J.; Ruoff, C.

1981-01-01

The field of computer vision is surveyed and assessed, key research issues are identified, and possibilities for a future vision system are discussed. The problems of descriptions of two and three dimensional worlds are discussed. The representation of such features as texture, edges, curves, and corners are detailed. Recognition methods are described in which cross correlation coefficients are maximized or numerical values for a set of features are measured. Object tracking is discussed in terms of the robust matching algorithms that must be devised. Stereo vision, camera control and calibration, and the hardware and systems architecture are discussed.

Feature Selection in Classification of Eye Movements Using Electrooculography for Activity Recognition

PubMed Central

Mala, S.; Latha, K.

2014-01-01

Activity recognition is needed in different requisition, for example, reconnaissance system, patient monitoring, and human-computer interfaces. Feature selection plays an important role in activity recognition, data mining, and machine learning. In selecting subset of features, an efficient evolutionary algorithm Differential Evolution (DE), a very efficient optimizer, is used for finding informative features from eye movements using electrooculography (EOG). Many researchers use EOG signals in human-computer interactions with various computational intelligence methods to analyze eye movements. The proposed system involves analysis of EOG signals using clearness based features, minimum redundancy maximum relevance features, and Differential Evolution based features. This work concentrates more on the feature selection algorithm based on DE in order to improve the classification for faultless activity recognition. PMID:25574185

Feature selection in classification of eye movements using electrooculography for activity recognition.

PubMed

Mala, S; Latha, K

2014-01-01

Activity recognition is needed in different requisition, for example, reconnaissance system, patient monitoring, and human-computer interfaces. Feature selection plays an important role in activity recognition, data mining, and machine learning. In selecting subset of features, an efficient evolutionary algorithm Differential Evolution (DE), a very efficient optimizer, is used for finding informative features from eye movements using electrooculography (EOG). Many researchers use EOG signals in human-computer interactions with various computational intelligence methods to analyze eye movements. The proposed system involves analysis of EOG signals using clearness based features, minimum redundancy maximum relevance features, and Differential Evolution based features. This work concentrates more on the feature selection algorithm based on DE in order to improve the classification for faultless activity recognition.

Influence of time and length size feature selections for human activity sequences recognition.

PubMed

Fang, Hongqing; Chen, Long; Srinivasan, Raghavendiran

2014-01-01

In this paper, Viterbi algorithm based on a hidden Markov model is applied to recognize activity sequences from observed sensors events. Alternative features selections of time feature values of sensors events and activity length size feature values are tested, respectively, and then the results of activity sequences recognition performances of Viterbi algorithm are evaluated. The results show that the selection of larger time feature values of sensor events and/or smaller activity length size feature values will generate relatively better results on the activity sequences recognition performances. © 2013 ISA Published by ISA All rights reserved.

Near-infrared face recognition utilizing open CV software

NASA Astrophysics Data System (ADS)

Sellami, Louiza; Ngo, Hau; Fowler, Chris J.; Kearney, Liam M.

2014-06-01

Commercially available hardware, freely available algorithms, and authors' developed software are synergized successfully to detect and recognize subjects in an environment without visible light. This project integrates three major components: an illumination device operating in near infrared (NIR) spectrum, a NIR capable camera and a software algorithm capable of performing image manipulation, facial detection and recognition. Focusing our efforts in the near infrared spectrum allows the low budget system to operate covertly while still allowing for accurate face recognition. In doing so a valuable function has been developed which presents potential benefits in future civilian and military security and surveillance operations.

Fusing face-verification algorithms and humans.

PubMed

O'Toole, Alice J; Abdi, Hervé; Jiang, Fang; Phillips, P Jonathon

2007-10-01

It has been demonstrated recently that state-of-the-art face-recognition algorithms can surpass human accuracy at matching faces over changes in illumination. The ranking of algorithms and humans by accuracy, however, does not provide information about whether algorithms and humans perform the task comparably or whether algorithms and humans can be fused to improve performance. In this paper, we fused humans and algorithms using partial least square regression (PLSR). In the first experiment, we applied PLSR to face-pair similarity scores generated by seven algorithms participating in the Face Recognition Grand Challenge. The PLSR produced an optimal weighting of the similarity scores, which we tested for generality with a jackknife procedure. Fusing the algorithms' similarity scores using the optimal weights produced a twofold reduction of error rate over the most accurate algorithm. Next, human-subject-generated similarity scores were added to the PLSR analysis. Fusing humans and algorithms increased the performance to near-perfect classification accuracy. These results are discussed in terms of maximizing face-verification accuracy with hybrid systems consisting of multiple algorithms and humans.

A Linked List-Based Algorithm for Blob Detection on Embedded Vision-Based Sensors

PubMed Central

Acevedo-Avila, Ricardo; Gonzalez-Mendoza, Miguel; Garcia-Garcia, Andres

2016-01-01

Blob detection is a common task in vision-based applications. Most existing algorithms are aimed at execution on general purpose computers; while very few can be adapted to the computing restrictions present in embedded platforms. This paper focuses on the design of an algorithm capable of real-time blob detection that minimizes system memory consumption. The proposed algorithm detects objects in one image scan; it is based on a linked-list data structure tree used to label blobs depending on their shape and node information. An example application showing the results of a blob detection co-processor has been built on a low-powered field programmable gate array hardware as a step towards developing a smart video surveillance system. The detection method is intended for general purpose application. As such, several test cases focused on character recognition are also examined. The results obtained present a fair trade-off between accuracy and memory requirements; and prove the validity of the proposed approach for real-time implementation on resource-constrained computing platforms. PMID:27240382

Hybrid wavefront sensing and image correction algorithm for imaging through turbulent media

NASA Astrophysics Data System (ADS)

Wu, Chensheng; Robertson Rzasa, John; Ko, Jonathan; Davis, Christopher C.

2017-09-01

It is well known that passive image correction of turbulence distortions often involves using geometry-dependent deconvolution algorithms. On the other hand, active imaging techniques using adaptive optic correction should use the distorted wavefront information for guidance. Our work shows that a hybrid hardware-software approach is possible to obtain accurate and highly detailed images through turbulent media. The processing algorithm also takes much fewer iteration steps in comparison with conventional image processing algorithms. In our proposed approach, a plenoptic sensor is used as a wavefront sensor to guide post-stage image correction on a high-definition zoomable camera. Conversely, we show that given the ground truth of the highly detailed image and the plenoptic imaging result, we can generate an accurate prediction of the blurred image on a traditional zoomable camera. Similarly, the ground truth combined with the blurred image from the zoomable camera would provide the wavefront conditions. In application, our hybrid approach can be used as an effective way to conduct object recognition in a turbulent environment where the target has been significantly distorted or is even unrecognizable.

The MITLL NIST LRE 2015 Language Recognition System

DTIC Science & Technology

2016-05-06

The MITLL NIST LRE 2015 Language Recognition System Pedro Torres-Carrasquillo, Najim Dehak*, Elizabeth Godoy, Douglas Reynolds, Fred Richardson...most recent MIT Lincoln Laboratory language recognition system developed for the NIST 2015 Language Recognition Evaluation (LRE). The submission...Task The National Institute of Science and Technology ( NIST ) has conducted formal evaluations of language detection algorithms since 1994. In

The MITLL NIST LRE 2015 Language Recognition system

DTIC Science & Technology

2016-02-05

The MITLL NIST LRE 2015 Language Recognition System Pedro Torres-Carrasquillo, Najim Dehak*, Elizabeth Godoy, Douglas Reynolds, Fred Richardson...recent MIT Lincoln Laboratory language recognition system developed for the NIST 2015 Language Recognition Evaluation (LRE). The submission features a...National Institute of Science and Technology ( NIST ) has conducted formal evaluations of language detection algorithms since 1994. In previous

Effectiveness of feature and classifier algorithms in character recognition systems

NASA Astrophysics Data System (ADS)

Wilson, Charles L.

1993-04-01

At the first Census Optical Character Recognition Systems Conference, NIST generated accuracy data for more than character recognition systems. Most systems were tested on the recognition of isolated digits and upper and lower case alphabetic characters. The recognition experiments were performed on sample sizes of 58,000 digits, and 12,000 upper and lower case alphabetic characters. The algorithms used by the 26 conference participants included rule-based methods, image-based methods, statistical methods, and neural networks. The neural network methods included Multi-Layer Perceptron's, Learned Vector Quantitization, Neocognitrons, and cascaded neural networks. In this paper 11 different systems are compared using correlations between the answers of different systems, comparing the decrease in error rate as a function of confidence of recognition, and comparing the writer dependence of recognition. This comparison shows that methods that used different algorithms for feature extraction and recognition performed with very high levels of correlation. This is true for neural network systems, hybrid systems, and statistically based systems, and leads to the conclusion that neural networks have not yet demonstrated a clear superiority to more conventional statistical methods. Comparison of these results with the models of Vapnick (for estimation problems), MacKay (for Bayesian statistical models), Moody (for effective parameterization), and Boltzmann models (for information content) demonstrate that as the limits of training data variance are approached, all classifier systems have similar statistical properties. The limiting condition can only be approached for sufficiently rich feature sets because the accuracy limit is controlled by the available information content of the training set, which must pass through the feature extraction process prior to classification.

Posture recognition associated with lifting of heavy objects using Kinect and Adaboost

NASA Astrophysics Data System (ADS)

Raut, Sayli; Navaneethakrishna, M.; Ramakrishnan, S.

2017-12-01

Lifting of heavy objects is the common task in the industries. Recent statistics from the Bureau of Labour indicate, back injuries account for one of every five injuries in the workplace. Eighty per cent of these injuries occur to the lower back and are associated with manual materials handling tasks. According to the Industrial ergonomic safety manual, Squatting is the correct posture for lifting a heavy object. In this work, an attempt has been made to monitor posture of the workers during squat and stoop using 3D motion capture and machine learning techniques. For this, Microsoft Kinect V2 is used for capturing the depth data. Further, Dynamic Time Warping and Euclidian distance algorithms are used for extraction of features. Ada-boost algorithm is used for classification of stoop and squat. The results show that the 3D image data is large and complex to analyze. The application of nonlinear and linear metrics captures the variation in the lifting pattern. Additionally, the features extracted from this metric resulted in a classification accuracy of 85% and 81% respectively. This framework may be put-upon to alert the workers in the industrial ergonomic environments.

Rotation-invariant features for multi-oriented text detection in natural images.

PubMed

Yao, Cong; Zhang, Xin; Bai, Xiang; Liu, Wenyu; Ma, Yi; Tu, Zhuowen

2013-01-01

Texts in natural scenes carry rich semantic information, which can be used to assist a wide range of applications, such as object recognition, image/video retrieval, mapping/navigation, and human computer interaction. However, most existing systems are designed to detect and recognize horizontal (or near-horizontal) texts. Due to the increasing popularity of mobile-computing devices and applications, detecting texts of varying orientations from natural images under less controlled conditions has become an important but challenging task. In this paper, we propose a new algorithm to detect texts of varying orientations. Our algorithm is based on a two-level classification scheme and two sets of features specially designed for capturing the intrinsic characteristics of texts. To better evaluate the proposed method and compare it with the competing algorithms, we generate a comprehensive dataset with various types of texts in diverse real-world scenes. We also propose a new evaluation protocol, which is more suitable for benchmarking algorithms for detecting texts in varying orientations. Experiments on benchmark datasets demonstrate that our system compares favorably with the state-of-the-art algorithms when handling horizontal texts and achieves significantly enhanced performance on variant texts in complex natural scenes.

Using human brain activity to guide machine learning.

PubMed

Fong, Ruth C; Scheirer, Walter J; Cox, David D

2018-03-29

Machine learning is a field of computer science that builds algorithms that learn. In many cases, machine learning algorithms are used to recreate a human ability like adding a caption to a photo, driving a car, or playing a game. While the human brain has long served as a source of inspiration for machine learning, little effort has been made to directly use data collected from working brains as a guide for machine learning algorithms. Here we demonstrate a new paradigm of "neurally-weighted" machine learning, which takes fMRI measurements of human brain activity from subjects viewing images, and infuses these data into the training process of an object recognition learning algorithm to make it more consistent with the human brain. After training, these neurally-weighted classifiers are able to classify images without requiring any additional neural data. We show that our neural-weighting approach can lead to large performance gains when used with traditional machine vision features, as well as to significant improvements with already high-performing convolutional neural network features. The effectiveness of this approach points to a path forward for a new class of hybrid machine learning algorithms which take both inspiration and direct constraints from neuronal data.

Real-time posture reconstruction for Microsoft Kinect.

PubMed

Shum, Hubert P H; Ho, Edmond S L; Jiang, Yang; Takagi, Shu

2013-10-01

The recent advancement of motion recognition using Microsoft Kinect stimulates many new ideas in motion capture and virtual reality applications. Utilizing a pattern recognition algorithm, Kinect can determine the positions of different body parts from the user. However, due to the use of a single-depth camera, recognition accuracy drops significantly when the parts are occluded. This hugely limits the usability of applications that involve interaction with external objects, such as sport training or exercising systems. The problem becomes more critical when Kinect incorrectly perceives body parts. This is because applications have limited information about the recognition correctness, and using those parts to synthesize body postures would result in serious visual artifacts. In this paper, we propose a new method to reconstruct valid movement from incomplete and noisy postures captured by Kinect. We first design a set of measurements that objectively evaluates the degree of reliability on each tracked body part. By incorporating the reliability estimation into a motion database query during run time, we obtain a set of similar postures that are kinematically valid. These postures are used to construct a latent space, which is known as the natural posture space in our system, with local principle component analysis. We finally apply frame-based optimization in the space to synthesize a new posture that closely resembles the true user posture while satisfying kinematic constraints. Experimental results show that our method can significantly improve the quality of the recognized posture under severely occluded environments, such as a person exercising with a basketball or moving in a small room.

Cross-modal face recognition using multi-matcher face scores

NASA Astrophysics Data System (ADS)

Zheng, Yufeng; Blasch, Erik

2015-05-01

The performance of face recognition can be improved using information fusion of multimodal images and/or multiple algorithms. When multimodal face images are available, cross-modal recognition is meaningful for security and surveillance applications. For example, a probe face is a thermal image (especially at nighttime), while only visible face images are available in the gallery database. Matching a thermal probe face onto the visible gallery faces requires crossmodal matching approaches. A few such studies were implemented in facial feature space with medium recognition performance. In this paper, we propose a cross-modal recognition approach, where multimodal faces are cross-matched in feature space and the recognition performance is enhanced with stereo fusion at image, feature and/or score level. In the proposed scenario, there are two cameras for stereo imaging, two face imagers (visible and thermal images) in each camera, and three recognition algorithms (circular Gaussian filter, face pattern byte, linear discriminant analysis). A score vector is formed with three cross-matched face scores from the aforementioned three algorithms. A classifier (e.g., k-nearest neighbor, support vector machine, binomial logical regression [BLR]) is trained then tested with the score vectors by using 10-fold cross validations. The proposed approach was validated with a multispectral stereo face dataset from 105 subjects. Our experiments show very promising results: ACR (accuracy rate) = 97.84%, FAR (false accept rate) = 0.84% when cross-matching the fused thermal faces onto the fused visible faces by using three face scores and the BLR classifier.

A focus of attention mechanism for gaze control within a framework for intelligent image analysis tools

NASA Astrophysics Data System (ADS)

Rodrigo, Ranga P.; Ranaweera, Kamal; Samarabandu, Jagath K.

2004-05-01

Focus of attention is often attributed to biological vision system where the entire field of view is first monitored and then the attention is focused to the object of interest. We propose using a similar approach for object recognition in a color image sequence. The intention is to locate an object based on a prior motive, concentrate on the detected object so that the imaging device can be guided toward it. We use the abilities of the intelligent image analysis framework developed in our laboratory to generate an algorithm dynamically to detect the particular type of object based on the user's object description. The proposed method uses color clustering along with segmentation. The segmented image with labeled regions is used to calculate the shape descriptor parameters. These and the color information are matched with the input description. Gaze is then controlled by issuing camera movement commands as appropriate. We present some preliminary results that demonstrate the success of this approach.

[Algorithm for the automated processing of rheosignals].

PubMed

Odinets, G S

1988-01-01

Algorithm for rheosignals recognition for a microprocessing device with a representation apparatus and with automated and manual cursor control was examined. The algorithm permits to automate rheosignals registrating and processing taking into account their changeability.

The development of newborn object recognition in fast and slow visual worlds

PubMed Central

Wood, Justin N.; Wood, Samantha M. W.

2016-01-01

Object recognition is central to perception and cognition. Yet relatively little is known about the environmental factors that cause invariant object recognition to emerge in the newborn brain. Is this ability a hardwired property of vision? Or does the development of invariant object recognition require experience with a particular kind of visual environment? Here, we used a high-throughput controlled-rearing method to examine whether newborn chicks (Gallus gallus) require visual experience with slowly changing objects to develop invariant object recognition abilities. When newborn chicks were raised with a slowly rotating virtual object, the chicks built invariant object representations that generalized across novel viewpoints and rotation speeds. In contrast, when newborn chicks were raised with a virtual object that rotated more quickly, the chicks built viewpoint-specific object representations that failed to generalize to novel viewpoints and rotation speeds. Moreover, there was a direct relationship between the speed of the object and the amount of invariance in the chick's object representation. Thus, visual experience with slowly changing objects plays a critical role in the development of invariant object recognition. These results indicate that invariant object recognition is not a hardwired property of vision, but is learned rapidly when newborns encounter a slowly changing visual world. PMID:27097925

Viewpoint dependence in the recognition of non-elongated familiar objects: testing the effects of symmetry, front-back axis, and familiarity.

PubMed

Niimi, Ryosuke; Yokosawa, Kazuhiko

2009-01-01

Visual recognition of three-dimensional (3-D) objects is relatively impaired for some particular views, called accidental views. For most familiar objects, the front and top views are considered to be accidental views. Previous studies have shown that foreshortening of the axes of elongation of objects in these views impairs recognition, but the influence of other possible factors is largely unknown. Using familiar objects without a salient axis of elongation, we found that a foreshortened symmetry plane of the object and low familiarity of the viewpoint accounted for the relatively worse recognition for front views and top views, independently of the effect of a foreshortened axis of elongation. We found no evidence that foreshortened front-back axes impaired recognition in front views. These results suggest that the viewpoint dependence of familiar object recognition is not a unitary phenomenon. The possible role of symmetry (either 2-D or 3-D) in familiar object recognition is also discussed.

A dynamical pattern recognition model of gamma activity in auditory cortex

PubMed Central

Zavaglia, M.; Canolty, R.T.; Schofield, T.M.; Leff, A.P.; Ursino, M.; Knight, R.T.; Penny, W.D.

2012-01-01

This paper describes a dynamical process which serves both as a model of temporal pattern recognition in the brain and as a forward model of neuroimaging data. This process is considered at two separate levels of analysis: the algorithmic and implementation levels. At an algorithmic level, recognition is based on the use of Occurrence Time features. Using a speech digit database we show that for noisy recognition environments, these features rival standard cepstral coefficient features. At an implementation level, the model is defined using a Weakly Coupled Oscillator (WCO) framework and uses a transient synchronization mechanism to signal a recognition event. In a second set of experiments, we use the strength of the synchronization event to predict the high gamma (75–150 Hz) activity produced by the brain in response to word versus non-word stimuli. Quantitative model fits allow us to make inferences about parameters governing pattern recognition dynamics in the brain. PMID:22327049

Structural model constructing for optical handwritten character recognition

NASA Astrophysics Data System (ADS)

Khaustov, P. A.; Spitsyn, V. G.; Maksimova, E. I.

2017-02-01

The article is devoted to the development of the algorithms for optical handwritten character recognition based on the structural models constructing. The main advantage of these algorithms is the low requirement regarding the number of reference images. The one-pass approach to a thinning of the binary character representation has been proposed. This approach is based on the joint use of Zhang-Suen and Wu-Tsai algorithms. The effectiveness of the proposed approach is confirmed by the results of the experiments. The article includes the detailed description of the structural model constructing algorithm’s steps. The proposed algorithm has been implemented in character processing application and has been approved on MNIST handwriting characters database. Algorithms that could be used in case of limited reference images number were used for the comparison.

Evaluation schemes for video and image anomaly detection algorithms

NASA Astrophysics Data System (ADS)

Parameswaran, Shibin; Harguess, Josh; Barngrover, Christopher; Shafer, Scott; Reese, Michael

2016-05-01

Video anomaly detection is a critical research area in computer vision. It is a natural first step before applying object recognition algorithms. There are many algorithms that detect anomalies (outliers) in videos and images that have been introduced in recent years. However, these algorithms behave and perform differently based on differences in domains and tasks to which they are subjected. In order to better understand the strengths and weaknesses of outlier algorithms and their applicability in a particular domain/task of interest, it is important to measure and quantify their performance using appropriate evaluation metrics. There are many evaluation metrics that have been used in the literature such as precision curves, precision-recall curves, and receiver operating characteristic (ROC) curves. In order to construct these different metrics, it is also important to choose an appropriate evaluation scheme that decides when a proposed detection is considered a true or a false detection. Choosing the right evaluation metric and the right scheme is very critical since the choice can introduce positive or negative bias in the measuring criterion and may favor (or work against) a particular algorithm or task. In this paper, we review evaluation metrics and popular evaluation schemes that are used to measure the performance of anomaly detection algorithms on videos and imagery with one or more anomalies. We analyze the biases introduced by these by measuring the performance of an existing anomaly detection algorithm.

Unsupervised learning in persistent sensing for target recognition by wireless ad hoc networks of ground-based sensors

NASA Astrophysics Data System (ADS)

Hortos, William S.

2008-04-01

In previous work by the author, effective persistent and pervasive sensing for recognition and tracking of battlefield targets were seen to be achieved, using intelligent algorithms implemented by distributed mobile agents over a composite system of unmanned aerial vehicles (UAVs) for persistence and a wireless network of unattended ground sensors for pervasive coverage of the mission environment. While simulated performance results for the supervised algorithms of the composite system are shown to provide satisfactory target recognition over relatively brief periods of system operation, this performance can degrade by as much as 50% as target dynamics in the environment evolve beyond the period of system operation in which the training data are representative. To overcome this limitation, this paper applies the distributed approach using mobile agents to the network of ground-based wireless sensors alone, without the UAV subsystem, to provide persistent as well as pervasive sensing for target recognition and tracking. The supervised algorithms used in the earlier work are supplanted by unsupervised routines, including competitive-learning neural networks (CLNNs) and new versions of support vector machines (SVMs) for characterization of an unknown target environment. To capture the same physical phenomena from battlefield targets as the composite system, the suite of ground-based sensors can be expanded to include imaging and video capabilities. The spatial density of deployed sensor nodes is increased to allow more precise ground-based location and tracking of detected targets by active nodes. The "swarm" mobile agents enabling WSN intelligence are organized in a three processing stages: detection, recognition and sustained tracking of ground targets. Features formed from the compressed sensor data are down-selected according to an information-theoretic algorithm that reduces redundancy within the feature set, reducing the dimension of samples used in the target recognition and tracking routines. Target tracking is based on simplified versions of Kalman filtration. Accuracy of recognition and tracking of implemented versions of the proposed suite of unsupervised algorithms is somewhat degraded from the ideal. Target recognition and tracking by supervised routines and by unsupervised SVM and CLNN routines in the ground-based WSN is evaluated in simulations using published system values and sensor data from vehicular targets in ground-surveillance scenarios. Results are compared with previously published performance for the system of the ground-based sensor network (GSN) and UAV swarm.

Con-Text: Text Detection for Fine-grained Object Classification.

PubMed

Karaoglu, Sezer; Tao, Ran; van Gemert, Jan C; Gevers, Theo

2017-05-24

This work focuses on fine-grained object classification using recognized scene text in natural images. While the state-of-the-art relies on visual cues only, this paper is the first work which proposes to combine textual and visual cues. Another novelty is the textual cue extraction. Unlike the state-of-the-art text detection methods, we focus more on the background instead of text regions. Once text regions are detected, they are further processed by two methods to perform text recognition i.e. ABBYY commercial OCR engine and a state-of-the-art character recognition algorithm. Then, to perform textual cue encoding, bi- and trigrams are formed between the recognized characters by considering the proposed spatial pairwise constraints. Finally, extracted visual and textual cues are combined for fine-grained classification. The proposed method is validated on four publicly available datasets: ICDAR03, ICDAR13, Con-Text and Flickr-logo. We improve the state-of-the-art end-to-end character recognition by a large margin of 15% on ICDAR03. We show that textual cues are useful in addition to visual cues for fine-grained classification. We show that textual cues are also useful for logo retrieval. Adding textual cues outperforms visual- and textual-only in fine-grained classification (70.7% to 60.3%) and logo retrieval (57.4% to 54.8%).

Subject independent facial expression recognition with robust face detection using a convolutional neural network.

PubMed

Matsugu, Masakazu; Mori, Katsuhiko; Mitari, Yusuke; Kaneda, Yuji

2003-01-01

Reliable detection of ordinary facial expressions (e.g. smile) despite the variability among individuals as well as face appearance is an important step toward the realization of perceptual user interface with autonomous perception of persons. We describe a rule-based algorithm for robust facial expression recognition combined with robust face detection using a convolutional neural network. In this study, we address the problem of subject independence as well as translation, rotation, and scale invariance in the recognition of facial expression. The result shows reliable detection of smiles with recognition rate of 97.6% for 5600 still images of more than 10 subjects. The proposed algorithm demonstrated the ability to discriminate smiling from talking based on the saliency score obtained from voting visual cues. To the best of our knowledge, it is the first facial expression recognition model with the property of subject independence combined with robustness to variability in facial appearance.

Possibilistic clustering for shape recognition

NASA Technical Reports Server (NTRS)

Keller, James M.; Krishnapuram, Raghu

1993-01-01

Clustering methods have been used extensively in computer vision and pattern recognition. Fuzzy clustering has been shown to be advantageous over crisp (or traditional) clustering in that total commitment of a vector to a given class is not required at each iteration. Recently fuzzy clustering methods have shown spectacular ability to detect not only hypervolume clusters, but also clusters which are actually 'thin shells', i.e., curves and surfaces. Most analytic fuzzy clustering approaches are derived from Bezdek's Fuzzy C-Means (FCM) algorithm. The FCM uses the probabilistic constraint that the memberships of a data point across classes sum to one. This constraint was used to generate the membership update equations for an iterative algorithm. Unfortunately, the memberships resulting from FCM and its derivatives do not correspond to the intuitive concept of degree of belonging, and moreover, the algorithms have considerable trouble in noisy environments. Recently, the clustering problem was cast into the framework of possibility theory. Our approach was radically different from the existing clustering methods in that the resulting partition of the data can be interpreted as a possibilistic partition, and the membership values may be interpreted as degrees of possibility of the points belonging to the classes. An appropriate objective function whose minimum will characterize a good possibilistic partition of the data was constructed, and the membership and prototype update equations from necessary conditions for minimization of our criterion function were derived. The ability of this approach to detect linear and quartic curves in the presence of considerable noise is shown.

Possibilistic clustering for shape recognition

NASA Technical Reports Server (NTRS)

Keller, James M.; Krishnapuram, Raghu

1992-01-01

Clustering methods have been used extensively in computer vision and pattern recognition. Fuzzy clustering has been shown to be advantageous over crisp (or traditional) clustering in that total commitment of a vector to a given class is not required at each iteration. Recently fuzzy clustering methods have shown spectacular ability to detect not only hypervolume clusters, but also clusters which are actually 'thin shells', i.e., curves and surfaces. Most analytic fuzzy clustering approaches are derived from Bezdek's Fuzzy C-Means (FCM) algorithm. The FCM uses the probabilistic constraint that the memberships of a data point across classes sum to one. This constraint was used to generate the membership update equations for an iterative algorithm. Unfortunately, the memberships resulting from FCM and its derivatives do not correspond to the intuitive concept of degree of belonging, and moreover, the algorithms have considerable trouble in noisy environments. Recently, we cast the clustering problem into the framework of possibility theory. Our approach was radically different from the existing clustering methods in that the resulting partition of the data can be interpreted as a possibilistic partition, and the membership values may be interpreted as degrees of possibility of the points belonging to the classes. We constructed an appropriate objective function whose minimum will characterize a good possibilistic partition of the data, and we derived the membership and prototype update equations from necessary conditions for minimization of our criterion function. In this paper, we show the ability of this approach to detect linear and quartic curves in the presence of considerable noise.

Study of robot landmark recognition with complex background

NASA Astrophysics Data System (ADS)

Huang, Yuqing; Yang, Jia

2007-12-01

It's of great importance for assisting robot in path planning, position navigating and task performing by perceiving and recognising environment characteristic. To solve the problem of monocular-vision-oriented landmark recognition for mobile intelligent robot marching with complex background, a kind of nested region growing algorithm which fused with transcendental color information and based on current maximum convergence center is proposed, allowing invariance localization to changes in position, scale, rotation, jitters and weather conditions. Firstly, a novel experiment threshold based on RGB vision model is used for the first image segmentation, which allowing some objects and partial scenes with similar color to landmarks also are detected with landmarks together. Secondly, with current maximum convergence center on segmented image as each growing seed point, the above region growing algorithm accordingly starts to establish several Regions of Interest (ROI) orderly. According to shape characteristics, a quick and effectual contour analysis based on primitive element is applied in deciding whether current ROI could be reserved or deleted after each region growing, then each ROI is judged initially and positioned. When the position information as feedback is conveyed to the gray image, the whole landmarks are extracted accurately with the second segmentation on the local image that exclusive to landmark area. Finally, landmarks are recognised by Hopfield neural network. Results issued from experiments on a great number of images with both campus and urban district as background show the effectiveness of the proposed algorithm.

Recognition of pornographic web pages by classifying texts and images.

PubMed

Hu, Weiming; Wu, Ou; Chen, Zhouyao; Fu, Zhouyu; Maybank, Steve

2007-06-01

With the rapid development of the World Wide Web, people benefit more and more from the sharing of information. However, Web pages with obscene, harmful, or illegal content can be easily accessed. It is important to recognize such unsuitable, offensive, or pornographic Web pages. In this paper, a novel framework for recognizing pornographic Web pages is described. A C4.5 decision tree is used to divide Web pages, according to content representations, into continuous text pages, discrete text pages, and image pages. These three categories of Web pages are handled, respectively, by a continuous text classifier, a discrete text classifier, and an algorithm that fuses the results from the image classifier and the discrete text classifier. In the continuous text classifier, statistical and semantic features are used to recognize pornographic texts. In the discrete text classifier, the naive Bayes rule is used to calculate the probability that a discrete text is pornographic. In the image classifier, the object's contour-based features are extracted to recognize pornographic images. In the text and image fusion algorithm, the Bayes theory is used to combine the recognition results from images and texts. Experimental results demonstrate that the continuous text classifier outperforms the traditional keyword-statistics-based classifier, the contour-based image classifier outperforms the traditional skin-region-based image classifier, the results obtained by our fusion algorithm outperform those by either of the individual classifiers, and our framework can be adapted to different categories of Web pages.

Software for Partly Automated Recognition of Targets

NASA Technical Reports Server (NTRS)

Opitz, David; Blundell, Stuart; Bain, William; Morris, Matthew; Carlson, Ian; Mangrich, Mark; Selinsky, T.

2002-01-01

The Feature Analyst is a computer program for assisted (partially automated) recognition of targets in images. This program was developed to accelerate the processing of high-resolution satellite image data for incorporation into geographic information systems (GIS). This program creates an advanced user interface that embeds proprietary machine-learning algorithms in commercial image-processing and GIS software. A human analyst provides samples of target features from multiple sets of data, then the software develops a data-fusion model that automatically extracts the remaining features from selected sets of data. The program thus leverages the natural ability of humans to recognize objects in complex scenes, without requiring the user to explain the human visual recognition process by means of lengthy software. Two major subprograms are the reactive agent and the thinking agent. The reactive agent strives to quickly learn the user's tendencies while the user is selecting targets and to increase the user's productivity by immediately suggesting the next set of pixels that the user may wish to select. The thinking agent utilizes all available resources, taking as much time as needed, to produce the most accurate autonomous feature-extraction model possible.

DORSAL HIPPOCAMPAL PROGESTERONE INFUSIONS ENHANCE OBJECT RECOGNITION IN YOUNG FEMALE MICE

PubMed Central

Orr, Patrick T.; Lewis, Michael C.; Frick, Karyn M.

2009-01-01

The effects of progesterone on memory are not nearly as well studied as the effects of estrogens. Although progesterone can reportedly enhance spatial and/or object recognition in female rodents when given immediately after training, previous studies have injected progesterone systemically, and therefore, the brain regions mediating this enhancement are not clear. As such, this study was designed to determine the role of the dorsal hippocampus in mediating the beneficial effect of progesterone on object recognition. Young ovariectomized C57BL/6 mice were trained in a hippocampal-dependent object recognition task utilizing two identical objects, and then immediately or 2 hrs afterwards, received bilateral dorsal hippocampal infusions of vehicle or 0.01, 0.1, or 1.0 μg/μl water-soluble progesterone. Forty-eight hours later, object recognition memory was tested using a previously explored object and a novel object. Relative to the vehicle group, memory for the familiar object was enhanced in all groups receiving immediate infusions of progesterone. Progesterone infusion delayed 2 hrs after training did not affect object recognition. These data suggest that the dorsal hippocampus may play a critical role in progesterone-induced enhancement of object recognition. PMID:19477194

Automatic updating and 3D modeling of airport information from high resolution images using GIS and LIDAR data

NASA Astrophysics Data System (ADS)

Lv, Zheng; Sui, Haigang; Zhang, Xilin; Huang, Xianfeng

2007-11-01

As one of the most important geo-spatial objects and military establishment, airport is always a key target in fields of transportation and military affairs. Therefore, automatic recognition and extraction of airport from remote sensing images is very important and urgent for updating of civil aviation and military application. In this paper, a new multi-source data fusion approach on automatic airport information extraction, updating and 3D modeling is addressed. Corresponding key technologies including feature extraction of airport information based on a modified Ostu algorithm, automatic change detection based on new parallel lines-based buffer detection algorithm, 3D modeling based on gradual elimination of non-building points algorithm, 3D change detecting between old airport model and LIDAR data, typical CAD models imported and so on are discussed in detail. At last, based on these technologies, we develop a prototype system and the results show our method can achieve good effects.

Interactive object recognition assistance: an approach to recognition starting from target objects

NASA Astrophysics Data System (ADS)

Geisler, Juergen; Littfass, Michael

1999-07-01

Recognition of target objects in remotely sensed imagery required detailed knowledge about the target object domain as well as about mapping properties of the sensing system. The art of object recognition is to combine both worlds appropriately and to provide models of target appearance with respect to sensor characteristics. Common approaches to support interactive object recognition are either driven from the sensor point of view and address the problem of displaying images in a manner adequate to the sensing system. Or they focus on target objects and provide exhaustive encyclopedic information about this domain. Our paper discusses an approach to assist interactive object recognition based on knowledge about target objects and taking into account the significance of object features with respect to characteristics of the sensed imagery, e.g. spatial and spectral resolution. An `interactive recognition assistant' takes the image analyst through the interpretation process by indicating step-by-step the respectively most significant features of objects in an actual set of candidates. The significance of object features is expressed by pregenerated trees of significance, and by the dynamic computation of decision relevance for every feature at each step of the recognition process. In the context of this approach we discuss the question of modeling and storing the multisensorial/multispectral appearances of target objects and object classes as well as the problem of an adequate dynamic human-machine-interface that takes into account various mental models of human image interpretation.

A Joint Gaussian Process Model for Active Visual Recognition with Expertise Estimation in Crowdsourcing

PubMed Central

Long, Chengjiang; Hua, Gang; Kapoor, Ashish

2015-01-01

We present a noise resilient probabilistic model for active learning of a Gaussian process classifier from crowds, i.e., a set of noisy labelers. It explicitly models both the overall label noise and the expertise level of each individual labeler with two levels of flip models. Expectation propagation is adopted for efficient approximate Bayesian inference of our probabilistic model for classification, based on which, a generalized EM algorithm is derived to estimate both the global label noise and the expertise of each individual labeler. The probabilistic nature of our model immediately allows the adoption of the prediction entropy for active selection of data samples to be labeled, and active selection of high quality labelers based on their estimated expertise to label the data. We apply the proposed model for four visual recognition tasks, i.e., object category recognition, multi-modal activity recognition, gender recognition, and fine-grained classification, on four datasets with real crowd-sourced labels from the Amazon Mechanical Turk. The experiments clearly demonstrate the efficacy of the proposed model. In addition, we extend the proposed model with the Predictive Active Set Selection Method to speed up the active learning system, whose efficacy is verified by conducting experiments on the first three datasets. The results show our extended model can not only preserve a higher accuracy, but also achieve a higher efficiency. PMID:26924892

Bottlenose dolphins perceive object features through echolocation.

PubMed

Harley, Heidi E; Putman, Erika A; Roitblat, Herbert L

2003-08-07

How organisms (including people) recognize distant objects is a fundamental question. The correspondence between object characteristics (distal stimuli), like visual shape, and sensory characteristics (proximal stimuli), like retinal projection, is ambiguous. The view that sensory systems are 'designed' to 'pick up' ecologically useful information is vague about how such mechanisms might work. In echolocating dolphins, which are studied as models for object recognition sonar systems, the correspondence between echo characteristics and object characteristics is less clear. Many cognitive scientists assume that object characteristics are extracted from proximal stimuli, but evidence for this remains ambiguous. For example, a dolphin may store 'sound templates' in its brain and identify whole objects by listening for a particular sound. Alternatively, a dolphin's brain may contain algorithms, derived through natural endowments or experience or both, which allow it to identify object characteristics based on sounds. The standard method used to address this question in many species is indirect and has led to equivocal results with dolphins. Here we outline an appropriate method and test it to show that dolphins extract object characteristics directly from echoes.

The Maximum Likelihood Estimation of Signature Transformation /MLEST/ algorithm. [for affine transformation of crop inventory data

NASA Technical Reports Server (NTRS)

Thadani, S. G.

1977-01-01

The Maximum Likelihood Estimation of Signature Transformation (MLEST) algorithm is used to obtain maximum likelihood estimates (MLE) of affine transformation. The algorithm has been evaluated for three sets of data: simulated (training and recognition segment pairs), consecutive-day (data gathered from Landsat images), and geographical-extension (large-area crop inventory experiment) data sets. For each set, MLEST signature extension runs were made to determine MLE values and the affine-transformed training segment signatures were used to classify the recognition segments. The classification results were used to estimate wheat proportions at 0 and 1% threshold values.

Tracking Small Artists

NASA Astrophysics Data System (ADS)

Russell, James C.; Klette, Reinhard; Chen, Chia-Yen

Tracks of small animals are important in environmental surveillance, where pattern recognition algorithms allow species identification of the individuals creating tracks. These individuals can also be seen as artists, presented in their natural environments with a canvas upon which they can make prints. We present tracks of small mammals and reptiles which have been collected for identification purposes, and re-interpret them from an esthetic point of view. We re-classify these tracks not by their geometric qualities as pattern recognition algorithms would, but through interpreting the 'artist', their brush strokes and intensity. We describe the algorithms used to enhance and present the work of the 'artists'.

False alarm reduction by the And-ing of multiple multivariate Gaussian classifiers

NASA Astrophysics Data System (ADS)

Dobeck, Gerald J.; Cobb, J. Tory

2003-09-01

The high-resolution sonar is one of the principal sensors used by the Navy to detect and classify sea mines in minehunting operations. For such sonar systems, substantial effort has been devoted to the development of automated detection and classification (D/C) algorithms. These have been spurred by several factors including (1) aids for operators to reduce work overload, (2) more optimal use of all available data, and (3) the introduction of unmanned minehunting systems. The environments where sea mines are typically laid (harbor areas, shipping lanes, and the littorals) give rise to many false alarms caused by natural, biologic, and man-made clutter. The objective of the automated D/C algorithms is to eliminate most of these false alarms while still maintaining a very high probability of mine detection and classification (PdPc). In recent years, the benefits of fusing the outputs of multiple D/C algorithms have been studied. We refer to this as Algorithm Fusion. The results have been remarkable, including reliable robustness to new environments. This paper describes a method for training several multivariate Gaussian classifiers such that their And-ing dramatically reduces false alarms while maintaining a high probability of classification. This training approach is referred to as the Focused- Training method. This work extends our 2001-2002 work where the Focused-Training method was used with three other types of classifiers: the Attractor-based K-Nearest Neighbor Neural Network (a type of radial-basis, probabilistic neural network), the Optimal Discrimination Filter Classifier (based linear discrimination theory), and the Quadratic Penalty Function Support Vector Machine (QPFSVM). Although our experience has been gained in the area of sea mine detection and classification, the principles described herein are general and can be applied to a wide range of pattern recognition and automatic target recognition (ATR) problems.

Regional Principal Color Based Saliency Detection

PubMed Central

Lou, Jing; Ren, Mingwu; Wang, Huan

2014-01-01

Saliency detection is widely used in many visual applications like image segmentation, object recognition and classification. In this paper, we will introduce a new method to detect salient objects in natural images. The approach is based on a regional principal color contrast modal, which incorporates low-level and medium-level visual cues. The method allows a simple computation of color features and two categories of spatial relationships to a saliency map, achieving higher F-measure rates. At the same time, we present an interpolation approach to evaluate resulting curves, and analyze parameters selection. Our method enables the effective computation of arbitrary resolution images. Experimental results on a saliency database show that our approach produces high quality saliency maps and performs favorably against ten saliency detection algorithms. PMID:25379960

Infant Visual Attention and Object Recognition

PubMed Central

Reynolds, Greg D.

2015-01-01

This paper explores the role visual attention plays in the recognition of objects in infancy. Research and theory on the development of infant attention and recognition memory are reviewed in three major sections. The first section reviews some of the major findings and theory emerging from a rich tradition of behavioral research utilizing preferential looking tasks to examine visual attention and recognition memory in infancy. The second section examines research utilizing neural measures of attention and object recognition in infancy as well as research on brain-behavior relations in the early development of attention and recognition memory. The third section addresses potential areas of the brain involved in infant object recognition and visual attention. An integrated synthesis of some of the existing models of the development of visual attention is presented which may account for the observed changes in behavioral and neural measures of visual attention and object recognition that occur across infancy. PMID:25596333

Three-dimensional fingerprint recognition by using convolution neural network

NASA Astrophysics Data System (ADS)

Tian, Qianyu; Gao, Nan; Zhang, Zonghua

2018-01-01

With the development of science and technology and the improvement of social information, fingerprint recognition technology has become a hot research direction and been widely applied in many actual fields because of its feasibility and reliability. The traditional two-dimensional (2D) fingerprint recognition method relies on matching feature points. This method is not only time-consuming, but also lost three-dimensional (3D) information of fingerprint, with the fingerprint rotation, scaling, damage and other issues, a serious decline in robustness. To solve these problems, 3D fingerprint has been used to recognize human being. Because it is a new research field, there are still lots of challenging problems in 3D fingerprint recognition. This paper presents a new 3D fingerprint recognition method by using a convolution neural network (CNN). By combining 2D fingerprint and fingerprint depth map into CNN, and then through another CNN feature fusion, the characteristics of the fusion complete 3D fingerprint recognition after classification. This method not only can preserve 3D information of fingerprints, but also solves the problem of CNN input. Moreover, the recognition process is simpler than traditional feature point matching algorithm. 3D fingerprint recognition rate by using CNN is compared with other fingerprint recognition algorithms. The experimental results show that the proposed 3D fingerprint recognition method has good recognition rate and robustness.

Atmospheric turbulence and sensor system effects on biometric algorithm performance

NASA Astrophysics Data System (ADS)

Espinola, Richard L.; Leonard, Kevin R.; Byrd, Kenneth A.; Potvin, Guy

2015-05-01

Biometric technologies composed of electro-optical/infrared (EO/IR) sensor systems and advanced matching algorithms are being used in various force protection/security and tactical surveillance applications. To date, most of these sensor systems have been widely used in controlled conditions with varying success (e.g., short range, uniform illumination, cooperative subjects). However the limiting conditions of such systems have yet to be fully studied for long range applications and degraded imaging environments. Biometric technologies used for long range applications will invariably suffer from the effects of atmospheric turbulence degradation. Atmospheric turbulence causes blur, distortion and intensity fluctuations that can severely degrade image quality of electro-optic and thermal imaging systems and, for the case of biometrics technology, translate to poor matching algorithm performance. In this paper, we evaluate the effects of atmospheric turbulence and sensor resolution on biometric matching algorithm performance. We use a subset of the Facial Recognition Technology (FERET) database and a commercial algorithm to analyze facial recognition performance on turbulence degraded facial images. The goal of this work is to understand the feasibility of long-range facial recognition in degraded imaging conditions, and the utility of camera parameter trade studies to enable the design of the next generation biometrics sensor systems.

Real-time skeleton tracking for embedded systems

NASA Astrophysics Data System (ADS)

Coleca, Foti; Klement, Sascha; Martinetz, Thomas; Barth, Erhardt

2013-03-01

Touch-free gesture technology is beginning to become more popular with consumers and may have a significant future impact on interfaces for digital photography. However, almost every commercial software framework for gesture and pose detection is aimed at either desktop PCs or high-powered GPUs, making mobile implementations for gesture recognition an attractive area for research and development. In this paper we present an algorithm for hand skeleton tracking and gesture recognition that runs on an ARM-based platform (Pandaboard ES, OMAP 4460 architecture). The algorithm uses self-organizing maps to fit a given topology (skeleton) into a 3D point cloud. This is a novel way of approaching the problem of pose recognition as it does not employ complex optimization techniques or data-based learning. After an initial background segmentation step, the algorithm is ran in parallel with heuristics, which detect and correct artifacts arising from insufficient or erroneous input data. We then optimize the algorithm for the ARM platform using fixed-point computation and the NEON SIMD architecture the OMAP4460 provides. We tested the algorithm with two different depth-sensing devices (Microsoft Kinect, PMD Camboard). For both input devices we were able to accurately track the skeleton at the native framerate of the cameras.

Sensor-Aware Recognition and Tracking for Wide-Area Augmented Reality on Mobile Phones

PubMed Central

Chen, Jing; Cao, Ruochen; Wang, Yongtian

2015-01-01

Wide-area registration in outdoor environments on mobile phones is a challenging task in mobile augmented reality fields. We present a sensor-aware large-scale outdoor augmented reality system for recognition and tracking on mobile phones. GPS and gravity information is used to improve the VLAD performance for recognition. A kind of sensor-aware VLAD algorithm, which is self-adaptive to different scale scenes, is utilized to recognize complex scenes. Considering vision-based registration algorithms are too fragile and tend to drift, data coming from inertial sensors and vision are fused together by an extended Kalman filter (EKF) to achieve considerable improvements in tracking stability and robustness. Experimental results show that our method greatly enhances the recognition rate and eliminates the tracking jitters. PMID:26690439

Sensor-Aware Recognition and Tracking for Wide-Area Augmented Reality on Mobile Phones.

PubMed

Chen, Jing; Cao, Ruochen; Wang, Yongtian

2015-12-10

Wide-area registration in outdoor environments on mobile phones is a challenging task in mobile augmented reality fields. We present a sensor-aware large-scale outdoor augmented reality system for recognition and tracking on mobile phones. GPS and gravity information is used to improve the VLAD performance for recognition. A kind of sensor-aware VLAD algorithm, which is self-adaptive to different scale scenes, is utilized to recognize complex scenes. Considering vision-based registration algorithms are too fragile and tend to drift, data coming from inertial sensors and vision are fused together by an extended Kalman filter (EKF) to achieve considerable improvements in tracking stability and robustness. Experimental results show that our method greatly enhances the recognition rate and eliminates the tracking jitters.

Recognition-induced forgetting is not due to category-based set size.

PubMed

Maxcey, Ashleigh M

2016-01-01

What are the consequences of accessing a visual long-term memory representation? Previous work has shown that accessing a long-term memory representation via retrieval improves memory for the targeted item and hurts memory for related items, a phenomenon called retrieval-induced forgetting. Recently we found a similar forgetting phenomenon with recognition of visual objects. Recognition-induced forgetting occurs when practice recognizing an object during a two-alternative forced-choice task, from a group of objects learned at the same time, leads to worse memory for objects from that group that were not practiced. An alternative explanation of this effect is that category-based set size is inducing forgetting, not recognition practice as claimed by some researchers. This alternative explanation is possible because during recognition practice subjects make old-new judgments in a two-alternative forced-choice task, and are thus exposed to more objects from practiced categories, potentially inducing forgetting due to set-size. Herein I pitted the category-based set size hypothesis against the recognition-induced forgetting hypothesis. To this end, I parametrically manipulated the amount of practice objects received in the recognition-induced forgetting paradigm. If forgetting is due to category-based set size, then the magnitude of forgetting of related objects will increase as the number of practice trials increases. If forgetting is recognition induced, the set size of exemplars from any given category should not be predictive of memory for practiced objects. Consistent with this latter hypothesis, additional practice systematically improved memory for practiced objects, but did not systematically affect forgetting of related objects. These results firmly establish that recognition practice induces forgetting of related memories. Future directions and important real-world applications of using recognition to access our visual memories of previously encountered objects are discussed.

Mechanisms of object recognition: what we have learned from pigeons

PubMed Central

Soto, Fabian A.; Wasserman, Edward A.

2014-01-01

Behavioral studies of object recognition in pigeons have been conducted for 50 years, yielding a large body of data. Recent work has been directed toward synthesizing this evidence and understanding the visual, associative, and cognitive mechanisms that are involved. The outcome is that pigeons are likely to be the non-primate species for which the computational mechanisms of object recognition are best understood. Here, we review this research and suggest that a core set of mechanisms for object recognition might be present in all vertebrates, including pigeons and people, making pigeons an excellent candidate model to study the neural mechanisms of object recognition. Behavioral and computational evidence suggests that error-driven learning participates in object category learning by pigeons and people, and recent neuroscientific research suggests that the basal ganglia, which are homologous in these species, may implement error-driven learning of stimulus-response associations. Furthermore, learning of abstract category representations can be observed in pigeons and other vertebrates. Finally, there is evidence that feedforward visual processing, a central mechanism in models of object recognition in the primate ventral stream, plays a role in object recognition by pigeons. We also highlight differences between pigeons and people in object recognition abilities, and propose candidate adaptive specializations which may explain them, such as holistic face processing and rule-based category learning in primates. From a modern comparative perspective, such specializations are to be expected regardless of the model species under study. The fact that we have a good idea of which aspects of object recognition differ in people and pigeons should be seen as an advantage over other animal models. From this perspective, we suggest that there is much to learn about human object recognition from studying the “simple” brains of pigeons. PMID:25352784

Recognition of explosives fingerprints on objects for courier services using machine learning methods and laser-induced breakdown spectroscopy.

PubMed

Moros, J; Serrano, J; Gallego, F J; Macías, J; Laserna, J J

2013-06-15

During recent years laser-induced breakdown spectroscopy (LIBS) has been considered one of the techniques with larger ability for trace detection of explosives. However, despite of the high sensitivity exhibited for this application, LIBS suffers from a limited selectivity due to difficulties in assigning the molecular origin of the spectral emissions observed. This circumstance makes the recognition of fingerprints a latent challenging problem. In the present manuscript the sorting of six explosives (chloratite, ammonal, DNT, TNT, RDX and PETN) against a broad list of potential harmless interferents (butter, fuel oil, hand cream, olive oil, …), all of them in the form of fingerprints deposited on the surfaces of objects for courier services, has been carried out. When LIBS information is processed through a multi-stage architecture algorithm built from a suitable combination of 3 learning classifiers, an unknown fingerprint may be labeled into a particular class. Neural network classifiers trained by the Levenberg-Marquardt rule were decided within 3D scatter plots projected onto the subspace of the most useful features extracted from the LIBS spectra. Experimental results demonstrate that the presented algorithm sorts fingerprints according to their hazardous character, although its spectral information is virtually identical in appearance, with rates of false negatives and false positives not beyond of 10%. These reported achievements mean a step forward in the technology readiness level of LIBS for this complex application related to defense, homeland security and force protection. Copyright © 2013 Elsevier B.V. All rights reserved.

Development of visuo-haptic transfer for object recognition in typical preschool and school-aged children.

PubMed

Purpura, Giulia; Cioni, Giovanni; Tinelli, Francesca

2018-07-01

Object recognition is a long and complex adaptive process and its full maturation requires combination of many different sensory experiences as well as cognitive abilities to manipulate previous experiences in order to develop new percepts and subsequently to learn from the environment. It is well recognized that the transfer of visual and haptic information facilitates object recognition in adults, but less is known about development of this ability. In this study, we explored the developmental course of object recognition capacity in children using unimodal visual information, unimodal haptic information, and visuo-haptic information transfer in children from 4 years to 10 years and 11 months of age. Participants were tested through a clinical protocol, involving visual exploration of black-and-white photographs of common objects, haptic exploration of real objects, and visuo-haptic transfer of these two types of information. Results show an age-dependent development of object recognition abilities for visual, haptic, and visuo-haptic modalities. A significant effect of time on development of unimodal and crossmodal recognition skills was found. Moreover, our data suggest that multisensory processes for common object recognition are active at 4 years of age. They facilitate recognition of common objects, and, although not fully mature, are significant in adaptive behavior from the first years of age. The study of typical development of visuo-haptic processes in childhood is a starting point for future studies regarding object recognition in impaired populations.

Multivariate fMRI and Eye Tracking Reveal Differential Effects of Visual Interference on Recognition Memory Judgments for Objects and Scenes.

PubMed

O'Neil, Edward B; Watson, Hilary C; Dhillon, Sonya; Lobaugh, Nancy J; Lee, Andy C H

2015-09-01

Recent work has demonstrated that the perirhinal cortex (PRC) supports conjunctive object representations that aid object recognition memory following visual object interference. It is unclear, however, how these representations interact with other brain regions implicated in mnemonic retrieval and how congruent and incongruent interference influences the processing of targets and foils during object recognition. To address this, multivariate partial least squares was applied to fMRI data acquired during an interference match-to-sample task, in which participants made object or scene recognition judgments after object or scene interference. This revealed a pattern of activity sensitive to object recognition following congruent (i.e., object) interference that included PRC, prefrontal, and parietal regions. Moreover, functional connectivity analysis revealed a common pattern of PRC connectivity across interference and recognition conditions. Examination of eye movements during the same task in a separate study revealed that participants gazed more at targets than foils during correct object recognition decisions, regardless of interference congruency. By contrast, participants viewed foils more than targets for incorrect object memory judgments, but only after congruent interference. Our findings suggest that congruent interference makes object foils appear familiar and that a network of regions, including PRC, is recruited to overcome the effects of interference.

Anatomically constrained neural network models for the categorization of facial expression

NASA Astrophysics Data System (ADS)

McMenamin, Brenton W.; Assadi, Amir H.

2004-12-01

The ability to recognize facial expression in humans is performed with the amygdala which uses parallel processing streams to identify the expressions quickly and accurately. Additionally, it is possible that a feedback mechanism may play a role in this process as well. Implementing a model with similar parallel structure and feedback mechanisms could be used to improve current facial recognition algorithms for which varied expressions are a source for error. An anatomically constrained artificial neural-network model was created that uses this parallel processing architecture and feedback to categorize facial expressions. The presence of a feedback mechanism was not found to significantly improve performance for models with parallel architecture. However the use of parallel processing streams significantly improved accuracy over a similar network that did not have parallel architecture. Further investigation is necessary to determine the benefits of using parallel streams and feedback mechanisms in more advanced object recognition tasks.