Search

The article presents information in a special section in the current issue of this periodical that focuses on syntactic and structural pattern recognition. The fields of syntactic and structural pattern recognition experienced explosive growth during the 1960s and 1970s, as evidenced by the number of papers published in this area. The syntactic approach takes the view that a pattern is composed of simpler sub patterns which, in turn, are built from even simpler sub patterns.

In many physical experiments and applications with photomultiplier tubes (PMTs), high-speed pulse digitization is used extensively. The current pulse from a PMT has a rising time of several to a hundred nanoseconds. The current pulse shape can be used to obtain the pulse energy and discriminate between different particles. The conventional readout system with a PMT uses the discrete or integrated pulse-shaping circuits and analog-to-digital converter (ADC) boards that are based on the Nuclear Instrument Modules (NIMs) or VersaModule Eurocard (VME) system to implement the data acquisition function. In many applications, such as security instruments, there are only several PMTs used in the whole system, or in some distributed applications, long-distance analog cable with high-voltage power cable is not applicable due to the tremendous number of channels and enormous distributed space. In this paper, an integrated digitizer base is designed and interfaced with a Cs2LiYCl6 (CLYC) scintillator with a PMT. The CLYC scintillator has the ability to realize the pulse shape discrimination (PSD) between the neutron and gamma rays. There is only one Category 5 cable needed for over 700-Mb/s transmission control protocol (TCP) data throughput and more than 10-W power. The boards of high voltage supply, current-sensitive preamplifier, 500-MSPS/12-bit ADC, readout module based on ZYNQ system-on-chip (SoC), power over Ethernet, and user-interface circuits are stacked with board-to-board connectors. The gamma-ray energy resolution is ∼4.6% at 662 keV with a $20-\mu \text{s}$ pulse integral and PSD figure of merit (FOM) is ∼3.0 by using the totally recorded events of neutrons and gamma rays. This integrated digitizer base can also be interfaced with other detectors with a PMT. [ABSTRACT FROM AUTHOR]

Recently, siamese-based trackers have achieved significant successes. However, those trackers are restricted by the difficulty of learning consistent feature representation with the object. To address the above challenge, this paper proposes a novel siamese implicit region proposal network with compound attention for visual tracking. First, an implicit region proposal (IRP) module is designed by combining a novel pixel-wise correlation method. This module can aggregate feature information of different regions that are similar to the pre-defined anchor boxes in Region Proposal Network. To this end, the adaptive feature receptive fields then can be obtained by linear fusion of features from different regions. Second, a compound attention module including a channel and non-local attention is raised to assist the IRP module to perform a better perception of the scale and shape of the object. The channel attention is applied for mining the discriminative information of the object to handle the background clutters of the template, while non-local attention is trained to aggregate the contextual information to learn the semantic range of the object. Finally, experimental results demonstrate that the proposed tracker achieves state-of-the-art performance on six challenging benchmark tests, including VOT-2018, VOT-2019, OTB-100, GOT-10k, LaSOT, and TrackingNet. Further, our obtained results demonstrate that the proposed approach can be run at an average speed of 72 FPS in real time. [ABSTRACT FROM AUTHOR]

The main role of the ITER Radial Neutron Camera (RNC) diagnostic is to measure in real time the plasma neutron emissivity profile at high peak count rates for a time duration up to 500 s. Due to the unprecedented high-performance conditions and after the identification of critical problems, a set of activities have been selected, focused on the development of high-priority prototypes, and capable to deliver answers to those problems before the final RNC design. This paper presents one of the selected activities: the design, development, and testing of a dedicated field-programmable gate array (FPGA) code for the RNC data acquisition prototype. The FPGA code aims to acquire, process, and store in real time the neutron and gamma pulses from the detectors located in collimated lines of sight (LOS) viewing a poloidal plasma section from the ITER Equatorial Port Plug 1. The hardware platform used was an evaluation board from Xilinx (KC705) carrying an IPFN FPGA Mezzanine Card (FMC-AD2-1600) with two digitizer channels of 12-bit resolution sampling up to 1.6 Gsamples/s. The code performs the proper input signal conditioning using a down-sampled configuration to 400 Msamples/s, applies dedicated algorithms for pulse detection, filtering and pile up (PU) detection, and includes two distinct data paths operating simultaneously: 1) the event-based datapath for pulse storage and 2) the real-time processing with dedicated algorithms for pulse shape discrimination (PDS) and pulse height spectra (PHS). For continuous data throughput, both datapaths are streamed to the host through two distinct PCIe $\times 8$ direct memory access (DMA) channels. [ABSTRACT FROM AUTHOR]

This paper introduces a new benchmark study to evaluate the performance of landmark-based shape correspondence used for statistical shape analysis. Different from previous shape-correspondence evaluation methods, the proposed benchmark first generates a large set of synthetic shape instances by randomly sampling a given statistical shape model that defines a ground-truth shape space. We then run a test shape-correspondence algorithm on these synthetic shape instances to identify a set of corresponded landmarks. According to the identified corresponded landmarks, we construct a new statistical shape model which defines a new shape space. We finally compare this new shape space against the ground-truth shape space to determine the performance of the test shape- correspondence algorithm. In this paper, we introduce three new performance measures that are landmark independent to quantify the difference between the ground-truth and the newly derived shape spaces. By introducing a ground-truth shape space that is defined by a statistical shape model and three new landmark-independent performance measures, we believe the proposed benchmark allows for a more objective evaluation of shape correspondence than previous methods. In this paper, we focus on developing the proposed benchmark for 2D shape correspondence. However, it can easily be extended to 3D cases. [ABSTRACT FROM AUTHOR]

The usual goal of modeling natural and artificial perception involves determining how a system can extract the object that it perceives from an image that is noisy. The "inverse" of this problem is one of modeling how even a clear image can be perceived to be blurred in certain contexts. To our knowledge, there is no solution to this in the literature other than for an oversimplified model in which the true image is garbled with noise by the perceiver himself. In this paper, we propose a chaotic model of pattern recognition (PR) for the theory of "blurring." This paper, which is an extension to a companion paper demonstrates how one can model blurring from the view point of a chaotic PR system. Unlike the companion paper in which a chaotic PR system extracts the pattern from the input, in this case, we show that even without the inclusion of additional noise, perception of an object can be "blurred" if the dynamics of the chaotic system are modified. We thus propose a formal model and present an analysis using the Lyapunov exponents and the Routh-Hurwitz criterion. We also demonstrate experimentally the validity of our model by using a numeral data set. A byproduct of this model is the theoretical possibility of desynchronization of the periodic behavior of the brain (as a chaotic system), rendering us the possibility of predicting, controlling, and annulling epileptic behavior. [ABSTRACT FROM AUTHOR]

In this paper, we introduce feedback-based associative learning in self-organized learning arrays (SOLAR). SOLAR structures are hierarchically organized networks of sparsely connected neurons that define their own functions and select their interconnections locally. This paper provides a description of neuron self-organization and signal processing. Feedforward processing is used to make necessary correlations and learn the input patterns. Discovered associations between neuron inputs are used to generate feedback signals. These feedback signals, when propagated to the primary inputs, can establish the expected input values. This can be used for heteroassociative (HA) and autoassociative (AA) learning and pattern recognition. Example applications in HA learning are given. [ABSTRACT FROM AUTHOR]

The matching pursuit algorithm has been successfully applied in many areas such as dab compression and pattern recognition. The performance of matching pursuit is closely related to the selection of the dictionary. In this paper, we propose an algorithm to estimate the optimal dictionary distribution ratio and discuss the decay of the norm of residual signal in matching pursuit when the coefficients are quantized by a uniform scalar quantizer. It is proposed that if the approximation error E and the dimension of the space N are given, the optimal size of the dictionary and the optimal quantizer step should be obtained by minimizing the number of bits required to store the matching pursuit representation of any signal in the space to satisfy the error bound. [ABSTRACT FROM AUTHOR]

Feedback is a fundamental mechanism existing in the human visual system, but has not been explored deeply in designing computer vision algorithms. In this paper, we claim that feedback plays a critical role in understanding convolutional neural networks (CNNs), e.g., how a neuron in CNNs describes an object's pattern, and how a collection of neurons form comprehensive perception to an object. To model the feedback in CNNs, we propose a novel model named Feedback CNN and develop two new processing algorithms, i.e., neural pathway pruning and pattern recovering. We mathematically prove that the proposed method can reach local optimum. Note that Feedback CNN belongs to weakly supervised methods and can be trained only using category-level labels. But it possesses a powerful capability to accurately localize and segment category-specific objects. We conduct extensive visualization analysis, and the results reveal the close relationship between neurons and object parts in Feedback CNN. Finally, we evaluate the proposed Feedback CNN over the tasks of weakly supervised object localization and segmentation, and the experimental results on ImageNet and Pascal VOC show that our method remarkably outperforms the state-of-the-art ones. [ABSTRACT FROM AUTHOR]

We introduce a semi-automatic lighting design method that deploys per-voxel accessory lights (fill and detail lights) to enhance local shapes, as well as to increase the perceptibility and visual saliency of an object. Our approach allows the user to manually design arbitrary lights in a scene for creating the desired feeling of emotion. The user designed lights are used as key lights and our approach automatically configures per-voxel accessory lights that preserve the user designed feeling of emotion. Per-voxel fill lights brighten the shadows and thus increase the perceptibility and visual saliency. Per-voxel detail lights enhance the visual cues for the local shape perception. Moreover, the revealed local shapes are controlled by the user employing an importance distribution. Similarly, the perceptibility and visual saliency are also controlled based on an importance distribution. Our perceptual measurement guarantees that the revealed local shapes are independent of the key lights. In addition, our method provides two control parameters, which adjust the fill and detail lights, to provide the user with additional flexibility in designing the expected lighting effect. The major contributions of this paper are the idea of using the importance distribution to control local shapes, the per-voxel accessory lights and the perceptual measurement. [ABSTRACT FROM AUTHOR]

Recent narratives about technology and the future have been dominated by dystopian futures, limiting our collective imagination. This is not merely a product of technology itself but is deeply rooted in the bio-psycho-social dynamics of our historical context. Humans have a natural tendency to focus on problems, often exhibiting a negativity bias that is exacerbated by the relentless pace and stressors of modern life and the pervasive exposure to stress-inducing media. While Antonio Gramsci’s notion of cultural hegemony illuminates how dominant societal forces can shape our perceptions and values, the prevalence of dystopian views about technology also reflects broader societal concerns. These range from genuine fears about privacy and autonomy to anxieties about technology’s role in widening social inequalities. Such dynamics do not merely reinforce fear and anxiety but also create a fertile ground for “dark mirrors”—narratives in our cultural imagination that reflect our deepest fears and foster cycles of pessimism about the role of technology in our future. [ABSTRACT FROM AUTHOR]

This paper describes detectors comprised of Cs2LiYCl6:Ce (CLYC) scintillators coupled to silicon photomultipliers (MPPC, Hamamatsu). CLYC has been developed for dual gamma ray and thermal neutron detection. MPPCs are compact detectors with a very thin profile (\sim2 mm), but also a small active area (6 mm \times 6 mm). The combination of both can create a compact replacement of a He-3 tube. Three different crystal sizes were tested: a 5\ mm\times 5\ mm\times 5\ mm cube, a 1\ cm\times 1\ cm\times 4\ cm cuboid, and a \varnothing 1\ in\times 1\ in cylinder. All three detectors showed a well-resolved thermal neutron peak with energy resolution of 5.4%, 7%, and 11% (FWHM), respectively. The degradation in larger crystals is due to a mismatch between the coupled crystal face and the active area of the light detector. All detectors showed the 662 keV gamma ray peak from a Cs-137 source, indicating capability for limited gamma ray spectroscopy, with energy resolutions of 10%, 17%, and 26%, respectively. The capability for pulse shape discrimination was shown as well. The efficiency of the detectors was measured against a 10 atm He-3 tube (9 cm^3 volume). The best absolute efficiency was shown by the cylinder detector, next by the He-3 tube (almost the same as the cylinder detector), and finally by the cuboid detector. The latter showed the best neutron count per cm^3, twice as high as the two other detectors. [ABSTRACT FROM PUBLISHER]

The new plastic scintillators with n/\gamma pulse shape discrimination (PSD) properties being developed by the Lawrence Livermore National Laboratory (LLNL) and commercialized by Eljen Technology are addressing the toxicity and flammability issues of liquid scintillators, thus enabling a much wider range of practical applications for the detection of neutrons. These scintillation materials use multiple dyes, the concentration of which can vary, and therefore the light output and PSD properties of these new materials are expected to vary as well. In this paper, we compare the light signal time profiles of a liquid scintillator and two samples (one from LLNL and one from Eljen Technology) of new plastic scintillators with PSD properties. We acquired the light signal time profiles using both \gamma sources (^60Co, ^137Cs, ^241Am) and neutrons calibrated in electron-equivalent by the gamma sources. The n/\gamma PSD properties for time profiles collected are analyzed and discussed with respect to charge integration time. [ABSTRACT FROM PUBLISHER]

Since cameras blur the incoming light during measurement, different images of the same surface do not contain the same information about that surface. Thus, in general, corresponding points in multiple views of a scene have different image intensities. While multiple-view geometry constrains the locations of corresponding points, it does not give relationships between the signals at corresponding locations. This paper offers an elementary treatment of these relationships. We first develop the notion of "ideal" and "real" images, corresponding to, respectively, the raw incoming light and the measured signal. This framework separates the filtering and geometric aspects of imaging. We then consider how to synthesize one view of a surface from another; if the transformation between the two views is affine, it emerges that this is possible if and only if the singular values of the affine matrix are positive. Next, we consider how to combine the information in several views of a surface into a single output image. By developing a new tool called "frequency segmentation," we show how this can be done despite not knowing the blurring kernel. [ABSTRACT FROM AUTHOR]

The ability of practical recognition systems to recognize a large number of objects is constrained by a variety of factors that include choice of a feature extraction technique, quality of images, complexity and variability of underlying objects and of collected data. Given a feature extraction technique generating templates of objects from data and a resolution of the original images, the remaining factors can be attributed to distortions due to a recognition channel. We define the recognition channel as the environment that transforms reference templates of objects in a database into templates submitted for recognition. If templates in an object database are generated to be statistically independent and the noise in a query template is statistically independent of templates in the database, then the abilities of the recognition channel to recognize a large number of object classes can be characterized by a number called recognition capacity. In this paper, we evaluate the empirical recognition capacity of PCA-based object recognition systems. The encoded data (templates) and the additive noise in query templates are modeled to be Gaussian distributed with zero mean and estimated variances. We analyze both the case of a single encoded image and the case of encoded correlated multiple images. For this case, we propose a model that is orientation and elevation angle (pose) dependent. The fit of proposed models is judged using statistical goodness of fit tests. We define recognition rate as the ratio R = log(M)/n, where M is the number of objects to recognize and n is the length of PCA templates. The empirical capacity of PCA-based recognition systems is numerically evaluated. The empirical random coding exponent is also numerically evaluated and plotted as a function of the recognition rate. With these results, given a value of the recognition capacity and the length of templates (assume large), we can predict the number of distinct object classes that can be stored in an object library and be identified with probability of error close to zero. [ABSTRACT FROM AUTHOR]

In this paper, a preliminary experimentation is carried out to investigate the necessary stimulation conditions for a pattern display that may be used for the blind to display obstacle distribution. To design an efficient vibrotactile display device of array-type and compact size, the effect of some main parameters, such as the amplitude and frequency of vibration and the spacing and quantity of vibrated pins on vibrotactile perception, should be considered. Through experiment and analysis, the minimal amplitude of vibrating stimuli and the spacing effect on the perception of vibrotactile pattern are investigated and discussed. Also an appropriate type of actuator satisfying the requirements of a compact tactile display device for the effective transfer of pattern information is discussed. [ABSTRACT FROM AUTHOR]

In some pattern recognition tasks, the dimension of the sample space is larger than the number of samples in the training set. This is known as the ‘small sample size problem.’ Linear discriminant analysis (LDA) techniques cannot be applied directly to the small sample size case. The small sample size problem is also encountered when kernel approaches are used for recognition. In this paper, we attempt to answer the question of ‘How should one choose the optimal projection vectors for feature extraction in the small sample size case?’ Based on our findings, we propose a new method called the kernel discriminative common vector method. In this method, we first nonlinearly map the original input space to an implicit higher dimensional feature space, in which the data are hoped to be linearly separable. Then, the optimal projection vectors are computed in this transformed space. The proposed method yields an optimal solution for maximizing a modified Fisher's linear discriminant criterion, discussed in the paper. Thus, under certain conditions, a 100% recognition rate is guaranteed for the training set samples. Experiments on test data also show that, in many situations, the generalization performance of the proposed method compares favorably with other kernel approaches. [ABSTRACT FROM AUTHOR]

The traditional approach to automated analysis of medical data is mostly based on statistical or theoretical-decision methods of pattern recognition. Using such methods, we can obtain many valuable items, e.g., tracking patients' movements, control of medical treatment, etc. In medical informatics there are still many problems not solvable by computers and reserved for human medical staff. Such problems can be solved by the development of scientific research toward machine intelligence. In this paper, we try to show how the computer can understand medical data instead of simple processing and analysis. Sometimes it may be useful to make semantic content analysis leading to automatic understanding of medical data, e.g., for intelligent help in the diagnosis process or in semantics-based searching through medical databases. This paper will present the application of the cognitive-based approach for intelligent semantic analysis, allowing describing automatically important diagnostic features of analyzed images. This approach is based on a special kind of image description language and grammar formalism. During the linguistic analysis of medical patterns, we can solve the problem of generalization of features of a selected image and obtaining semantic content description of the image. The most important part of this analysis depends on the "cognitive resonance" process, in which features of real images are compared with some kind of expectation taken from the knowledge base containing knowledge regarding pathological cases originating from medical practice. [ABSTRACT FROM AUTHOR]

Graph structures have proven computationally cumbersome for pattern analysis. The reason for this is that, before graphs can be converted to pattern vectors, correspondences must be established between the nodes of structures which are potentially of different size. To overcome this problem, in this paper, we turn to the spectral decomposition of the Laplacian matrix. We show how the elements of the spectral matrix for the Laplacian can be used to construct symmetric polynomials that are permutation invariants. The coefficients of these polynomials can be used as graph features which can be encoded in a vectorial manner. We extend this representation to graphs in which there are unary attributes on the nodes and binary attributes on the edges by using the spectral decomposition of a Hermitian property matrix that can be viewed as a complex analogue of the Laplacian. To embed the graphs in a pattern space, we explore whether the vectors of invariants can be embedded in a low-dimensional space using a number of alternative strategies, including principal components analysis (PCA), multidimensional scaling (MDS), and locality preserving projection (LPP). Experimentally, we demonstrate that the embeddings result in well-defined graph clusters. Our experiments with the spectral representation involve both synthetic and real-world data. The experiments with synthetic data demonstrate that the distances between spectral feature vectors can be used to discriminate between graphs on the basis of their structure. The real-world experiments show that the method can be used to locate clusters of graphs. [ABSTRACT FROM AUTHOR]

Probabilistic finite-state machines are used today in a variety of areas in pattern recognition, or in fields to which pattern recognition is linked: computational linguistics, machine learning, time series analysis, circuit testing, computational biology, speech recognition, and machine translation are some of them. In Part I of this paper, we survey these generative objects and study their definitions and properties. In Part II, we will study the relation of probabilistic finite-state automata with other well-known devices that generate strings as hidden Markov models and n-grams and provide theorems, algorithms, and properties that represent a current state of the art of these objects. [ABSTRACT FROM AUTHOR]

In this paper, we derive a technique for analysis of local distortions which affect data in real-world applications. In the paper, we focus on image data, specifically handwritten characters. Given a reference image and a distorted copy of it, the method is able to efficiently determine the rotations, translations, scaling, and any other distortions that have been applied. Because the method is robust, it is also able to estimate distortions for two unrelated images, thus determining the distortions that would be required to cause the two images to resemble each other. The approach is based on a polynomial series expansion using matrix powers of linear transformation matrices. The technique has applications in pattern recognition in the presence of distortions. [ABSTRACT FROM AUTHOR]

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 normalization, a state-of-the-art quadratic assignment relaxation algorithm. [ABSTRACT FROM AUTHOR]

Learning a class prototype from a set of exemplars is an important challenge facing researchers in object categorization. Although the problem is receiving growing interest, most approaches assume a one-to-one correspondence among local features, restricting their ability to learn true abstractions of a shape. In this paper, we present a new technique for learning an abstract shape prototype from a set of exemplars whose features are in many-to-many correspondence. Focusing on the domain of 2D shape, we represent a silhouette as a medial axis graph whose nodes correspond to "parts" defined by medial branches and whose edges connect adjacent parts. Given a pair of medial axis graphs, we establish a many-to-many correspondence between their nodes to find correspondences among articulating parts. Based on these correspondences, we recover the abstracted medial axis graph along with the positional and radial attributes associated with its nodes. We evaluate the abstracted prototypes in the context of a recognition task. [ABSTRACT FROM AUTHOR]

The instabilities of the medial axis of a shape under deformations have long been recognized as a major obstacle to its use in recognition and other applications. These instabilities, or transitions, occur when the structure of the medial axis graph changes abruptly under deformations of shape. The recent classification of these transitions in 2D for the medial axis and for the shock graph was a key factor in the development of an object recognition system where the classified instabilities were utilized to represent deformation paths. The classification of generic transitions of the 3D medial axis could likewise potentially lead to a similar representation in 3D. In this paper, these transitions are classified by examining the order of contact of spheres with the surface, leading to an enumeration of possible transitions which are then examined on a case-by-case basis. Some cases are ruled out as never occurring in any family of deformations, while others are shown to be nongeneric in a one-parameter family of deformations. Finally, the remaining cases are shown to be viable by developing a specific example for each. Our work is inspired by that of Bogaevsky, who obtained the transitions as part of an investigation of viscosity solutions of Hamilton-Jacobi equations. Our contribution is to give a more down-to-earth approach, bringing this work to the attention of the computer vision community, and to provide explicit constructions for the various transitions using simple surfaces. We believe that the classification of these transitions is vital to the successful regularization of the medial axis in its use in real applications. [ABSTRACT FROM AUTHOR]

Recognizing lines of unconstrained handwritten text is a challenging task. The difficulty of segmenting cursive or overlapping characters, combined with the need to exploit surrounding context, has led to low recognition rates for even the best current recognizers. Most recent progress in the field has been made either through improved preprocessing or through advances in language modeling. Relatively little work has been done on the basic recognition algorithms. Indeed, most systems rely on the same hidden Markov models that have been used for decades in speech and handwriting recognition, despite their well-known shortcomings. This paper proposes an alternative approach based on a novel type of recurrent neural network, specifically designed for sequence labeling tasks where the data is hard to segment and contains long-range bidirectional interdependencies. In experiments on two large unconstrained handwriting databases, our approach achieves word recognition accuracies of 79.7 percent on online data and 74.1 percent on offline data, significantly outperforming a state-of-the-art HMM-based system. In addition, we demonstrate the network's robustness to lexicon size, measure the individual influence of its hidden layers, and analyze its use of context. Last, we provide an in-depth discussion of the differences between the network and HMMs, suggesting reasons for the network's superior performance. [ABSTRACT FROM AUTHOR]

In this paper, we propose a practical and efficient method for finding the globally optimal solution to the problem of determining the pose of an object. We present a framework that allows us to use point-to-point, point-to-line, and point-to-plane correspondences for solving various types of pose and registration problems involving euclidean (or similarity) transformations. Traditional methods such as the iterative closest point algorithm or bundle adjustment methods for camera pose may get trapped in local minima due to the nonconvexity of the corresponding optimization problem. Our approach of solving the mathematical optimization problems guarantees global optimality. The optimization scheme is based on ideas from global optimization theory, in particular convex underestimators in combination with branch-and-bound methods. We provide a provably optimal algorithm and demonstrate good performance on both synthetic and real data. We also give examples of where traditional methods fail due to the local minima problem. [ABSTRACT FROM AUTHOR]

In this paper, we develop a new framework for face recognition based on nonparametric discriminant analysis (NDA) and multiclassifier integration. Traditional LDA-based methods suffer a fundamental limitation originating from the parametric nature of scatter matrices, which are based on the Gaussian distribution assumption. The performance of these methods notably degrades when the actual distribution is non-Gaussian. To address this problem, we propose a new formulation of scatter matrices to extend the two-class NDA to multiclass cases. Then, in order to exploit the discriminant information in both the principal space and the null space of the intraclass scatter matrix, we develop two improved multiclass NDA-based algorithms (NSA and NFA) with each one having two complementary methods that are based on the principal space and the null space of the intraclass scatter matrix, respectively. Comparing to the NSA, the NFA is more effective in the utilization of the classification boundary information. In order to exploit the complementary nature of the two kinds of NFA (PNFA and NNFA), we finally develop a dual NFA-based multiclassifier fusion framework by employing the overcomplete Gabor representation for face images to boost the recognition performance. We show the improvements of the developed new algorithms over the traditional subspace methods through comparative experiments on two challenging face databases, the Purdue AR database and the XM2VTS database. [ABSTRACT FROM AUTHOR]

The recent years have witnessed a surge of interests of learning a subspace for image classification, which has aroused considerable researches from the pattern recognition and signal processing fields. However, for image classification, the accuracies of previous methods are not so high since they neglect some particular characters of the image data. In this paper, we propose a new subspace learning method. It constrains that the transformation basis is orthonormal and the derived coefficients ape spatially smooth. Classification is then performed in the image subspace. The proposed method can not only represent the intrinsic structure of the image data, but also avoid over-fitting. More importantly, it can be considered as a general framework, within which the performances of other subspace learning methods can be improved in the same way. Some related analyses of the proposed approach are presented. Promising experimental results on different kinds of real images demonstrate the effectiveness of our algorithm for image classification. [ABSTRACT FROM AUTHOR]

In computer vision, shape matching is a challenging problem, especially when articulation and deformation of parts occur. These variations may be insignificant for human recognition but often cause a matching algorithm to give results that are inconsistent with our perception. In this paper, we propose a novel shape descriptor of planar contours, called contour flexibility, which represents the deformable potential at each point along a contour. With this descriptor, the local and global features can be obtained from the contour. We then present a shape matching scheme based on the features obtained. Experiments with comparisons to recently published algorithms show that our algorithm performs best. [ABSTRACT FROM AUTHOR]

Registration and modeling of shapes are two important problems in computer vision and pattern recognition. Despite enormous progress made over the past decade, these problems are still open. In this paper, we advance the state of the art in both directions. First, we consider an efficient registration method that aims to recover a one-to-one correspondence between shapes and introduce measures of uncertainties driven from the data which explain the local support of the recovered transformations. To this end, a free-form deformation is used to describe the deformation model. The transformation is combined with an objective function defined in the space of implicit functions used to represent shapes. Once the registration parameters have been recovered, we introduce a novel technique for model building and statistical interpretation of the training examples based on a variable bandwidth kernel approach. The support on the kernels varies spatially and is determined according to the uncertainties of the registration process. Such a technique introduces the ability to account for potential registration errors in the model. Handwritten character recognition and knowledge-based object extraction in medical images are examples of applications that demonstrate the potentials of the proposed framework. [ABSTRACT FROM AUTHOR]

This paper proposes a nevel graph matching algorithm and applies it to shape recognition based on object silhouettes. The main idea is to match skeleton graphs by comparing the geodesic paths between skeleton endpoints. In contrast to typical tree or graph matching methods, we do not consider the topological graph structure. The proposed comparison of geodesic path between endpoints of skeleton graph yields correct matching results in such cases. The skeletons are pruned by contour partitioning with Discrete Curve Evolution, which implies that the endpoints of skeleton branches correspond to visual parts of the objects. The experimental results demonstrate that our method is able to produce results in the presence of articulations, stretching, and contour deformations. [ABSTRACT FROM AUTHOR]

This paper proposes a new technique for face detection and lip feature extraction. A real-time field-programmable gate array (FPGA) implementation of the two proposed techniques is also presented. Face detection is based on a naive Bayes classifier that classifies an edge-extracted representation of an image. Using edge representation significantly reduces the model's size to only 5184 B, which is 2417 times smaller than a comparable statistical modeling technique, while achieving an 86.6% correct detection rate under various lighting conditions. Lip feature extraction uses the contrast around the lip contour to extract the height and width of the mouth, metrics that are useful for speech filtering. The proposed FPGA system occupies only 15 050 logic cells, or about six times less than a current comparable FPGA face detection system. [ABSTRACT FROM AUTHOR]

Principal component analysis (PCA) has been proven to be an efficient method in pattern recognition and image analysis. Recently, PCA has been extensively employed for face-recognition algorithms, such as eigenface and fisherface. The encouraging results have been reported and discussed in the literature. Many PCA-based face-recognition systems have also been developed in the last decade. However, existing PCA-based face-recognition systems are hard to scale up because of the computational cost and memory-requirement burden. To overcome this limitation, an incremental approach is usually adopted. Incremental PCA (IPCA) methods have been studied for many years in the machine-learning community. The major limitation of existing IPCA methods is that there is no guarantee on the approximation error. In view of this limitation, this paper proposes a new IPCA method based on the idea of a singular value decomposition (SVD) updating algorithm, namely an SVD updating-based IPCA (SVDU-l[PCA) algorithm. In the proposed SVDU-IPCA algorithm, we have mathematically proved that the approximation error is bounded. A complexity analysis on the proposed method is also presented. Another characteristic of the proposed SVDU-IPCA algorithm is that it can be easily extended to a kernel version. The proposed method has been evaluated using available public databases, namely FERET, AR, and Yale B, and applied to existing face-recognition algorithms. Experimental results show that the difference of the average recognition accuracy between the proposed incremental method and the batch-mode method is less than 1%. This implies that the proposed SVDU-IPCA method gives a close approximation to the batch-mode PCA method. [ABSTRACT FROM AUTHOR]

There are many learning algorithms available in the field of pattern classification and people are still discovering new algorithms that they hope will work better. Any new learning algorithm, beside its theoretical foundation, needs to be justified in many aspects including accuracy and efficiency when applied to real life problems. In this paper, we report the empirical comparison of a recent algorithm RM, its new extensions and three classical classifiers in different aspects including classification accuracy, computational time and storage requirement. The comparison is per- formed in a standardized way and we believe that this would give a good insight into the algorithm RM and its extension. The experiments also show that nominal attributes do have an impact on the performance of those compared learning algorithms. [ABSTRACT FROM AUTHOR]

We present a novel method that provides an accurate and precise estimate of the length of the boundary (perimeter) of an object by taking into account gray levels on the boundary of the digitization of the same object. Assuming a model where pixel intensity is proportional to the coverage of a pixel, we show that the presented method provides error-free measurements of the length of straight boundary segments in the case of nonquantized pixel values. For a more realistic situation, where pixel values are quantized, we derive optimal estimates that minimize the maximal estimation error. We show that the estimate converges toward a correct value as the number of gray levels tends toward infinity. The method is easy to implement; we provide the complete pseudocode. Since the method utilizes Only a small neighborhood, it is very easy to parallelize. We evaluate the estimator on a set of concave and convex shapes with known perimeters, digitized at increasing resolution. In addition, we provide an example of applicability of the method on real images, by suggesting appropriate preprocessing steps and presenting results of a comparison of the suggested method with other local approaches. [ABSTRACT FROM AUTHOR]

The kinetic analysis of $^{{18}}\text{F}$ -FET time-activity curves (TAC) can provide valuable diagnostic information in glioma patients. The analysis is most often limited to the average TAC over a large tissue volume and is normally assessed by visual inspection or by evaluating the time-to-peak and linear slope during the late uptake phase. Here, we derived and validated a linearized model for TACs of $^{{18}}\text{F}$ -FET in dynamic PET scans. Emphasis was put on the robustness of the numerical parameters and how reliably automatic voxel-wise analysis of TAC kinetics was possible. The diagnostic performance of the extracted shape parameters for the discrimination between isocitrate dehydrogenase (IDH) wildtype (wt) and IDH-mutant (mut) glioma was assessed by receiver-operating characteristic in a group of 33 adult glioma patients. A high agreement between the adjusted model and measured TACs could be obtained and relative, estimated parameter uncertainties were small. The best differentiation between IDH-wt and IDH-mut gliomas was achieved with the linearized model fitted to the averaged TAC values from dynamic FET PET data in the time interval 4–50 min p.i.. When limiting the acquisition time to 20–40 min p.i., classification accuracy was only slightly lower (-3%) and was comparable to classification based on linear fits in this time interval. Voxel-wise fitting was possible within a computation time $\approx ~{1}$ min per image slice. Parameter uncertainties smaller than 80% for all fits with the linearized model were achieved. The agreement of best-fit parameters when comparing voxel-wise fits and fits of averaged TACs was very high (p < 0.001). [ABSTRACT FROM AUTHOR]

This article presents a composite (COM) method to obtain the high-resolution pulse shape discrimination (PSD) for the neutron and gamma-ray pulses generated from scintillation detectors. The method, which is based on a selective combination of the digital charge integration (DCI) with the reference pulse method, aims to reduce the mixed radiation events in the low-energy range. An EJ-301 liquid scintillation detector together with a fast sampling analog-to-digital converter (ADC) is used to measure and digitize the pulses induced from the radioactive decays of 60Co and 252Cf, which are then analyzed by our COM method. The proposed method is evaluated using the figure of merit (FoM) and separation quality function $F(u)$ , and the results are compared with three known methods, namely the DCI, standard event fit (SEF), and artificial neural network (ANN) methods. We show that the average values of FoM and $F(u)$ obtained within the COM method are about ten times higher than those obtained within the DCI and SEF in the whole energy range from 50 to 1000 keV electron equivalent (keVee). In particular, by using the COM method, the percentage of gamma events being confused as neutrons ranges from 0.32% to 8.80% when the energy is reduced from 400 to 50 keVee. This finding, which is significantly lower than those obtained by using the DCI and SEF, indicates that the proposed COM method should be considered as a leading method for producing a neutron/gamma PSD counter system with high resolution. [ABSTRACT FROM AUTHOR]

Studies the application of directed acylic graphs (DAG) to a large class of (temporal) pattern recognition problems and presents a dynamic programming algorithm for comparison of two DAG types. Extraction of continuous streams to DAG; Algorithm for matching DAG; Neural structure of DAG; Application of DAG to on-line cursive handwriting recognition; Conclusions.

We note that the images in the CASIA version 1.0 iris data set have been edited so that the pupil area is replaced by a circular region of uniform intensity. We recommend that this data set no longer be used in iris biometrics research unless there is a compelling reason that takes into account the nature of the images. In addition, based on our experience with the Iris Challenge Evaluation (ICE) 2005 technology development project, we make recommendations for reporting results of iris recognition experiments. [ABSTRACT FROM AUTHOR]

This work proposes Winglets, an enhancement to the classic scatterplot to better perceptually pronounce multiple classes by improving the perception of association and uncertainty of points to their related cluster. Designed as a pair of dual-sided strokes belonging to a data point, Winglets leverage the Gestalt principle of Closure to shape the perception of the form of the clusters, rather than use an explicit divisive encoding. Through a subtle design of two dominant attributes, length and orientation, Winglets enable viewers to perform a mental completion of the clusters. A controlled user study was conducted to examine the efficiency of Winglets in perceiving the cluster association and the uncertainty of certain points. The results show Winglets form a more prominent association of points into clusters and improve the perception of associating uncertainty. [ABSTRACT FROM AUTHOR]

The advent of Industry 4.0 with massive connectivity places significant strains on the current spectrum resources, and challenges the industry and regulators to respond promptly with new disruptive spectrum management strategies. The envisioned spectrum intelligent radio has long been promised to unlock the full potential of spectrum resource. However, the current radio development, with certain elements of intelligence, is nowhere near showing an agile response to the complex radio environments. Following the line of intelligence, we propose to classify spectrum intelligent radio into three streams: classical signal processing, machine learning (ML), and contextual adaptation. We focus on the ML approach, and propose a new intelligent radio architecture with three hierarchical forms: perception, understanding, and reasoning. For each form, we propose some preliminary methods. The proposed perception method achieves fully blind multi-level spectrum sensing. The understanding method accurately predicts the primary users' coverage across a large area, and the reasoning method performs near-optimal idle channel selection. Opportunities, challenges, and future visions are also discussed for the realization of a fully intelligent radio. [ABSTRACT FROM AUTHOR]

In a scintillation detector, the light generated in the scintillator by a gamma interaction is converted to photoelectrons by a photodetector and produces a time-dependent waveform, the shape of which depends on the scintillator properties and the photodetector response. Several depth-of-interaction (DOI) encoding strategies have been developed that manipulate the scintillator’s temporal response along the crystal length and therefore require pulse shape discrimination techniques to differentiate waveform shapes. In this work, we demonstrate how maximum likelihood (ML) estimation methods can be applied to pulse shape discrimination to better estimate deposited energy, DOI and interaction time (for time-of-flight (TOF) PET) of a gamma ray in a scintillation detector. We developed likelihood models based on either the estimated detection times of individual photoelectrons or the number of photoelectrons in discrete time bins, and applied to two phosphor-coated crystals (LFS and LYSO) used in a previously developed TOF-DOI detector concept. Compared with conventional analytical methods, ML pulse shape discrimination improved DOI encoding by 27% for both crystals. Using the ML DOI estimate, we were able to counter depth-dependent changes in light collection inherent to long scintillator crystals and recover the energy resolution measured with fixed depth irradiation (~11.5% for both crystals). Lastly, we demonstrated how the Richardson-Lucy algorithm, an iterative, ML-based deconvolution technique, can be applied to the digitized waveforms to deconvolve the photodetector’s single photoelectron response and produce waveforms with a faster rising edge. After deconvolution and applying DOI and time-walk corrections, we demonstrated a 13% improvement in coincidence timing resolution (from 290 to 254 ps) with the LFS crystal and an 8% improvement (323 to 297 ps) with the LYSO crystal. [ABSTRACT FROM PUBLISHER]

We consider the problem of estimating detailed 3D structure from a single still image of an unstructured environment. Our goal is to create 3D models that are both quantitatively accurate as well as visually pleasing. For each small homogeneous patch in the image, we use a Markov Random Field (MRF) to infer a set of 'plane parameters" that capture both the 3D location and 3D orientation of the patch. The MRF, trained via supervised learning, models both image depth cues as well as the relationships between different parts of the image. Other than assuming that the environment is made up of a number of small planes, our model makes no explicit assumptions about the structure of the scene; this enables the algorithm to capture much more detailed 3D structure than does prior art and also give a much richer experience in the 3D flythroughs created using image-based rendering, even for scenes with significant nonvertical structure. Using this approach, we have created qualitatively correct 3D models for 64.9 percent of 588 images downloaded from the Internet. We have also extended our model to produce large-scale 3D models from a few images. [ABSTRACT FROM AUTHOR]

Particle filtering is frequently used for visual tracking problems since it provides a general framework for estimating and propagating probability density functions for nonlinear and non-Gaussian dynamic systems. However, this algorithm is based on a Monte Carlo approach and the cost of sampling and measurement is a problematic issue, especially for high-dimensional problems. We describe an alternative to the classical particle filter in which the underlying density function has an analytic representation for better approximation and effective propagation. The techniques of density interpolation and density approximation are introduced to represent the likelihood and the posterior densities with Gaussian mixtures, where all relevant parameters are automatically determined. The proposed analytic approach is shown to perform more efficiently in sampling in high-dimensional space. We apply the algorithm to real-time tracking problems and demonstrate its performance on real video sequences as well as synthetic examples. [ABSTRACT FROM AUTHOR]

We present a nonstationary stochastic filtering framework for the task of albedo estimation from a single image. There are several approaches in the literature for albedo estimation, but few include the errors in estimates of surface normals and light source direction to improve the albedo estimate. The proposed approach effectively utilizes the error statistics of surface normals and illumination direction for robust estimation of albedo, for images illuminated by single and multiple light sources. The albedo estimate obtained is subsequently used to generate albedo-free normalized images for recovering the shape of an object. Traditional Shape- from-Shading (SFS) approaches often assume constant/piecewise constant albedo and known light source direction to recover the underlying shape. Using the estimated albedo, the general problem of estimating the shape of an object with varying albedo map and unknown illumination source is reduced to one that can be handled by traditional SFS approaches. Experimental results are provided to show the effectiveness of the approach and its application to illumination-invariant matching and shape recovery. The estimated albedo maps are compared with the ground truth. The maps are used as illumination-invariant signatures for the task of face recognition across illumination variations. The recognition results obtained compare well with the current state-of-the-art approaches. Impressive shape recovery results are obtained using images downloaded from the Web with little control over imaging conditions. The recovered shapes are also used to synthesize novel views under novel illumination conditions. [ABSTRACT FROM AUTHOR]

We propose a novel model for nonlinear dimension reduction motivated by the probabilistic formulation of principal component analysis. Nonlinearity is achieved by specifying different transformation matrices at different locations of the latent space and smoothing the transformation using a Markov random field type prior. The computation is made feasible by the recent advances in sampling from von Mises-Fisher distributions. The computational properties of the algorithm are illustrated through simulations as well as an application to handwritten digits data. [ABSTRACT FROM AUTHOR]