Search

We present a simple and effective method for denoising phase patterns based on a discrete model. The proposed filtering method transforms the image denoising problem to solving the energy diffusion problem of a system with complex-valued fields. We establish an appropriate cost function that uses the discrete form of complex-valued Markov random fields. The attractiveness of the proposed filtering method includes three points: the first is that the filtering process can be easily implemented using an iterative method, the second is that 2[pi] phase jumps are well preserved, and the third is its little computational effort. The performance of the proposed method is demonstrated by simulated and experimentally obtained phase patterns. [c] 2010 Optical Society of America OCIS codes: 100.3008, 110.3175.

We present a method to obtain simultaneous three-dimensional shape and color information from a single captured image using a composite red, green, and blue (RGB) projected fringe pattern. Previous attempts at single snapshot shape and color metrology have suffered from either poor dynamic range or have been highly dependent on the color of the artifact. An optimum multiwavelength process has been employed to maximize the dynamic range of the shape data and give absolute depth information independently at each pixel. Fringe processing is via a Fourier transform process with algorithms introduced to obtain RGB color texture. Simulated and experimental data demonstrate the algorithm's robustness in the vicinity of surface discontinuities. Experimental results from a human hand show the applicability to dynamic scenes. OCIS codes: 110.6880, 120.2650, 120.5050, 330.1710.

The automated detection of structural elements (e.g., columns and beams) from visual data can be used to facilitate many construction and maintenance applications. The research in this area is under initial investigation. The existing methods solely rely on color and texture information, which makes them unable to identify each structural element if these elements connect each other and are made of the same material. The paper presents a novel method of automated concrete column detection from visual data. The method overcomes the limitation by combining columns' boundary information with their color and texture cues. It starts from recognizing long vertical lines in an image/video frame through edge detection and Hough transform. The bounding rectangle for each pair of lines is then constructed. When the rectangle resembles the shape of a column and the color and texture contained in the pair of lines are matched with one of the concrete samples in knowledge base, a concrete column surface is assumed to be located. This way, one concrete column in images/videos is detected. The method was tested using real images/videos. The results are compared with the manual detection ones to indicate the method's validity. DOI: 10.1061/(ASCE)CP.1943-5487.0000053 CE Database subject headings: Concrete columns; Identification; Imaging techniques; Information technology (IT). Author keywords: Concrete columns; Automatic identification systems; Images; Information technology.

In digital image correlation (DIC), to obtain the displacements of each point of interest, a correlation criterion must be predefined to evaluate the similarity between the reference subset and the target subset. The correlation criterion is of fundamental importance in DIC, and various correlation criteria have been designed and used in literature. However, little research has been carried out to investigate their relations. In this paper, we first provide a comprehensive overview of various correlation criteria used in DIC. Then we focus on three robust and most widely used correlation criteria, i.e., a zero-mean normalized cross-correlation (ZNCC) criterion, a zero-mean normalized sum of squared difference (ZNSSD) criterion, and a parametric sum of squared difference ([PSSD.sub.ab]) criterion with two additional unknown parameters, since they are insensitive to the scale and offset changes of the target subset intensity and have been highly recommended for practical use in literature. The three correlation criteria are analyzed to establish their transversal relationships, and the theoretical analyses clearly indicate that the three correlation criteria are actually equivalent, which elegantly unifies these correlation criteria for pattern matching. Finally, the equivalence of these correlation criteria is further validated by numerical simulation and actual experiment. OCIS codes: 100.4999, 120.6650.

A multichannel, multilayer feed forward neural network mode] is proposed for rotation invariant recognition of objects. In the M channel network, each channel consists of a one dimensional slice of the two dimensional (2D) Fourier transform (FT) of the input pattern that connects fully to the weight matrix. Each slice is taken at different angles from the 2D FT of the object. From each channel, only one neuron can fire in the presence of the training object. The output layer sums up the response of the hidden layer neuron and confirms the presence of the object. Rotation invariant recognition from 0[degrees] to 360[degrees] is obtained even in the case of degraded images. OCIS codes: 070.4550, 150.0150.

An application of the continuous wavelet transform to modulation extraction of additive moire fringes and time-average patterns is proposed. We present numerical studies of the influence of various parameters of the wavelet transformation itself and a fringe pattern under study on the demodulation results. To facilitate the task of demodulating a signal with zero crossing values, a two-frame approach for wavelet ridge extraction is proposed. Experimental studies of vibration mode patterns by time-average interferometry provide excellent verification of numerical findings. They compare very well with the results of our previous investigations using the temporal phase-shifting method widely considered as the most accurate one. No need of performing phase shifting represents significant simplification of the experimental procedure. [c] 2010 Optical Society of America OCIS codes: 120.2650, 120.3180, 120.4120, 120.7280, 100.7410.

This letter presents an algorithm for detecting cross-fade scene changes in video carrying 3:2 or mixed film cadence. There are many existing methods for detecting gradual video transitions, but none of the current literature addresses the complication of film cadence. The differences between video and film capture and the mechanics of the telecine transfer process used to convert 24-Hz film to the main international television standards alter the temporal properties in a nonlinear way that makes cross-fades more difficult to detect with existing methods. An algorithm is proposed to address this problem. Index Terms--Image motion analysis, image sequences, pattern recognition, video signal processing.

The problem addressed in this study is the offline recognition of handwritten Arabic city names. The names are assumed to belong to a fixed lexicon of about 1,000 entries. A state-of-the-art classical right-left hidden Markov model (HMM)-based recognizer (reference system) using the sliding window approach is developed. The feature set includes both baseline-independent and baseline-dependent features. The analysis of the errors made by the recognizer shows that the inclination, overlap, and shifted positions of diacritical marks are major sources of errors. In this paper, we propose coping with these problems. Our approach relies on the combination of three homogeneous HMM-based classifiers. All classifiers have the same topology as the reference system and differ only in the orientation of the sliding window. We compare three combination schemes of these classifiers at the decision level. Our reported results on the benchmark IFN/ENIT database of Arabic Tunisian city names give a recognition rate higher than 90 percent accuracy and demonstrate the superiority of the neural network-based combination. Our results also show that the combination of classifiers performs better than a single classifier dealing with slant-corrected images and that the approach is robust for a wide range of orientation angles. Index Terms--Arabic handwriting, word recognition, feature extraction, IFN/ENIT database, hidden Markov models, HMM, neural network, multilayer perceptron, classifier combination.

Sign language spotting is the task of detecting and recognizing signs in a signed utterance, in a set vocabulary. The difficulty of sign language spotting is that instances of signs vary in both motion and appearance. Moreover, signs appear within a continuous gesture stream, interspersed with transitional movements between signs in a vocabulary and nonsign patterns (which include out-of-vocabulary signs, epentheses, and other movements that do not correspond to signs). In this paper, a novel method for designing threshold models in a conditional random field (CRF) model is proposed which performs an adaptive threshold for distinguishing between signs in a vocabulary and nonsign patterns. A short-sign detector, a hand appearance-based sign verification method, and a subsign reasoning method are included to further improve sign language spotting accuracy. Experiments demonstrate that our system can spot signs from continuous data with an 87.0 percent spotting rate and can recognize signs from isolated data with a 93.5 percent recognition rate versus 73.5 percent and 85.4 percent, respectively, for CRFs without a threshold model, short-sign detection, subsign reasoning, and hand appearance-based sign verification. Our system can also achieve a 15.0 percent sign error rate (SER) from continuous data and a 6.4 percent SER from isolated data versus 76.2 percent and 14.5 percent, respectively, for conventional CRFs. Index Terms--Sign language recognition, sign language spotting, conditional random field, threshold model.

This paper proposes a technique for jointly quantizing continuous features and the posterior distributions of their class labels based on minimizing empirical information loss such that the quantizer index of a given feature vector approximates a sufficient statistic for its class label. Informally, the quantized representation retains as much information as possible for classifying the feature vector correctly. We derive an alternating minimization procedure for simultaneously learning codebooks in the euclidean feature space and in the simplex of posterior class distributions. The resulting quantizer can be used to encode unlabeled points outside the training set and to predict their posterior class distributions, and has an elegant interpretation in terms of lossless source coding. The proposed method is validated on synthetic and real data sets and is applied to two diverse problems: learning discriminative visual vocabularies for bag-of-features image classification and image segmentation. Index Terms--Pattern recognition, information theory, quantization, clustering, computer vision, scene analysis, segmentation.

Fingerprint analysis is typically based on the location and pattern of detected singular points in the images. These singular points (cores and deltas) not only represent the characteristics of local ridge patterns but also determine the topological structure (i.e., fingerprint type) and largely influence the orientation field. In this paper, we propose a novel algorithm for singular points detection. After an initial detection using the conventional Poincare Index method, a so-called DORIC feature is used to remove spurious singular points. Then, the optimal combination of singular points is selected to minimize the difference between the original orientation field and the model-based orientation field reconstructed using the singular points. A core-delta relation is used as a global constraint for the final selection of singular points. Experimental results show that our algorithm is accurate and robust, giving better results than competing approaches. The proposed detection algorithm can also be used for more general 2D oriented patterns, such as fluid flow motion, and so forth. Index Terms--Singular points, topological structure, Poincare Index, orientation field.

Transformation invariance is an important property in pattern recognition, where different observations of the same object typically receive the same label. This paper focuses on a transformation-invariant distance measure that represents the minimum distance between the transformation manifolds spanned by patterns of interest. Since these manifolds are typically nonlinear, the computation of the manifold distance (MD) becomes a nonconvex optimization problem. We propose representing a pattern of interest as a linear combination of a few geometric functions extracted from a structured and redundant basis. Transforming the pattern results in the transformation of its constituent parts. We show that, when the transformation is restricted to a synthesis of translations, rotations, and isotropic scalings, such a pattern representation results in a closed-form expression of the manifold equation with respect to the transformation parameters. The MD computation can then be formulated as a minimization problem whose objective function is expressed as the difference of convex functions (DC). This interesting property permits optimally solving the optimization problem with DC programming solvers that are globally convergent. We present experimental evidence which shows that our method is able to find the globally optimal solution, outperforming existing methods that yield suboptimal solutions. Index Terms--Transformation invariance, pattern manifolds, sparse approximations.

This paper presents a statistical approach to the preprocessing of degraded handwritten forms including the steps of binarization and form line removal. The degraded image is modeled by a Markov Random Field (MRF) where the hidden-layer prior probability is learned from a training set of high-quality binarized images and the observation probability density is learned on-the-fly from the gray-level histogram of the input image. We have modified the MRF model to drop the preprinted ruling lines from the image. We use the patch-based topology of the MRF and Belief Propagation (BP) for efficiency in processing. To further improve the processing speed, we prune unlikely solutions from the search space while solving the MRF. Experimental results show higher accuracy on two data sets of degraded handwritten images than previously used methods. Index Terms--Markov random field, image segmentation, document analysis, handwriting recognition.

We propose a five-layer hierarchical space-time model (HSTM) for representing and searching human actions in videos. From a features point of view, both invariance and selectivity are desirable characteristics, which seem to contradict each other. To make these characteristics coexist, we introduce a coarse-to-fine search and verification scheme for action searching, based on the HSTM model. Because going through layers of the hierarchy corresponds to progressively turning the knob between invariance and selectivity, this strategy enables search for human actions ranging from rapid movements of sports to subtle motions of facial expressions. The introduction of the Histogram of Gabor Orientations feature makes the searching for actions go smoothly across the hierarchical layers of the HSTM model. The efficient matching is achieved by applying integral histograms to compute the features in the top two layers. The HSTM model was tested on three selected challenging video sequences and on the KTH human action database. And it achieved improvement over other state-of-the-art algorithms. These promising results validate that the HSTM model is both selective and robust for searching human actions. Index Terms--Action recognition, action search, hierarchical space-time model (HSTM), Histogram of Gabor Orientations (HIGO).

An improved unsupervised classification method to extract and link places features and cluster recurrent physical locations (key-places) within a movie is presented. Our approach finds links between key frames of a common key-place based on the use of a probabilistic latent space model over the possible local matches between the key frames image set. This allows the extraction of significant groups of local matching descriptors that may represent characteristic elements of a key-place. An exhaustive evaluation of our approach was conducted on in-house and public image datasets, as well as on full-length movies. Results revealed that our method is very efficient for near-duplicate object/background detection with weak overlap. Performance measurements on full-length movies indicate a recognition rate of about 75% on the key-places clustering with a false alarm rate (FAR) of approximately 2%. Index Terms--Duplicate detection, scene categorization, scene matching, video description, video indexing.

Nowadays, electrical drives generally associate inverter and induction machine. Thus, these two elements must be taken into account in order to provide a relevant diagnosis of these electrical systems. In this context, the paper presents a diagnosis method based on a multidimensional function and pattern recognition (PR). Traditional formalism of the PR method has been extended with some improvements such as the automatic choice of the feature space dimension or a 'nonexclusive' decision rule based on the k-nearest neighbors. Thus, we introduce a new membership function, which takes into account the number of nearest neighbors as well as the distance from these neighbors with the sample to be classified. This approach is illustrated on a 5.5 kW inverter-fed asynchronous motor, in order to detect supply and motor faults. In this application, diagnostic features are only extracted from electrical measurements. Experimental results prove the efficiency of our diagnosis method. Index Terms--Data standardization, diagnosis, induction machine, inverter, membership function, nonexclusive decision rule, pattern recognition (PR), reliability index.

Kernel methods are a class of well established and successful algorithms for pattern analysis due to their mathematical elegance and good performance. Numerous nonlinear extensions of pattern recognition techniques have been proposed so far based on the so-called kernel trick. The objective of this paper is twofold. First, we derive an additional kernel tool that is still missing, namely kernel quadratic discriminant (KQD). We discuss different formulations of KQD based on the regularized kernel Mahalanobis distance in both complete and class-related subspaces. Second, we propose suitable extensions of kernel linear and quadratic discriminants to indefinite kernels. We provide classifiers that are applicable to kernels defined by any symmetric similarity measure. This is important in practice because problem-suited proximity measures often violate the requirement of positive definiteness. As in the traditional case, KQD can be advantageous for data with unequal class spreads in the kernel-induced spaces, which cannot be well separated by a linear discriminant. We illustrate this on artificial and real data for both positive definite and indefinite kernels. Index Terms--Machine learning, pattern recognition, kernel methods, indefinite kernels, discriminant analysis.

This paper introduces a novel binary discriminative learning technique based on the approximation of the nonlinear decision boundary by a piecewise linear smooth additive model. The decision border is geometrically defined by means of the characterizing boundary points--points that belong to the optimal boundary under a certain notion of robustness. Based on these points, a set of locally robust linear classifiers is defined and assembled by means of a Tikhonov regularized optimization procedure in an additive model to create a final [lambda]-smooth decision rule. As a result, a very simple and robust classifier with a strong geometrical meaning and nonlinear behavior is obtained. The simplicity of the method allows its extension to cope with some of today's machine learning challenges, such as online learning, large-scale learning of parallelization, with linear computational complexity. We validate our approach on the UCI database, comparing with several state-of-the-art classification techniques. Finally, we apply our technique in online and large-scale scenarios and in six real-life computer vision and pattern recognition problems: gender recognition based on face images, intravascular ultrasound tissue classification, speed traffic sign detection, Chagas' disease myocardial damage severity detection, old musical scores clef classification, and action recognition using 3D accelerometer data from a wearable device. The results are promising and this paper opens a line of research that deserves further attention. Index Terms--Classification, ensemble of classifiers, Gabriel neighboring rule, visual object recognition.

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. Index Terms--Graph matching, learning, support vector machines, structured estimation, optimization.

The evidential value of palmprints in forensic applications is clear as about 30 percent of the latents recovered from crime scenes are from palms. While biometric systems for palmprint-based personal authentication in access control type of applications have been developed, they mostly deal with low-resolution (about 100 ppi) palmprints and only perform full-to-full palmprint matching. We propose a latent-to-full palmprint matching system that is needed in forensic applications. Our system deals with palmprints captured at 500 ppi (the current standard in forensic applications) or higher resolution and uses minutiae as features to be compatible with the methodology used by latent experts. Latent palmprint matching is a challenging problem because latent prints lifted at crime scenes are of poor image quality, cover only a small area of the palm, and have a complex background. Other difficulties include a large number of minutiae in full prints (about 10 times as many as fingerprints), and the presence of many creases in latents and full prints. A robust algorithm to reliably estimate the local ridge direction and frequency in palmprints is developed. This facilitates the extraction of ridge and minutiae features even in poor quality palmprints. A fixed-length minutia descriptor, MinutiaCode, is utilized to capture distinctive information around each minutia and an alignment-based minutiae matching algorithm is used to match two palmprints. Two sets of partial palmprints (150 live-scan partial palmprints and 100 latent palmprints) are matched to a background database of 10,200 full palmprints to test the proposed system. Despite the inherent difficulty of latent-to-full palmprint matching, rank-1 recognition rates of 78.7 and 69 percent, respectively, were achieved in searching live-scan partial palmprints and latent palmprints against the background database. Index Terms--Palmprint, forensics, latents, minutiae, MinutiaCode, matching, region growing.

Problem statement: The study presented an efficient Iris recognition system. Approach: The design used the discrete cosine transform for feature extraction and artificial neural networks for classification. The iris images used in this system were obtained from the CASIA database. Results: A robust system for iris recognition was developed. Conclusion: An iris recognition system that produces very low error rates was successfully designed. Key words: iris, biometrics, CASIA database, cosine transform, artificial neural networks, feature extraction, INTRODUCTION In many applications, it is important to determine the identity of a person. Conventional methods of recognizing the identity of a person by using cards or passwords are not [...]

Problem statement: The study presented in this study to combined face and ear algorithms as an application of human identification. Biometric system to the detection and identification of human faces and ears developed a multimodal biometric system using eigenfaces and eigenears. Approach: The proposed system used the extracted face and ear images to develop the respective feature spaces via the PCA algorithm called eigenfaces and eigenears, respectively. The proposed system showed promising results than individual face or ear biometrics investigated in the experiments. Results: The final achieve was then used to affirm the person as genuine or an impostor. System was tested on several databases and gave an overall accuracy of 92.24% with FAR of 10% and FRR of 6.1%. Conclusion: The results display if we combined face and ear is a good technique because it offered a high accuracy and security. Key words: Face recognition, ear recognition, PCA, algorithms, eigenfaces, eigenears, pattern recognition, INTRODUCTION Biometrics refers to the use of physiological or biological characteristics to measure the identity of an individual. These features are unique to each individual and remain unaltered during a [...]

Problem statement: Offline recognition of handwritten Arabic text awaits accurate recognition solutions. Most of the Arabic letters have secondary components that are important in recognizing these letters. However these components have large writing variations. We targeted enhancing the feature extraction stage in recognizing handwritten Arabic text. Approach: In this study, we proposed a novel feature extraction approach of handwritten Arabic letters. Pre-segmented letters were first partitioned into main body and secondary components. Then moment features were extracted from the whole letter as well as from the main body and the secondary components. Using multi-objective genetic algorithm, efficient feature subsets were selected. Finally, various feature subsets were evaluated according to their classification error using an SVM classifier. Results: The proposed approach improved the classification error in all cases studied. For example, the improvements of 20-feature subsets of normalized central moments and Zernike moments were 15 and 10%, respectively. Conclusion/Recommendations: Extracting and selecting statistical features from handwritten Arabic letters, their main bodies and their secondary components provided feature subsets that give higher recognition accuracies compared to the subsets of the whole letters alone. Key words: Normalized central moments, Zernike moments, feature extraction, feature selection, handwritten Arabic letters, INTRODUCTION Arabic letters are used in about 27 writing languages including Arabic, Persian, Kurdish, Urdu and Jawi (1). Offline recognition of handwritten cursive text such as Arabic text is an [...]

This paper presents a novel independent component analysis (ICA) color space method for pattern recognition. The novelty of the ICA color space method is twofold: 1) deriving effective color image representation based on ICA, and 2) implementing efficient color image classification using the independent color image representation and an enhanced Fisher model (EFM). First, the ICA color space method assumes that each color image is defined by three independent source images, which can be derived by means of a blind source separation procedure, such as ICA. Unlike the RGB color space, where the R, G, and B component images are correlated, the new ICA color space method derives three component images [C.sub.1], [C.sub.2], and [C.sub.3] a that are independent and hence uncorrelated. Second, the three independent color component images are concatenated to form an augmented pattern vector, whose dimensionality is reduced by principal component analysis (PCA). An EFM then derives the discriminating features of the reduced pattern vector for pattern recognition. The effectiveness of the proposed ICA color space method is demonstrated using a complex grand challenge pattern recognition problem and a large scale database. In particular, the face recognition grand challenge (FRGC) and the biometric experimentation environment (BEE) reveal that for the most challenging FRGC version 2 Experiment 4, which contains 12 776 training images, 16 028 controlled target images, and 8014 uncontrolled query images, the ICA color space method achieves the face verification rate (ROC III) of 73.69 % at the false accept rate (FAR) of 0.1%, compared to the face verification rate (FVR) of 67.13% of the RGB color space (using the same EFM) and 11.86% of the FRGC baseline algorithm at the same FAR. Index Terms--Biometric experimentation environment (BEE), enhanced Fisher model (EFM), face recognition grand challenge (FRGC), independent component analysis (ICA) color space, pattern recognition, principal component analysis (PCA), RGB color space.

In a way similar to the string-to-string correction problem, we address discrete time series similarity in light of a time-series-to-time-series-correction problem for which the similarity between two time series is measured as the minimum cost sequence of edit operations needed to transform one time series into another. To define the edit operations, we use the paradigm of a graphical editing process and end up with a dynamic programming algorithm that we call Time Warp Edit Distance (TWED). (TWED) is slightly different in form from Dynamic Time Warping (DTW), Longest Common Subsequence (LCSS), or Edit Distance with Real Penalty (ERP) algorithms. In particular, it highlights a parameter that controls a kind of stiffness of the elastic measure along the time axis. We show that the similarity provided by TWED is a potentially useful metric in time series retrieval applications since it could benefit from the triangular inequality property to speed up the retrieval process while tuning the parameters of the elastic measure. In that context, a lower bound is derived to link the matching of time series into downsampled representation spaces to the matching into the original space. The empiric quality of the TWED distance is evaluated on a simple classification task. Compared to Edit Distance, DTW, LCSS, and ERP, TWED has proved to be quite effective on the considered experimental task. Index Term--Pattern recognition, time series, algorithms, similarity measures.

Low-complexity feature selection is analyzed in the context of visual recognition. It is hypothesized that high-order dependences of bandpass features contain little information for discrimination of natural images. This hypothesis is characterized formally by the introduction of the concepts of conjunctive interference and decomposability order of a feature set. Necessary and sufficient conditions for the feasibility of low-complexity feature selection are then derived in terms of these concepts. It is shown that the intrinsic complexity of feature selection is determined by the decomposability order of the feature set and not its dimension. Feature selection algorithms are then derived for all levels of complexity and are shown to be approximated by existing information-theoretic methods, which they consistently outperform. The new algorithms are also used to objectively test the hypothesis of low decomposability order through comparison of classification performance. It is shown that, for image classification, the gain of modeling feature dependencies has strongly diminishing returns: best results are obtained under the assumption of decomposability order 1. This suggests a generic law for bandpass features extracted from natural images: that the effect, on the dependence of any two features, of observing any other feature is constant across image classes. Index Terms--Feature extraction and construction, low complexity, natural image statistics, information theory, feature discrimination versus dependence, image databases, object recognition, texture, perceptual reasoning.

This paper proposes an uncorrelated multilinear discriminant analysis (UMLDA) framework for the recognition of multidimensional objects, known as tensor objects. Uncorrelated features are desirable in recognition tasks since they contain minimum redundancy and ensure independence of features. The UMLDA aims to extract uncorrelated discriminative features directly from tensorial data through solving a tensor-to-vector projection. The solution consists of sequential iterative processes based on the alternating projection method, and an adaptive regularization procedure is incorporated to enhance the performance in the small sample size (SSS) scenario. A simple nearest-neighbor classifier is employed for classification. Furthermore, exploiting the complementary information from differently initialized and regularized UMLDA recognizers, an aggregation scheme is adopted to combine them at the matching score level, resulting in enhanced generalization performance while alleviating the regularization parameter selection problem. The UMLDA-based recognition algorithm is then empirically shown on face and gait recognition tasks to outperform four multilinear subspace solutions (MPCA, DATER, GTDA, TR1DA) and four linear subspace solutions (Bayesian, LDA, ULDA, R-JD-LDA). Index Terms--Dimensionality reduction, face recognition, feature extraction, fusion, gait recognition, multilinear discriminant analysis, regularization, tensor objects.

Shape is a fundamental image feature used in content-based image-retrieval systems. This paper proposes a robust and effective shape feature, which is based on a set of orthogonal complex moments of images known as Zernike moments (ZMs). As the rotation of an image has an impact on the ZM phase coefficients of the image, existing proposals normally use magnitude-only ZM as the image feature. In this paper, we compare, by using a mathematical form of analysis, the amount of visual information captured by ZM phase and the amount captured by ZM magnitude. This analysis shows that the ZM phase captures significant information for image reconstruction. We therefore propose combining both the magnitude and phase coefficients to form a new shape descriptor, referred to as invariant ZM descriptor (IZMD). The scale and translation invariance of IZMD could be obtained by prenormalizing the image using the geometrical moments. To make the phase invariant to rotation, we perform a phase correction while extracting the IZMD features. Experiment results show that the proposed shape feature is, in general, robust to changes caused by image shape rotation, translation, and/or scaling. The proposed IZMD feature also outperforms the commonly used magnitude-only ZMD in terms of noise robustness and object discriminability. Index Terms--Invariant features, object recognition, phase, shape, Zernike moments (ZMs).

Feature subset selection is an important preprocessing step for pattern recognition, to discard irrelevant and redundant information, as well as to identify the most important attributes. In this paper, we investigate a computationally efficient solution to select the most important features for gait recognition. The specific technique applied is based on mutual information (MI), which evaluates the statistical dependence between two random variables and has an established relation with the Bayes classification error. Extending our earlier research, we show that a sequential selection method based on MI can provide an effective solution for high-dimensional human gait data. To assess the performance of the approach, experiments are carried out based on a 73-dimensional model-based gait features set and on a 64 by 64 pixels model-free gait symmetry map on the Southampton HiD Gait database. The experimental results confirm the effectiveness of the method, removing about 50% of the model-based features and 95% of the symmetry map's pixels without significant loss in recognition capability, which outperforms correlation and analysis-of-variance-based methods. Index Terms--Biometrics, feature selection, gait recognition, mutual information (MI).

Iris recognition has long been widely regarded as a highly accurate biometric despite the lack of independent large-scale testing of its performance. Recently, however, three third-party evaluations of iris recognition were performed. This paper compares and contrasts the results of these independent evaluations. We find that despite differences in methods, hardware, and/or software, all three studies report error rates of the same order of magnitude: observed false nonmatch rates from 0.0122 to 0.03847 at a false match rate of 0.001. Furthermore, the differences between the best performers' error rates are an order of magnitude smaller than the observed error rates. Index Terms--Biometrics, evaluation, iris recognition, meta-analysis.

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. Index Terms--Shape registration, shape modeling, uncertainty estimates, nonparametric statistics, variable metric kernels.

This paper proposes a novel method for fast pattern matching based on dissimilarity functions derived from the [L.sub.p] norm, such as the Sum of Squared Differences (SSD) and the Sum of Absolute Differences (SAD). The proposed method is a full-search equivalent, i.e., it yields the same results as the Full Search (FS) algorithm. In order to pursue computational savings, the method deploys a succession of increasingly tighter lower bounds of the adopted [L.sub.p] norm-based dissimilarity function. Such bounding functions allow for establishing a hierarchy of pruning conditions aimed at rapidly skipping those candidates that cannot satisfy the matching criterion. The paper includes an experimental comparison between the proposed method and other FS-equivalent approaches known in the literature, which proves the remarkable computational efficiency of our proposal. Index Terms--Pattern matching, IDA, SSD, SAD, efficient, full-search equivalent.

Little attention has been paid so far to physiological signals for emotion recognition compared to audiovisual emotion channels such as facial expression or speech. This paper investigates the potential of physiological signals as reliable channels for emotion recognition. All essential stages of an automatic recognition system are discussed, from the recording of a physiological data set to a feature-based multiclass classification. In order to collect a physiological data set from multiple subjects over many weeks, we used a musical induction method that spontaneously leads subjects to real emotional states, without any deliberate laboratory setting. Four-channel biosensors were used to measure electromyogram, electrocardiogram, skin conductivity, and respiration changes. A wide range of physiological features from various analysis domains, including time/frequency, entropy, geometric analysis, subband spectra, multiscale entropy, etc., is proposed in order to find the best emotion-relevant features and to correlate them with emotional states. The best features extracted are specified in detail and their effectiveness is proven by classification results. Classification of four musical emotions (positive/high arousal, negative/high arousal, negative/low arousal, and positive/low arousal) is performed by using an extended linear discriminant analysis (pLDA). Furthermore, by exploiting a dichotomic property of the 2D emotion model, we develop a novel scheme of emotion-specific multilevel dichotomous classification (EMDC) and compare its performance with direct multiclass classification using the pLDA. An improved recognition accuracy of 95 percent and 70 percent for subject-dependent and subject-independent classification, respectively, is achieved by using the EMDC scheme. Index Terms--Emotion recognition, physiological signal, biosignal, skin conductance, electrocardiogram, electromyogram, respiration, affective computing, human-computer interaction, musical emotion, autonomic nervous system, arousal, valence.

A recent paper [1] proposed a provably optimal polynomial time method for performing near-isometric point pattern matching by means of exact probabilistic inference in a chordal graphical model. Its fundamental result is that the chordal graph in question is shown to be globally rigid, implying that exact inference provides the same matching solution as exact inference in a complete graphical model. This implies that the algorithm is optimal when there is no noise in the point patterns. In this paper, we present a new graph that is also globally rigid but has an advantage over the graph proposed in [1]: Its maximal clique size is smaller, rendering inference significantly more efficient. However, this graph is not chordal, and thus, standard Junction Tree algorithms cannot be directly applied. Nevertheless, we show that loopy belief propagation in such a graph converges to the optimal solution. This allows us to retain the optimality guarantee in the noiseless case, while substantially reducing both memory requirements and processing time. Our experimental results show that the accuracy of the proposed solution is indistinguishable from that in [1] when there is noise in the point patterns. Index Terms--Point pattern matching, graph matching, graphical models, belief propagation, global rigidity, chordal graphs.

For quick access to new handwritten collections, current handwriting recognition methods are too cumbersome. They cannot deal with the lack of labeled data and would require extensive laboratory training for each individual script, style, language, and collection. We propose a biologically inspired whole-word recognition method that is used to incrementally elicit word labels in a live Web-based annotation system, named Monk. Since human labor should be minimized given the massive amount of image data, it becomes important to rely on robust perceptual mechanisms in the machine. Recent computational models of the neurophysiology of vision are applied to isolated word classification. A primate cortex-like mechanism allows us to classify text images that have a low frequency of occurrence. Typically, these images are the most difficult to retrieve and often contain named entities and are regarded as the most important to people. Usually, standard pattern-recognition technology cannot deal with these text images if there are not enough labeled instances. The results of this retrieval system are compared to normalized word-image matching and appear to be very promising. Index Terms--Digital libraries, image retrieval, computer vision, machine learning, computational neuroscience, pattern recognition, handwriting retrieval, Gabor filtering.

In this work, we systematically study the problem of event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which video clip similarity plays an important role. First, we represent a video clip as a bag of orderless descriptors extracted from all of the constituent frames and apply the earth mover's distance (EMD) to integrate similarities among frames from two clips. Observing that a video clip is usually comprised of multiple subclips corresponding to event evolution over time, we further build a multilevel temporal pyramid. At each pyramid level, we integrate the information from different subclips with Integer-value-constrained EMD to explicitly align the subclips. By fusing the information from the different pyramid levels, we develop Temporally Aligned Pyramid Matching (TAPM) for measuring video similarity. We conduct comprehensive experiments on the TRECVID 2005 corpus, which contains more than 6,800 clips. Our experiments demonstrate that 1) the TAPM multilevel method clearly outperforms single-level EMD (SLEMD) and 2) SLEMD outperforms keyframe and multiframe-based detection methods by a large margin. In addition, we conduct in-depth investigation of various aspects of the proposed techniques such as weight selection in SLEMD, sensitivity to temporal clustering, the effect of temporal alignment, and possible approaches for speedup. Extensive analysis of the results also reveals intuitive interpretation of video event recognition through video subclip alignment at different levels. Index Terms--Event recognition, news video, concept ontology, Temporally Aligned Pyramid Matching, video indexing, earth mover's distance.

This paper presents novel homotopic image pseudo-invariants for face recognition based on pixelwise analysis. An exemplar face and test images are matched and the most similar image is determined first. The homotopic image pseudo-invariants are calculated next to judge whether the most similar image contains the same person as the exemplar. The proposed method can be applied to openset recognition. The recognition task can be performed with or without face databases, while the recognition rate is higher when a database is available. This fact facilitates the recognition of faces and various other objects on the Internet. We benchmark the method using FERET and PIE, as well as images downloaded from the Internet. Index Terms--Face recognition, content-based image retrieval, open set recognition, homotopic image pseudo-invariants.