Spectral recognition using a modified Eckhorn neural network model

Studies of the visual cortex of the cat highlight the role of temporal processing using synchronous oscillations for object identification. In this paper, the original neural network model of Eckhorn has been modified according to the proposal of Johnson and others and used for spectral recognition. The method developed turns out to be a much simpler, faster and elegant way of spectral recognition than reported elsewhere.     

Robust Hausdorff distance measure for face recognition

Face is considered to be one of the biometrics in automatic person identification. The non-intrusive nature of face recognition makes it an attractive choice. For face recognition system to be practical, it should be robust to variations in illumination, pose and expression as humans recognize faces irrespective of all these variations. In this paper, an attempt to address these issues is made using a new Hausdorff distance-based measure. The proposed measure represent the gray values of pixels in face images as vectors giving the neighborhood intensity distribution of the pixels. The transformation is expected to be less sensitive to illumination variations besides preserving the appearance of face embedded in the original gray image. While the existing Hausdorff distance-based measures are defined between the binary edge images of faces which contains primarily structural information, the proposed measure gives the dissimilarity between the appearance of faces. An efficient method to compute the proposed measure is presented. The performance of the method on bench mark face databases shows that it is robust to considerable variations in pose, expression and illumination. Comparison with some of the existing Hausdorff distance-based methods shows that the proposed method performs better in many cases.     

Interval type-2 fuzzy logic and modular neural networks for face recognition applications

In this paper we present a method for response integration in multi-net neural systems using interval type-2 fuzzy logic and fuzzy integrals, with the purpose of improving the performance in the solution of problems with a great volume of information. The method can be generalized for pattern recognition and prediction problems, but in this work we show the implementation and tests of the method applied to the face recognition problem using modular neural networks. In the application we use two interval type-2 fuzzy inference systems (IT2-FIS); the first IT2-FIS was used for feature extraction in the training data, and the second one to estimate the relevance of the modules in the multi-net system. Fuzzy logic is shown to be a tool that can help improve the results of a neural system by facilitating the representation of human perceptions.     

Robust face recognition via occlusion dictionary learning

Sparse representation based classification (SRC) has recently been proposed for robust face recognition. To deal with occlusion, SRC introduces an identity matrix as an occlusion dictionary on the assumption that the occlusion has sparse representation in this dictionary. However, the results show that SRC's use of this occlusion dictionary is not nearly as robust to large occlusion as it is to random pixel corruption. In addition, the identity matrix renders the expanded dictionary large, which results in expensive computation. In this paper, we present a novel method, namely structured sparse representation based classification (SSRC), for face recognition with occlusion. A novel structured dictionary learning method is proposed to learn an occlusion dictionary from the data instead of an identity matrix. Specifically, a mutual incoherence of dictionaries regularization term is incorporated into the dictionary learning objective function which encourages the occlusion dictionary to be as independent as possible of the training sample dictionary. So that the occlusion can then be sparsely represented by the linear combination of the atoms from the learned occlusion dictionary and effectively separated from the occluded face image. The classification can thus be efficiently carried out on the recovered non-occluded face images and the size of the expanded dictionary is also much smaller than that used in SRC. The extensive experiments demonstrate that the proposed method achieves better results than the existing sparse representation based face recognition methods, especially in dealing with large region contiguous occlusion and severe illumination variation, while the computational cost is much lower.     

Bimode model for face recognition and face representation

Tensorface based approaches decompose an image into its constituent factors (i.e., person, lighting, viewpoint, etc.), and then utilize these factor spaces for recognition. However, tensorface is not a preferable choice, because of the complexity of its multimode. In addition, a single mode space, except the person-space, could not be used for recognition directly. From the viewpoint of practical application, we propose a bimode model for face recognition and face representation. This new model can be treated as a simplified model representation of tensorface. However, their respective algorithms for training are completely different, due to their different definitions of subspaces. Thanks to its simpler model form, the proposed model requires less iteration times in the process of training and testing. Moreover bimode model can be further applied to an image reconstruction and image synthesis via an example image. Comprehensive experiments on three face image databases (PEAL, YaleB frontal and Weizmann) validate the effectiveness of the proposed new model.     

Robust face recognition using 2D and 3D data: Pose and illumination compensation

The paper addresses the problem of face recognition under varying pose and illumination. Robustness to appearance variations is achieved not only by using a combination of a 2D color and a 3D image of the face, but mainly by using face geometry information to cope with pose and illumination variations that inhibit the performance of 2D face recognition. A face normalization approach is proposed, which unlike state-of-the-art techniques is computationally efficient and does not require an extended training set. Experimental results on a large data set show that template-based face recognition performance is significantly benefited from the application of the proposed normalization algorithms prior to classification.     

Robust detection of outliers for projection-based face recognition methods

In this paper, the impact of outliers on the performance of high-dimensional data analysis methods is studied in the context of face recognition. Most of the existing face recognition methods are based on PCA-like methods: faces are projected into a lower dimensional space in which similarity between faces is supposed to be more easily evaluated. These methods are, however, very sensitive to the quality of the face images used in the training and in the recognition phases. Their performance significantly drops when face images are not well centered or taken under variable illumination conditions. In this paper, we study this phenomenon for two face recognition methods, namely PCA and LDA2D, and we propose a filtering process that allows the automatic selection of noisy face images which are responsible for the performance degradation. This process uses two techniques. The first one is based on the recently proposed robust high-dimensional data analysis method called RobPCA. It is specific to the case of recognition from video sequences. The second technique is based on a novel and effective face classification technique. It allows isolating still face images that are not very precisely cropped, not well-centered or in a non-frontal pose. Experiments show that this filtering process significantly improves recognition rates by 10 to 30%.

Speech recognition using a stereo vision neural network model

This paper describes a new algorithm for speech recognition by using stereo vision pattern recognition equations with competition and cooperation. In our research, we applied recently developed 3-layered neural net (3LNN) equations to speech recognition. Our proposed acoustic models using these equations yield better recognition results than the hidden Markov model (HMM). When using a 216 (240) word database, stereo vision acoustic models gave 6.5% (6.6%) higher accuracy than HMMs. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999     

Pose-invariant face recognition using a 3D deformable model

The paper proposes a novel, pose-invariant face recognition system based on a deformable, generic 3D face model, that is a composite of: (1) an edge model, (2) a color region model and (3) a wireframe model for jointly describing the shape and important features of the face. The first two submodels are used for image analysis and the third mainly for face synthesis. In order to match the model to face images in arbitrary poses, the 3D model can be projected onto different 2D viewplanes based on rotation, translation and scale parameters, thereby generating multiple face-image templates (in different sizes and orientations). Face shape variations among people are taken into account by the deformation parameters of the model. Given an unknown face, its pose is estimated by model matching and the system synthesizes face images of known subjects in the same pose. The face is then classified as the subject whose synthesized image is most similar. The synthesized images are generated using a 3D face representation scheme which encodes the 3D shape and texture characteristics of the faces. This face representation is automatically derived from training face images of the subject. Experimental results show that the method is capable of determining pose and recognizing faces accurately over a wide range of poses and with naturally varying lighting conditions. Recognition rates of 92.3% have been achieved by the method with 10 training face images per person.     

Robust 3D face recognition based on resolution invariant features

A novel resolution invariant local feature based method is proposed for 3D face recognition. Scale space extrema on shape index images and texture images are detected and matched, through which resolution and noise insensitive face matching is achieved without complex preprocessing and normalization. An outlier removal strategy is designed to eliminate incorrect matching points while keeping relevant ones. Six different scale invariant similarity measures are proposed and fused at the score level, which increases the robustness against expression variations. Systematical experiments are conducted on the FRGC v2.0 database, achieving in the neutral vs. all experiment a verification rate of 90.7% with un-normalized similarity scores, and 96.3% with normalized similarity scores at False Acceptance Rate (FAR) of 0.1%, and 96.2% rank-1 identification rate, which are comparable to the state of the art, and promising considering the significantly reduced preprocessing requirement.     

Solving the small sample size problem in face recognition using generalized discriminant analysis

The goal of face recognition is to distinguish persons via their facial images. Each person's images form a cluster, and a new image is recognized by assigning it to the correct cluster. Since the images are very high-dimensional, it is necessary to reduce their dimension. Linear discriminant analysis (LDA) has been shown to be effective at dimension reduction while preserving the cluster structure of the data. It is classically defined as an optimization problem involving covariance matrices that represent the scatter within and between clusters. The requirement that one of these matrices be nonsingular restricts its application to datasets in which the dimension of the data does not exceed the sample size. For face recognition, however, the dimension typically exceeds the number of images in the database, resulting in what is referred to as the small sample size problem. Recently, the applicability of LDA has been extended by using the generalized singular value decomposition (GSVD) to circumvent the nonsingularity requirement, thus making LDA directly applicable to face recognition data. Our experiments confirm that LDA/GSVD solves the small sample size problem very effectively as compared with other current methods.     

Exploring album structure for face recognition in online social networks

In this paper, we propose an album-oriented face-recognition model that exploits the album structure for face recognition in online social networks. Albums, usually associated with pictures of a small group of people at a certain event or occasion, provide vital information that can be used to effectively reduce the possible list of candidate labels. We show how this intuition can be formalized into a model that expresses a prior on how albums tend to have many pictures of a small number of people. We also show how it can be extended to include other information available in a social network. Using two real-world datasets independently drawn from Facebook, we show that this model is broadly applicable and can significantly improve recognition rates.     

Real-time face tracking and recognition by sparse eigentracker with associative mapping to 3D shape

This paper proposes a novel framework of real-time face tracking and recognition by combining two eigen-based methods. The first method is a novel extension of eigenface called augmented eigenface and the second method is a sparse 3D eigentemplate tracker controlled by a particle filter. The augmented eigenface is an eigenface augmented by an associative mapping to 3D shape that is specified by a set of volumetric face models. This paper discusses how to make up the augmented eigenface and how it can be used for inference of 3D shape from partial images. The associative mapping is also generalized to subspace-to-one mappings to cover photometric image changes for a fixed shape. A novel technique, called photometric adjustment, is introduced for simple implementation of associative mapping when an image subspace should be combined to a shape. The sparse 3D eigentemplate tracker is an extension of the 3D template tracker proposed by Oka et al. In combination with the augmented eigenface, the sparse 3D eigentemplate tracker facilitates real-time 3D tracking and recognition when a monocular image sequence is provided. In the tracking, sparse 3D eigentemplate is updated by the augmented eigenface while face pose is estimated by the sparse eigentracker. Since the augmented eigenface is constructed on the conventional eigenfaces, face identification and expression recognition are also accomplished efficiently during the tracking. In the experiment, an augmented eigenface was constructed from 25 faces where 24 images were taken in different lighting conditions for each face. Experimental results show that the augmented eigenface works with the 3D eigentemplate tracker for real-time tracking and recognition.     

High-throughput-derived biologically-inspired features for unconstrained face recognition

Many modern computer vision algorithms are built atop of a set of low-level feature operators (such as SIFT [23,24]; HOG [8,3]; or LBP [1,2]) that transform raw pixel values into a representation better suited to subsequent processing and classification. While the choice of feature representation is often not central to the logic of a given algorithm, the quality of the feature representation can have critically important implications for performance. Here, we demonstrate a large-scale feature search approach to generating new, more powerful feature representations in which a multitude of complex, nonlinear, multilayer neuromorphic feature representations are randomly generated and screened to find those best suited for the task at hand. In particular, we show that a brute-force search can generate representations that, in combination with standard machine learning blending techniques, achieve state-of-the-art performance on the Labeled Faces in the Wild (LFW) [19] unconstrained face recognition challenge set. These representations outperform previous state-of-the-art approaches, in spite of requiring less training data and using a conceptually simpler machine learning backend. We argue that such large-scale-search-derived feature sets can play a synergistic role with other computer vision approaches by providing a richer base of features with which to work.     

Shape recognition using eigenvalues of the Dirichlet Laplacian

The eigenvalues of the Dirichlet Laplacian are used to generate three different sets of features for shape recognition and classification in binary images. The generated features are rotation-, translation-, and size-invariant. The features are also shown to be tolerant of noise and boundary deformation. These features are used to classify hand-drawn, synthetic, and natural shapes with correct classification rates ranging from 88.9% to 99.2%. The classification was done using few features (only two features in some cases) and simple feedforward neural networks or minimum Euclidian distance.     

Human face profile recognition using attributed string

A new attributed string matching method for human face profile recognition is proposed in this work. It is a novel idea to apply structural and syntactic technique on face profile matching. The approach works on a chain of profile line segments and highlights the favor of curve matching by suppressing the operations of insert and delete. The technique relies mainly on the merge and change operations of string to tackle the inconsistency problem of feature point detection. A quadratic penalty function is proposed to prohibit large angle changes and overmerging. The method produces very encouraging results and is found to be suitable for similar shape classification.     

A novel statistical generative model dedicated to face recognition

In this paper, a novel statistical generative model to describe a face is presented, and is applied to the face authentication task. Classical generative models used so far in face recognition, such as Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs) for instance, are making strong assumptions on the observations derived from a face image. Indeed, such models usually assume that local observations are independent, which is obviously not the case in a face. The presented model hence proposes to encode relationships between salient facial features by using a static Bayesian Network. Since robustness against imprecisely located faces is of great concern in a real-world scenario, authentication results are presented using automatically localised faces. Experiments conducted on the XM2VTS and the BANCA databases showed that the proposed approach is suitable for this task, since it reaches state-of-the-art results. We compare our model to baseline appearance-based systems (Eigenfaces and Fisherfaces) but also to classical generative models, namely GMM, HMM and pseudo-2DHMM.     

Determining plane orientation from specular reflectance

This paper describes methods of estimating the orientation of a planar surface from the shapes of the contours of constant brightness on the surface, using perspective projection. It is assumed that the illumination is from a distant point source in a known direction. Two reflectance models, proposed respectively by Horn and Pentland, are used.     

Variable lighting face recognition using discrete wavelet transform

This paper presents a new discrete wavelet transform (DWT) based illumination normalization approach for face recognition under varying lighting conditions. Our method consists of three steps. Firstly, DWT-based denoising technique is employed to detect the illumination discontinuities in the detail subbands. And the detail coefficients are updated with using the obtained discontinuity information. Secondly, a smooth version of the input image is obtained by applying the inverse DWT on the updated wavelet coefficients. Finally, multi-scale reflectance model is presented to extract the illumination invariant features. The merit of the proposed method is it can preserve the illumination discontinuities when smoothing image. Thus it can reduce the halo artifacts in the normalized images. Moreover, only one parameter involved and the parameter selection process is simple and computationally fast. Experiments are carried out upon the Yale B and CMU PIE face databases, and the results demonstrate the proposed method can achieve satisfactory recognition rates under varying illumination conditions.