Abstract—Techniques that can introduce low-dimensional feature representation with enhanced discriminatory power is of paramount importance in face recognition (FR) systems. It is well known that the distribution of face images, under a perceivable variation in viewpoint, illumination or facial expression, is highly nonlinear and complex. It is, therefore, not surprising that linear techniques, such as those based on principle component analysis (PCA) or linear discriminant analysis (LDA), cannot provide reliable and robust solutions to those FR problems with complex face variations. In this paper, we propose a kernel machine-based discriminant analysis method, which deals with the nonlinearity of the face patterns ’ distribution. The proposed method also effectively solves the so-called “small sample size ” (SSS) problem, which exists in most FR tasks. The new algorithm has been tested, in terms of classification error rate performance, on the multiview UMIST face database. Results indicate that the proposed methodology is able to achieve excellent performance with only a very small set of features being used, and its error rate is approximately 34 % and 48 % of those of two other commonly used kernel FR approaches, the kernel-PCA (KPCA) and the generalized discriminant analysis (GDA), respectively. Index Terms—Face recognition (FR), kernel direct discriminant analysis (KDDA), linear discriminant analysis (LDA), principle component analysis (PCA), small sample size problem (SSS), kernel methods. I.

Face recognition is a rapidly growing research area due to increasing demands for security in commercial and law enforcement applications. This paper provides an up-to-date review of research efforts in face recognition techniques based on two-dimensional (2D) images in the visual and infrared (IR) spectra. Face recognition systems based on visual images have reached a significant level of maturity with some practical success. However, the performance of visual face recognition may degrade under poor illumination conditions or for subjects of various skin colors. IR imagery represents a viable alternative to visible imaging in the search for a robust and practical identification system. While visual face recognition systems perform relatively reliably under controlled illumination conditions, thermal IR face recognition systems are advantageous when there is no control over illumination or for detecting disguised faces. Face recognition using 3D images is another active area of face recognition, which provides robust face recognition with changes in pose. Recent research has also demonstrated that the fusion of different imaging modalities and spectral components can improve the overall performance of face recognition.

We present in this paper an Independent Gabor Features (IGF) method and its application to face recognition. The novelty of the IGF method comes from (i) the derivation of independent Gabor features in the feature extraction stage, and (ii) the development of an IGF features-based Probabilistic Reasoning Model (PRM) classification method in the pattern recognition stage. In particular, the IGF method first derives a Gabor feature vector from a set of downsampled Gabor wavelet representations of face images, then reduces the dimensionality of the vector by means of Principal Component Analysis (PCA), and finally defines the independent Gabor features based on the Independent Component Analysis (ICA). The independence property of these Gabor features facilitates the application of the PRM method for classification. The rationale behind integrating the Gabor wavelets and the ICA is two-fold. On the one hand, the Gabor transformed face images exhibit strong characteristics of spatial locality, scale and orientation selectivity. These images can thus produce salient local features that are most suitable for face recognition. On the other hand, ICA would further reduce redundancy and represent independent features explicitly. These independent features are most useful for subsequent pattern discrimination and associative recall. Experiments on face recognition using the FERET and the Chengjun Liu is with the Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102. E-mail: liu@cs.njit.edu.

Abstract not found

A biologically detailed computational model is described of how categorization judgments become automatic in tasks that depend on procedural learning. The model assumes 2 neural pathways from sensory association cortex to the premotor area that mediates response selection. A longer and slower path projects to the premotor area via the striatum, globus pallidus, and thalamus. A faster, purely cortical path projects directly to the premotor area. The model assumes that the subcortical path has greater neural plasticity because of a dopamine-mediated learning signal from the substantia nigra. In contrast, the cortical-cortical path learns more slowly via (dopamine independent) Hebbian learning. Because of its greater plasticity, early performance is dominated by the subcortical path, but the development of automaticity is characterized by a transfer of control to the faster cortical-cortical projection. The model, called SPEED (Subcortical Pathways Enable Expertise Development), includes differential equations that describe activation in the relevant brain areas and difference equations that describe the 2- and 3-factor learning. A variety of simulations are described, showing that the model accounts for some classic single-cell recording and behavioral results.

Abstract—A feature extractor and neural classifier for image recognition systems are proposed. The proposed feature extractor is based on the concept of random local descriptors (RLDs). It is followed by the encoder that is based on the permutation coding technique that allows to take into account not only detected features but also the position of each feature on the image and to make the recognition process invariant to small displacements. The combination of RLDs and permutation coding permits us to obtain a sufficiently general description of the image to be recognized. The code generated by the encoder is used as an input data for the neural classifier. Different types of images were used to test the proposed image recognition system. It was tested in the handwritten digit recognition problem, the face recognition problem, and the microobject shape recognition problem. The results of testing are very promising. The error rate for the Modified National Institute of Standards and Technology (MNIST) database is 0.44 % and for the Olivetti Research Laboratory (ORL) database it is 0.1%. Index Terms—Face recognition, handwritten digit recognition, MNIST database, Olivetti Research Laboratory (ORL) database, permutation coding neural classifier. I.

Abstract—When the feature dimension is larger than the number of samples the small sample-size problem occurs. There is great concern about it within the face recognition community. We point out that optimizing the Fisher index in linear discriminant analysis does not necessarily give the best performance for a face recognition system. We propose a new regularization scheme. The proposed method is evaluated using the Olivetti Research Laboratory database, the Yale database, and the Feret database. Index Terms—Face recognition, optimization, regularized discriminant analysis (RDA), small sample-size problem. I.

Abstract—This paper proposes a new face recognition approach by using the Discrete Cosine Transform (DCT) and hybrid flexible neural tree (FNT) classification model. The DCT is employed to extract the input features to build a face recognition system, and the flexible neural tree is used to identify the faces. Based on the pre-defined instruction/operator sets, a flexible neural tree model can be created and evolved. This framework allows input features selection, over-layer connections and different activation functions for the various nodes involved. The FNT structure is developed using an evolutionary algorithm and the parameters are optimized by a particle swarm optimization algorithm. Empirical results indicate that the proposed framework is efficient for face recognition. I.

Face recognition has been of interest to a growing number of researchers due to its applications on security. Within past years, there are numerous face recognition algorithms proposed by researchers. However, there is no unified framework for the integration. In this paper, we implement different existing well-known algorithms, Eigenface, Fisherface, Elastic Graph Matching (EGM), Support Vector Machine (SVM) and neural network, to give a comprehensive testing under same face databases. Moreover, we present a Face Recognition Committee Machine (FRCM), which is a novel approach for assembling the outputs of various face recognition algorithms to obtain a unified decision with improved accuracy. The machine consists of an ensemble of the above algorithms to cope with various face images. We have tested our system with ORL face database and Yale face database. A comparative experimental result of different algorithms with the committee machine demonstrates that the proposed system achieves improved accuracy over the individual algorithms.

This paper introduces a novel discriminant moment-based method as a feature extraction technique for face recognition. In this method, pseudo Zernike moments are performed before the application of Fisher’s Linear Discriminant to achieve a stable numerical computation and good generalization in small-sample-size problems. Fisher’s Linear Discriminant uses pseudo Zernike moments to derive an enhanced subset of moment features by maximizing the between-class scatter, while minimizing the within-class scatter, which leads to a better discrimination and classification performance. Experimental results show that the proposed method achieves superior performance with a recognition rate of 97.51 % in noise free environment and 97.12 % in noise induced environment for the Essex Face94 database. For the Essex Face95 database, the recognition rates obtained are 91.73 % and 90.30 % in noise free and noise induced environments, respectively. ACM Classification: I.5.4. (Computer Methodologies-Pattern Recognition – Applications) 1.