Appearance-based Face Recognition Research Articles

Anatomization of the systems of dimension relaxation for facial recognition

Face recognition is the most efficient image analysis application, and the reduction of dimensionality is an essential requirement. The curse of dimensionality occurs with the increase in dimensionality, the sample density decreases exponentially. Dimensionality Reduction is the process of taking into account the dimensionality of the feature space by obtaining a set of principal features. The purpose of this manuscript is to demonstrate a comparative study of Principal Component Analysis and Linear Discriminant Analysis methods which are two of the highly popular appearance-based face recognition projection methods. PCA creates a flat dimensional data representation that describes as much data variance as possible, while LDA finds the vectors that best discriminate between classes in the underlying space. The main idea of PCA is to transform high dimensional input space into the function space that displays the maximum variance. Traditional LDA feature selection is obtained by maximizing class differences and minimizing class distance.

New Variants of Global-Local Partial Least Squares Discriminant Analysis for Appearance-Based Face Recognition

We propose new appearance-based face recognition methods based on global-local structure-preserving partial least squares discriminant analysis. Two variants of the method are described in this article: the neighbourhood-preserving partial least squares discriminant analysis (NPPLS-DA) and the uncorrelated NPPLS-DA (UNNPPLS-DA). In contrast to standard partial least squares discriminant analysis (PLS-DA), which effectively only recognizes the global Euclidean structure of the face space, both NPPLS-DA and UNNPPLS-DA are designed to find an embedding that preserves both the global and local neighbourhood information and obtain a face subspace that best detects the essential manifold structure of the face space. Unlike global-local features extracted using other methods, the global-local PLS-DA features are obtained by maximizing covariance between data matrix and a response matrix which is coded with the class structure of the data. Furthermore, in UNPPLS-DA, an uncorrelated constraint is introduced into the objective function of NPPLS-DA to extract uncorrelated features that are important in many pattern recognition problems. We compare the proposed NPPLS-DA and UNPPLS-DA methods with several competing methods on six different face databases. The experimental results show that the proposed NPPLS-DA and UNPPLS-DA methods provide better representation and consistently achieve higher recognition rates in face recognition than the other competing methods.

A robust wavelet based decomposition of facial images to improve recognition accuracy in standard appearance based statistical face recognition methods

In traditional appearance based face recognition approaches, the facial images in standard face databases are used as it is for testing standard statistical face recognition algorithms. Due to the camera angle, position and lightening conditions, the facial image captured contains occlusion. Human pose, facial expressions and alignment of face with respect to camera axis also result in occluded image. Sometimes the background of the face also covered during the facial image capturing. We proposed an approach, called wavelet based facial image decomposition (WBFD) and in this approach the facial images are decomposed using two levels wavelet transform. In the faces obtained after two level wavelet decomposition, the occlusion and background images are suppressed. The face images from Yale database are used for our experiments. In order to test the performance of proposed WBFD approach, the face images obtained from WBFD approach, resized Yale face and Yale face from the original Yale face database are tested with five standard statistical appearance based face recognition algorithms such as eigen face, Fischer discriminant analysis, kernel principal component analysis, independent component analysis and 2D principal component analysis. The experimental results obtained show that, the proposed WBFD approach gives high recognition accuracy and require minimum recognition time in seconds for all the five face recognition methods.

A supervised multimanifold method with locality preserving for face recognition using single sample per person

Although real-world experiences show that preparing one image per person is more convenient, most of the appearance-based face recognition methods degrade or fail to work if there is only a single sample per person (SSPP). In this work, we introduce a novel supervised learning method called supervised locality preserving multimanifold (SLPMM) for face recognition with SSPP. In SLPMM, two graphs: within-manifold graph and between-manifold graph are made to represent the information inside every manifold and the information among different manifolds, respectively. SLPMM simultaneously maximizes the between-manifold scatter and minimizes the within-manifold scatter which leads to discriminant space by adopting locality preserving projection (LPP) concept. Experimental results on two widely used face databases FERET and AR face database are presented to prove the efficacy of the proposed approach.

Local appearance-based face recognition using adaptive directional wavelet transform

The latest research has shown that adaptive directional wavelet transform can constitute edges and textures in images efficiently due to the adaptive directional selectivity. This paper is primarily focused on the application of adaptive directional wavelet transform in conjunction with linear discriminant analysis (LDA) for capturing the discriminant directional multiresolution facial features. The intention of this paper is to explore the efficacy of adaptive directional wavelet transform in facial feature extraction and to offer a stepping stone for further research in this direction. The proposed approach is compared with existing subspace and local descriptor feature extraction methods. A performance comparison is also demonstrated with existing non-adaptive multiresolution analysis methods such as discrete wavelet transform (DWT), Gabor wavelet transform (GWT), curvelets, ridgelets, contourlets, and local Gabor binary pattern. Evaluation of the proposed approach on famous databases such as ORL, Essex Grimace, Yale, and Sterling face convinces the effectiveness of the adaptive directional wavelet transform based subspace features.

Two-dimensional exponential discriminant analysis for small sample size in face recognition

Appearance-based face recognition methods usually require converting 2D face images to 1D column vectors. Due to high dimensionality and few available samples, the performance becomes unsatisfactory. In this paper, we propose a novel technique called two-dimensional exponential discriminant analysis 2DEDA which extracts important features for classification directly from 2D face images. 2DEDA is especially suitable when the available sample size is small. Experimental results on two publicly available datasets viz. AR and CMU-PIE demonstrate the efficacy of the proposed technique, outperforming two-dimensional principal component analysis 2DPCA and two-dimensional linear discriminant analysis 2DLDA. The performance of the algorithms is evaluated in terms of average classification accuracy.

An enhanced representation of thermal faces for improving local appearance-based face recognition

AbstractThis paper proposes a new methodology to improve appearance-based thermal face recognition methods by using an enhanced representation of the thermal face information. This new representation is obtained by combining the pixels of the thermal face image and the vascular network information that is extracted from the same thermal face image. The effect of using the enhanced representation is evaluated for 5 different face recognition methods (LBP, WLD, GABOR, SIFT, SURF) in two public thermal face databases (Equinox and UCHThermalFace). The experimental results show that the proposed enhanced representation improves the performance of most of the analyzed appearance-based methods. The largest improvements are obtained when this representation is used together with methods based on the Gabor Jet Descriptor (GJD), the Weber Linear Discriminant (WLD) and Speeded Up Robust Features (SURF). In general terms the improvement is larger in indoor setups than in outdoors.

RECOGNIZING FACES USING INDIVIDUAL EIGEN SUBSPACES TECHNIQUE WITH FUZZY RULES METHODOLOGY

This paper proposes a new methodology of recognizing face using Individual Eigen Subspaces and it’s implemented in the field of Image Processing for Personnel verification or recognition. A major objective of this work is to develop a tool for face recognition, which can help in quicker and effective analysis of a face from the face set, thus reducing false acceptance rate and false rejection rate. Face recognition has been widely explored in the past years. A lot of techniques have been applied in various applications. Robustness and reliability have become more and more important for these applications especially in security systems. In this thesis, a variety of approaches for face recognition are reviewed first. These approaches are classified according to three basic tasks: face representation, face detection, and face identification. An implementation of the appearance-based face recognition method, the eigenface recognition approach, is reported. This method utilizes the idea of the principal component analysis and decomposes face images into a small set of characteristic feature images called eigenfaces. This proposed work is intended to develop, multiple face Eigen subspaces. With each one is corresponding to one known subject privately, rather than all individuals sharing one universal subspace as in the traditional eigenface method. Compared with the traditional single subspace face representation, the proposed method captures the extra personal difference to the most possible extent, which is crucial to distinguish between individuals, and on the other hand, it throws away the most intrapersonal difference and noise in the input.

Comparison of RBFNN, FBNN and KNN Algorithms for Face Recognition using PCA and Rectangular Feature

Face Recognition is a popular application of computer vision in recent years. Not only the computer science researchers, but also the psychologists and neuroscientists are involved in this area. Appearance-based face recognition system includes linear Analysis like PCA, ICA, LDA, and Non-linear analysis is Model-based face recognition like, Elastic Bunch Graph Matching, 2D Morphable Model, 3D Morphable Model etc. In linear Analysis, matching score between the test face image and training images can be achieved by calculating the differences between their projection vectors determined by PCA, ICA or LDA. In nonlinear analysis, a mapping function is required to be applied on data space and then the linear analysis on the mapped data is applied. In this paper, RBFNN, FBNN and KNN classifier algorithms for face recognition using PCA and Rectangular feature have been implemented for the purpose of their comparison. The number of PCA features on different image size has been used along with four rectangular features. The recognition rate of different classifiers has been recorded in different conditions for the comparison. General Terms Rectangular Feature, Neural Network Classifiers, Face Recognition.

Discriminative structure discovery via dimensionality reduction for facial image manifold

Manifold learning aims to map the original data from a high-dimensional space into a low-dimensional feature space with possible better discriminative structure. In this paper, we propose a supervised manifold learning approach called SubManifold Individuality LEarning (SMILE). In SMILE, the linear subspace derived from the principal component analysis based on data with the same label is named as "the individual subspace", while the linear subspace learned from all data is defined as "the global subspace". For each data sample, the aim of SMILE is to enlarge the diversity between its reconstructed data from individual subspace and global subspace, respectively, so that the intrinsic character of each class can be stimulated in the feature space. SMILE also utilizes the Laplacian matrix to restrict the local structure of data in the low-dimensional feature space in order to preserve the locality of the high-dimensional data. The proposed method is validated in appearance-based face recognition problem on some typical facial image databases via extracting discriminative features. Experimental results show that the proposed approach can obtain the discriminative structure of facial manifold and extract better features for face recognition than other counterparts approaches.

Face Recognition Using Eigen Face Based Technique Utilizing the Concept of Principal Component Analysis

Face recognition has been an active research area since late 1980s [1]. Eigenface approach is one of the earliest appearance-based face recognition methods, which was developed by M. Turk and A. Pentland [1] in 1991. In this approach we have to perform a lots of computations, which are not feasible with respect to time in many real time system. The concept of principal component analysis (PCA) is used in this approach to reduce the dimension and hence reducing the computation time. Principal component analysis [4] decomposes face images into a small set of characteristic feature images called eigen faces.

A Multifaceted Independent Performance Analysis of Facial Subspace Recognition Algorithms

Face recognition has emerged as the fastest growing biometric technology and has expanded a lot in the last few years. Many new algorithms and commercial systems have been proposed and developed. Most of them use Principal Component Analysis (PCA) as a base for their techniques. Different and even conflicting results have been reported by researchers comparing these algorithms. The purpose of this study is to have an independent comparative analysis considering both performance and computational complexity of six appearance based face recognition algorithms namely PCA, 2DPCA, A2DPCA, (2D)2PCA, LPP and 2DLPP under equal working conditions. This study was motivated due to the lack of unbiased comprehensive comparative analysis of some recent subspace methods with diverse distance metric combinations. For comparison with other studies, FERET, ORL and YALE databases have been used with evaluation criteria as of FERET evaluations which closely simulate real life scenarios. A comparison of results with previous studies is performed and anomalies are reported. An important contribution of this study is that it presents the suitable performance conditions for each of the algorithms under consideration.

Discriminative Multimanifold Analysis for Face Recognition from a Single Training Sample per Person

Conventional appearance-based face recognition methods usually assume that there are multiple samples per person (MSPP) available for discriminative feature extraction during the training phase. In many practical face recognition applications such as law enhancement, e-passport, and ID card identification, this assumption, however, may not hold as there is only a single sample per person (SSPP) enrolled or recorded in these systems. Many popular face recognition methods fail to work well in this scenario because there are not enough samples for discriminant learning. To address this problem, we propose in this paper a novel discriminative multimanifold analysis (DMMA) method by learning discriminative features from image patches. First, we partition each enrolled face image into several nonoverlapping patches to form an image set for each sample per person. Then, we formulate the SSPP face recognition as a manifold-manifold matching problem and learn multiple DMMA feature spaces to maximize the manifold margins of different persons. Finally, we present a reconstruction-based manifold-manifold distance to identify the unlabeled subjects. Experimental results on three widely used face databases are presented to demonstrate the efficacy of the proposed approach.

IMPACT OF FULL RANK PRINCIPAL COMPONENT ANALYSIS ON CLASSIFICATION ALGORITHMS FOR FACE RECOGNITION

Full rank principal component analysis (FR-PCA) is a special form of principal component analysis (PCA) which retains all nonzero components of PCA. Generally speaking, it is hard to estimate how the accuracy of a classifier will change after data are compressed by PCA. However, this paper reveals an interesting fact that the transformation by FR-PCA does not change the accuracy of many well-known classification algorithms. It predicates that people can safely use FR-PCA as a preprocessing tool to compress high-dimensional data without deteriorating the accuracies of these classifiers. The main contribution of the paper is that it theoretically proves that the transformation by FR-PCA does not change accuracies of the k nearest neighbor, the minimum distance, support vector machine, large margin linear projection, and maximum scatter difference classifiers. In addition, through extensive experimental studies conducted on several benchmark face image databases, this paper demonstrates that FR-PCA can greatly promote the efficiencies of above-mentioned five classification algorithms in appearance-based face recognition.

Face recognition using nonparametric-weighted Fisherfaces

Abstract This study presents an appearance-based face recognition scheme called the nonparametric-weighted Fisherfaces (NW-Fisherfaces). Pixels in a facial image are considered as coordinates in a high-dimensional space and are transformed into a face subspace for analysis by using nonparametric-weighted feature extraction (NWFE). According to previous studies of hyperspectral image classification, NWFE is a powerful tool for extracting hyperspectral image features. The Fisherfaces method maximizes the ratio of between-class scatter to that of within-class scatter. In this study, the proposed NW-Fisherfaces weighted the between-class scatter to emphasize the boundary structure of the transformed face subspace and, therefore, enhances the separability for different persons' face. The proposed NW-Fisherfaces was compared with Orthogonal Laplacianfaces, Eigenfaces, Fisherfaces, direct linear discriminant analysis, and null space linear discriminant analysis methods for tests on five facial databases. Experimental results showed that the proposed approach outperforms other feature extraction methods for most databases.

Face recognition via local preserving average neighborhood margin maximization and extreme learning machine

Average neighborhood maximum margin (ANMM) is an effective method for feature extraction in appearance-based face recognition. In this paper, we extend ANMM to locality preserving average neighborhood margin maximization (LPANMM) in order to maintain the local structure on the original data manifold in the discriminant feature space. We also combine LPANMM with extreme learning machine (ELM) as a new scheme for face recognition, we train the single-hidden layer feedforward neural network (SLFN) in the ELM classifier with the discriminant features that are extracted by LPANMM, then we use the trained ELM classifer to classify the test data. In the process of training SLFN, ELM can not only achieve the smallest training error in theory, but is also not sensitive to the initial value selection of the parameters for the SLFN. Experimental results on ORL, Yale, CMU PIE and FERET face databases demonstrate the scheme LPANMM/ELM can achieve better performance than ANMM and other traditional schemes for face recognition.

A two-dimensional Neighborhood Preserving Projection for appearance-based face recognition

This paper presents a two-dimensional Neighborhood Preserving Projection (2DNPP) for appearance-based face representation and recognition. 2DNPP enables us to directly use a feature input of 2D image matrices rather than 1D vectors. We use the same neighborhood weighting procedure that is involved in NPP to form the nearest neighbor affinity graph. Theoretical analysis of the connection between 2DNPP and other 2D methods is presented as well. We conduct extensive experimental verifications to evaluate the performance of 2DNPP on three face image datasets, i.e. ORL, UMIST, and AR face datasets. The results corroborate that 2DNPP outperforms the standard NPP approach across all experiments with respect to recognition rate and training time. 2DNPP delivers consistently promising results compared with other competing methods such as 2DLPP, 2DLDA, 2DPCA, ONPP, OLPP, LPP, LDA, and PCA.

Illumination normalization of facial images by reversing the process of image formation

Variations in illumination degrade the performance of appearance based face recognition. We present a novel algorithm for the normalization of color facial images using a single image and its co-registered 3D pointcloud (3D image). The algorithm borrows the physically based Phong’s lighting model from computer graphics which is used for rendering computer images and employs it in a reverse mode for the calculation of face albedo from real facial images. Our algorithm estimates the number of the dominant light sources and their directions from the specularities in the facial image and the corresponding 3D points. The intensities of the light sources and the parameters of the Phong’s model are estimated by fitting the Phong’s model onto the facial skin data. Unlike existing approaches, our algorithm takes into account both Lambertian and specular reflections as well as attached and cast shadows. Moreover, our algorithm is invariant to facial pose and expression and can effectively handle the case of multiple extended light sources. The algorithm was tested on the challenging FRGC v2.0 data and satisfactory results were achieved. The mean fitting error was 6.3% of the maximum color value. Performing face recognition using the normalized images increased both identification and verification rates.

Face Recognition Using L-Fisherfaces *

An appearance-based face recognition approach called the L-Fisherfaces is proposed in this paper, By using Local Fisher Discriminant Embedding (LFDE), the face images are mapped into a face subspace for analysis. Different from Linear Discriminant Analysis (LDA), which effectively sees only the Euclidean structure of face space, LFDE finds an embedding that preserves local information, and obtains a face subspace that best detects the essential face manifold structure. Different from Locality Preserving Projections (LPP) and Unsupervised Discriminant projections (UDP), which ignore the class label information, LFDE searches for the project axes on which the data points of different classes are far from each other while requiring data points of the same class to be close to each other. We compare the proposed L-Fisherfaces approach with PCA, LDA, LPP, and UDP on three different face databases. Experimental results suggest that the proposed L-Fisherfaces provides a better representation and achieves higher accuracy in face recognition.

Local appearance based face recognition method using block based steerable pyramid transform

In this paper, an efficient local appearance feature extraction method based on Steerable Pyramid (S-P) wavelet transform is proposed for face recognition. Local information is extracted by computing the statistics of each sub-block obtained by dividing S-P sub-bands. The obtained local features of each sub-band are combined at the feature and decision level to enhance face recognition performance. The purpose of this paper is to explore the usefulness of S-P as feature extraction method for face recognition. The proposed approach is compared with some related feature extraction methods such as principal component analysis (PCA), as well as linear discriminant analysis LDA and boosted LDA. Different multi-resolution transforms, wavelet (DWT), gabor, curvelet and contourlet, are also compared against the block-based S-P method. Experimental results on ORL, Yale, Essex and FERET face databases convince us that the proposed method provides a better representation of the class information, and obtains much higher recognition accuracies in real-world situations including changes in pose, expression and illumination.