Face Recognition

Face Recognition Face recognition is a task that humans perform routinely and effortlessly in our daily lives. Wide availability of powerful and low-cost desktop and embedded computing systems has created an enormous interest in automatic processing of digital images in a variety of applications, including biometric authentication, surveillance, human-computer interaction, and multimedia management. Research and […]

Introduction to Face Recognition Part 2

Solution Strategies There are two strategies for tackling the challenges outlined in Sect. 1.5: (i) extract invariant and discriminative face features, and (ii) construct a robust face classifier. A set of features, constituting a feature space, is deemed to be good if the face manifolds are simple (i.e., less nonlinear and nonconvex). This requires two […]

Face Recognition in Subspaces (Face Image Modeling and Representation) Part 1

Introduction Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision research in general, has witnessed a growing interest in techniques that capitalize on this observation and apply algebraic and statistical tools for extraction and analysis of the underlying manifold. In this topic, […]

Face Recognition in Subspaces (Face Image Modeling and Representation) Part 2

Independent Component Analysis and Source Separation While PCA minimizes the sample covariance (second-order dependence) of the data, independent component analysis (ICA) [6, 18] minimizes higher-order dependencies as well, and the components found by ICA are designed to be non-Gaussian. Like PCA, ICA yields a linear projectionbut    with    different properties that is, approximate reconstruction, nonorthogonality of […]

Face Recognition in Subspaces (Face Image Modeling and Representation) Part 3

Empirical Comparison of Subspace Methods Moghaddam [23] reported on an extensive evaluation of many of the subspace methods described above on a large subset of the FERET data set [31] (see also Chap. 13). Fig. 2.10 Experiments on FERET data. a Several faces from the gallery. b Multiple probes for one individual, with different facial […]

Face Subspace Learning (Face Image Modeling and Representation) (Face Recognition) Part 1

Introduction The last few decades have witnessed a great success of subspace learning for face recognition. From principal component analysis (PCA) [43] and Fisher’s linear discriminant analysis [1], a dozen of dimension reduction algorithms have been developed to select effective subspaces for the representation and discrimination of face images [17, 21, 45, 46, 51]. It […]

Face Subspace Learning (Face Image Modeling and Representation) (Face Recognition) Part 2

Related Works In addition to the general mean criteria and max-min distance analysis, there are also some methods proposed in recent years to deal with the class separation problem of FLDA. Among these methods, approximate pairwise accuracy criterion (aPAC) [28] and fractional step LDA (FS-LDA) [30] are the most representative ones, and both of them […]

Face Subspace Learning (Face Image Modeling and Representation) (Face Recognition) Part 3

Related Works Applying the idea of manifold learning, that is, exploring local geometry information of data distribution, into semisupervised or transductive subspace selection leads to a new framework of dimension reduction by manifold regularization. One example is the recently proposed manifold regularized sliced inverse regression (MRSIR) [4]. Sliced inverse regression (SIR) was proposed for sufficient […]

Local Representation of Facial Features (Face Image Modeling and Representation) (Face Recognition) Part 1

The aim of this topic is to give a comprehensive overview of different facial representations and in particular describe local facial features. Introduction Developing face recognition systems involves two crucial issues: facial representation and classifier design [47,101]. The aim of facial representation is to derive a set of features from the raw face images which […]

Local Representation of Facial Features (Face Image Modeling and Representation) (Face Recognition) Part 2

Face Description Using LBP Description of Static Face Images In the LBP approach for texture classification [64], the occurrences of the LBP codes in an image are collected into a histogram. The classification is then performed by computing simple histogram similarities. However, considering a similar approach for facial image representation results in a loss of […]