Unconstrained Face Recognition [electronic resource] / by Shaohua Kevin Zhou, Rama Chellappa, Wenyi Zhao.

Fundamentals, Preliminaries and Reviews -- Fundamentals -- Preliminaries and Reviews -- Face Recognition Under Variations -- Symmetric Shape from Shading -- Generalized Photometric Stereo -- Illuminating Light Field -- Facial Aging -- Face Recognition Via Kernel Learning -- Probabilistic Distances in Reproducing Kernel Hilbert Space -- Matrix-Based Kernel Subspace Analysis -- Face Tracking and Recognition from Videos -- Adaptive Visual Tracking -- Simultaneous Tracking and Recognition -- Probabilistic Identity Characterization -- Summary and Future Research Directions -- Summary and Future Research Directions.

Although face recognition has been actively studied over the past decade, the state-of-the-art recognition systems yield satisfactory performance only under controlled scenarios. Recognition accuracy degrades significantly when confronted with unconstrained situations. Examples of unconstrained conditions include illumination and pose variations, video sequences, expression, aging, and so on. Recently, researchers have begun to investigate face recognition under unconstrained conditions that is referred to as unconstrained face recognition. This volume provides a comprehensive view of unconstrained face recognition, especially face recognition from multiple still images and/or video sequences, assembling a collection of novel approaches able to recognize human faces under various unconstrained situations. The underlying basis of these approaches is that, unlike conventional face recognition algorithms, they exploit the inherent characteristics of the unconstrained situation and thus improve the recognition performance when compared with conventional algorithms. Unconstrained Face Recognition is accessible to a wide audience with an elementary level of linear algebra, probability and statistics, and signal processing. Unconstrained Face Recognition is designed primarily for a professional audience composed of practitioners and researchers working within face recognition and other biometrics. Also instructors can use the book as a textbook or supplementary reading material for graduate courses on biometric recognition, human perception, computer vision, or other relevant seminars.