Zhou S., Chellappa R., Zhao W. Unconstrained Face Recognition

Springer, 2006. — 244 p.The goal of this book is to provide a comprehensive review of unconstrained face recognition, especially face recognition from video, and to assemble descriptions of novel approaches that are able to recognize human faces under various unconstrained situations. The underlying theme of these approaches is that, unlike conventional face recognition algorithms, they exploit the inherent characteristics of the unconstrained situation and gain improvements in recognition performance when compared with conventional algorithms. For instance, generalized photometric stereo combines physics-based illumination model with statistical modeling to address face recognition under illumination variation. Simultaneous tracking and recognition employs the temporal information embedded in a video sequence and thus improves both tracking accuracy and recognition performance.
The book is organized into five parts: 1) Fundamentals, preliminaries, and reviews; II) Face recognition under variations; III) Face recognition via kernel learning; IV) Face tracking and recognition from video; and V) Future directions. Part I, consisting of two chapters, addresses fimdamental issues of face recognition, especially under unconstrained scenarios, and provides necessary background for following the discussions in subsequent parts and an up-to-date survey of unconstrained face recognition. Part II, consisting of four chapters, presents face recognition approaches that are able to handle variations due to illumination, pose, and aging. Part III, consisting of two chapters, studies face recognition from a viewpoint of an appearance manifold whose nonlinearity is characterized via two kernel learning methods: computing probabilistic distances in reproducing kernel Hilbert space and matrix-based kernel methods. Part IV, consisting of three chapters, presents adaptive visual tracking, simultaneous tracking and recognition, and a unifying framework of probabilistic identity characterization. A detailed description of the organization and the contents of each chapter are given in Section 1.2.