Unconstrained Face Recognition

by Zhou, Shaohua Kevin; Chellappa, Rama; Zhao, Wenyi

• ISBN13: 9780387264073
• ISBN10: 0387264078
• Format: Hardcover
• Copyright: 2005-12-01
• Publisher: Springer-Verlag New York Inc

Summary

Face recognition has been actively studied over the past decade and continues to be a big research challenge. Just recently, researchers have begun to investigate face recognition under unconstrained conditions. Unconstrained Face Recognition provides a comprehensive review of this biometric, especially face recognition from video, assembling a collection of novel approaches that are 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 structured to meet the needs of a professional audience of researchers and practitioners in industry. This volume is also suitable for advanced-level students in computer science.

Table of Contents

Dedication	v
Preface	xi
Part I Fundamentals, Preliminaries and Reviews
1. FUNDAMENTALS	3	(14)
1.1 Overview	3	(8)
1.2 Unconstrained Face Recognition	11	(6)
2. PRELIMINARIES AND REVIEWS	17	(28)
2.1 Preliminaries	17	(9)
2.2 Reviews	26	(19)
Part II Face Recognition Under Variations
3. SYMMETRIC SHAPE FROM SHADING	45	(26)
3.1 Symmetry Cue: Improved Model and Unique Solution	46	(8)
3.2 Theory of Symmetric Shape from Shading	54	(6)
3.3 Symmetric SFS Algorithms and Experiments	60	(7)
3.4 Beyond Symmetric SFS	67	(4)
4. GENERALIZED PHOTOMETRIC STEREO	71	(26)
4.1 Principle of Generalized Photometric Stereo	73	(9)
4.2 Illumination-Invariant Face Recognition in the Presence of a Single Light Source	82	(5)
4.3 Illumination-Invariant Face Recognition in the Presence of Multiple Light Sources	87	(10)
5. ILLUMINATING LIGHT FIELD	97	(14)
5.1 Principle of Illuminating Light Field	98	(5)
5.2 Face Recognition across Illumination and Poses	103	(8)
6. FACIAL AGING	111	(20)
6.1 Age Estimation	111	(10)
6.2 Face Recognition across Aging Progression	121	(10)
Part III Face Recognition Via Kernel Learning
7. PROBABILISTIC DISTANCES IN REPRODUCING KERNEL HILBERT SPACE	131	(14)
7.1 Probabilistic Distances in Rd	132	(2)
7.2 Mean and Covariance Marix in RKHS	134	(2)
7.3 Probabilistic Distances in RKHS	136	(5)
7.4 Experimental Results	141	(4)
8. MATRIX-BASED KERNEL SUBSPACE ANALYSIS	145	(14)
8.1 Matrix KPCA and Matrix KLDA	146	(5)
8.2 Discussions and Experimental Results	151	(8)
Part IV Face Tracking and Recognition From Videos
9. ADAPTIVE VISUAL TRACKING	159	(18)
9.1 Appearance-Adaptive Models	161	(8)
9.2 Experimental Results on Visual Tracking	169	(8)
10. SIMULTANEOUS TRACKING AND RECOGNITION	177	(24)
10.1 Stochastic Models and Algorithms for Recognition from Video	179	(5)
10.2 Still-to-Video Face Recognition Experiments	184	(12)
10.3 Appendix	196	(5)
11. PROBABILISTIC IDENTITY CHARACTERIZATION	201	(16)
11.1 Principle of Probabilistic Identity Characterization	202	(2)
11.2 Recognition Setting and Issues	204	(2)
11.3 Subspace Identity Encoding	206	(6)
11.4 Appendix	212	(5)
Part V Summary and Future Research Directions
12. SUMMARY AND FUTURE RESEARCH DIRECTIONS	217	(8)
12.1 Summary	217	(2)
12.2 Future Research Directions	219	(6)
References	225	(18)
Index	243