SPECIAL ISSUE: Facial Image Processing and Analysis; Edited by M. Grgic, S. Shan, R. Lukac, H. Wechsler and M. S. BartlettNo Access

FACE AUTHENTICATION USING RECOGNITION-BY-PARTS, BOOSTING AND TRANSDUCTION

FAYIN LI

Department of Computer Science, George Mason University, Fairfax, VA 22030, USA

Search for more papers by this author

and

HARRY WECHSLER

Department of Computer Science, George Mason University, Fairfax, VA 22030, USA

Search for more papers by this author

https://doi.org/10.1142/S0218001409007193Cited by:12 (Source: Crossref)

Abstract

The paper describes an integrated recognition-by-parts architecture for reliable and robust face recognition. Reliability and robustness are characteristic of the ability to deploy full-fledged and operational biometric engines, and handling adverse image conditions that include among others uncooperative subjects, occlusion, and temporal variability, respectively. The architecture proposed is model-free and non-parametric. The conceptual framework draws support from discriminative methods using likelihood ratios. At the conceptual level it links forensics and biometrics, while at the implementation level it links the Bayesian framework and statistical learning theory (SLT). Layered categorization starts with face detection using implicit rather than explicit segmentation. It proceeds with face authentication that involves feature selection of local patch instances including dimensionality reduction, exemplar-based clustering of patches into parts, and data fusion for matching using boosting driven by parts that play the role of weak-learners. Face authentication shares the same implementation with face detection. The implementation, driven by transduction, employs proximity and typicality (ranking) realized using strangeness and p-values, respectively. The feasibility and reliability of the proposed architecture are illustrated using FRGC data. The paper concludes with suggestions for augmenting and enhancing the scope and utility of the proposed architecture.

References

K. Anderson and P. McOwan, Comput. Vis. Imag. Underst. 95, 184 (2004), DOI: 10.1016/j.cviu.2004.01.001. Web of Science, Google Scholar
A. B. Ashraf , S. Lucey and T. Chen , CVPR ( Anchorage, Alaska , 2008 ) . Google Scholar
B. J. Balas and P. Sinha, ACM Trans. Appl. Perception 3(4), 354 (2006), DOI: 10.1145/1190036.1190038. Google Scholar
H. B. Barlow, Neural Comput. 1, 295 (1989), DOI: 10.1162/neco.1989.1.3.295. Web of Science, Google Scholar
B. Black, F. J. Ayala and C. Saffran-Brinks, Texas Law Rev. 72(4), 715 (1994). Web of Science, Google Scholar
C. Champod and D. Meuwly, Speech Commun. 31, 193 (2000), DOI: 10.1016/S0167-6393(99)00078-3. Web of Science, Google Scholar
O. Chapelle , B. Scholkopf and A. Zien (eds.) , Semi — Supervised Learning ( MIT Press , 2006 ) . Google Scholar
V. Cherkassky and F. Mulier , Learning from Data , 2nd edn. ( Wiley , 2007 ) . Google Scholar
H. Cott , Adaptive Coloration in Animals , 3rd edn. ( Methuen & Co , London , 1966 ) . Google Scholar
T. M. Cover and P. Hart, IEEE Trans. Inform. Th. IT-13, 21 (1967). Web of Science, Google Scholar
D. Dessimoz and C. Champod , Handbook of Biometrics , eds. A. K. Jain et al. ( Springer , 2008 ) . Google Scholar
I. S. Dhillon , Y. Guan and B. Kulis , Kernel k-means, Spectral Clustering and Normalized Cuts, KDD ( Seattle , 2004 ) . Google Scholar
R. O. Duda , P. E. Hart and D. G. Sork , Pattern Classification , 2nd edn. ( Wiley , 2000 ) . Google Scholar
G. M. Edelman , Neural Darwinism. The Theory of Neuronal Group Selection ( Basic Books , NY , 1987 ) . Google Scholar
R. El-Yaniv and L. Gerzon, Patt. Recogn. Lett. 26, 2104 (2005). Web of Science, Google Scholar
M. A. Fischler and R. A. Elschlager, IEEE Trans. Comput. C 22(1), 67 (1973). Web of Science, Google Scholar
Y. Freund and R. E. Shapire, Experiments with a new boosting algorithm, 13th Int. Conf. Machine Learning (ICML) (1996) pp. 148–156. Google Scholar
F. H. Friedman, T. Hastie and R. Tibshirani, Ann. Statist. 28, 337 (2000), DOI: 10.1214/aos/1016218223. Web of Science, Google Scholar
J. Gonzalez-Rodriguezet al., IEEE Trans. Audio Speech Lang. Process. 15(7), 2104 (2007), DOI: 10.1109/TASL.2007.902747. Web of Science, Google Scholar
E. Gurari and H. Wechsler, IEEE Trans. Patt. Anal. Mach. Intell. 4(3), 304 (1982). Web of Science, Google Scholar
S. Gutta and H. Wechsler , Face recognition using asymmetric faces , 1st Int. Conf. Biometric Authentication ( 2004 ) . Google Scholar
B. Heiseleet al., Comput. Vis. Imag. Underst. 91, 6 (2003), DOI: 10.1016/S1077-3142(03)00073-0. Web of Science, Google Scholar
B. Heisele, T. Serre and T. Poggio, Int. J. Comput. Vision 74(2), 167 (2007), DOI: 10.1007/s11263-006-0006-z. Web of Science, Google Scholar
S. S. Ho and H. Wechsler, IEEE Trans. Anal. Mach. Intell. 30(9), 1557 (2008). Web of Science, Google Scholar
D. Koller and M. Sahami , Toward optimal feature selection , 13th Int. Conf. Machine Learning (ICML) ( 1996 ) . Google Scholar
M. Ladeset al., IEEE Trans. Comput. 42, 300 (1993), DOI: 10.1109/12.210173. Web of Science, Google Scholar
H. Lai, V. Ramanat and H. Wechsler, Comput. Vis. Imag. Underst. 111(3), 329 (2008), DOI: 10.1016/j.cviu.2008.01.003. Web of Science, Google Scholar
M. Li and P. Vitanyi , An Introduction to Kolmogorov Complexity and Its Applications , 2nd edn. ( Springer-Verlag , 1997 ) . Google Scholar
F. Li and H. Wechsler, IEEE Trans. Patt. Anal. Mach. Intell. 27(11), 1686 (2005). Web of Science, Google Scholar
D. G. Lowe, Int. J. Comput. Vis. 60(2), 91 (2004), DOI: 10.1023/B:VISI.0000029664.99615.94. Web of Science, Google Scholar
S. Lucey and T. Chen , Learning Patch Dependencies for Improved Pose Mismatched Face Verification, (CVPR) ( New York, NY , 2006 ) . Google Scholar
D. McNeill , The Face — A Natural History ( Brown and Co , Little , 1998 ) . Google Scholar
T. Melluish et al. , The Typicalness Framework: A Comparison with the Bayesian Approach ( Royal Holloway College, Univ. of London , 2001 ) . Google Scholar
P. J. Phillips et al. , Computer Vision and Pattern Recognition (CVPR) ( New York, NY , 2005 ) . Google Scholar
N. Pinto, D. D. Cox and J. J. DiCarlo, PLOS Comput. Biol. 4(1), 151 (2008), DOI: 10.1371/journal.pcbi.0040027. Google Scholar
K. Prodrouet al., Transduction confidence machine for pattern recognition, 13th Eur. Conf. Machine Learning (ECML) (2002) pp. 381–390. Google Scholar
M. Robnik-Sikonja and I. Kononenko, J. Mach. Learn. 53, 23 (2003), DOI: 10.1023/A:1025667309714. Web of Science, Google Scholar
Y. D. Rubinstein and T. Hastie, Knowledge and Data Discovery (KDD) (1997) pp. 49–53. Google Scholar
R. V. Rullenet al., BioSystems 48, 229 (1998). Web of Science, Google Scholar
T. Serreet al., IEEE Trans. Patt. Anal. Mach. Intell. 29(3), 411 (2007), DOI: 10.1109/TPAMI.2007.56. Web of Science, Google Scholar
R. Singh, M. Vatsa and A. Noore, Imag. Vis. Comput. 27(3), 245 (2009), DOI: 10.1016/j.imavis.2007.06.010. Web of Science, Google Scholar
P. Sinhaet al., IEEE 94(11), 1948 (2006), DOI: 10.1109/JPROC.2006.884093. Web of Science, Google Scholar
S. Thorpe, D. Fize and C. Marlot, Nature 381, 520 (1996), DOI: 10.1038/381520a0. Web of Science, Google Scholar
K. Tsunodaet al., Nature Neurosci. 4(8), 832 (2001), DOI: 10.1038/90547. Web of Science, Google Scholar
V. N. Vapnik , Statistical Learning Theory ( Wiley , 1998 ) . Google Scholar
V. Vapnik , The Nature of Statistical Learning Theory , 2nd edn. ( Springer , 2000 ) . Google Scholar
P. Viola and M. Jones , CVPR ( Kauai, Hawaii , 2001 ) . Google Scholar
V. Vovk , A. Gammerman and C. Saunders , Machine learning application of algorithmic randomness , 16th Int. Conf. Machine Learning (ICML) ( 1999 ) . Google Scholar
L. Wiscottet al., IEEE Trans. Patt. Anal. Mach. Intell. 19(7), 775 (1997). Web of Science, Google Scholar