Comparison of feature extraction techniques for face verification using elastic graph matching on low-power mobile devices

This paper considers biometric face verification using elastic graph matching, fulfilling the requirements for mobile devices regarding performance, low complexity, and low-power consumption. Two feature extraction techniques are compared. A modified technique based on normalized mathematical morphological features is introduced, that results in performances comparable to ones achieved with Gabor features, however, with a substantially lower computational complexity.

[1]  John I. Goutsias,et al.  Mathematical Morphology and its Applications to Image and Signal Processing , 2000, Computational Imaging and Vision.

[2]  Jun Zhang,et al.  Pace recognition: eigenface, elastic matching, and neural nets , 1997, Proc. IEEE.

[3]  Jean-Luc Nagel,et al.  A multiscale morphological coprocessor for low-power face authentication , 2002, 2002 11th European Signal Processing Conference.

[4]  Stefan Fischer,et al.  Face authentication with Gabor information on deformable graphs , 1999, IEEE Trans. Image Process..

[5]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[6]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  M. Farah,et al.  What is "special" about face perception? , 1998, Psychological review.

[8]  Trygve Randen,et al.  Filtering for Texture Classification: A Comparative Study , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Steven Furnell,et al.  Acceptance of Subscriber Authentication Methods For Mobile Telephony Devices , 2002, Comput. Secur..

[10]  Anastasios Tefas,et al.  Morphological elastic graph matching applied to frontal face authentication under well-controlled and real conditions , 2000, Pattern Recognit..

[11]  Daniel A. Pollen,et al.  Visual cortical neurons as localized spatial frequency filters , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[12]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[13]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[15]  P. Jonathon Phillips,et al.  An Introduction to Evaluating Biometric Systems , 2000, Computer.

[16]  Samy Bengio,et al.  Evaluation of Biometric Technology on XM2VTS , 2001 .

[17]  Martin Lades.  FACE RECOGNITION TECHNOLOGY , 1999 .

[18]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.