Improving Face Recognition via Narrowband Spectral Range Selection Using Jeffrey Divergence

In order to achieve improved recognition performance in comparison with conventional broadband images, this paper addresses a new method that automatically specifies the optimal spectral range for multispectral face images according to given illuminations. The novelty of our method lies in the introduction of a distribution separation measure and the selection of the optimal spectral range by ranking these separation values. The selected spectral ranges are consistent with the physics analysis of the multispectral imaging process. The fused images from these chosen spectral ranges are verified to outperform the conventional broadband images by 3%-20%, based on a variety of experiments with indoor and outdoor illuminations using two well-recognized face-recognition engines. Our discovery can be practically used for a new customized sensor design associated with given illuminations for improved face-recognition performance over the conventional broadband images.

[1]  Mongi A. Abidi,et al.  Physics-based Fusion of Multispectral Data for Improved Face Recognition , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[2]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[3]  Meng Joo Er,et al.  Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Seong G. Kong,et al.  Multiscale Fusion of Visible and Thermal IR Images for Illumination-Invariant Face Recognition , 2007, International Journal of Computer Vision.

[5]  Seiji Inokuchi,et al.  Simulation and analysis of spectral distributions of human skin , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[6]  Norimichi Tsumura,et al.  Principal Component Analysis of Skin Color and Its Application to Colorimetric Color Reproduction on CRT Display and Hardcopy , 1996, Journal of Imaging Science and Technology.

[7]  Alex Pentland,et al.  Bayesian face recognition , 2000, Pattern Recognit..

[8]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[9]  Bruce J. Tromberg,et al.  Multiband and spectral eigenfaces for face recognition in hyperspectral images , 2005, SPIE Defense + Commercial Sensing.

[10]  Wen Gao,et al.  Illumination normalization for robust face recognition against varying lighting conditions , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[11]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  E. A. Edwards,et al.  The pigments and color of living human skin , 1939 .

[13]  Evgueni A. Haroutunian,et al.  Information Theory and Statistics , 2011, International Encyclopedia of Statistical Science.

[14]  Yajie Tian,et al.  Handbook of face recognition , 2003 .

[15]  Bruce J. Tromberg,et al.  Face Recognition in Hyperspectral Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Larry Wasserman,et al.  All of Statistics: A Concise Course in Statistical Inference , 2004 .

[17]  Chengjun Liu,et al.  A unified Bayesian framework for face recognition , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[18]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[19]  Saurabh Singh,et al.  Face recognition by fusing thermal infrared and visible imagery , 2006, Image Vis. Comput..

[20]  Sang-Woong Lee,et al.  Face recognition under arbitrary illumination using illuminated exemplars , 2007, Pattern Recognit..

[21]  Lawrence B. Wolff,et al.  Illumination invariant face recognition using thermal infrared imagery , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[22]  Bruce J. Tromberg,et al.  Hyperspectral face recognition under variable outdoor illumination , 2004, SPIE Defense + Commercial Sensing.

[23]  Kin-Man Lam,et al.  Face recognition under varying illumination based on a 2D face shape model , 2005, Pattern Recognit..