On the usefulness of hyperspectral imaging for face recognition

Abstract. Hyperspectral cameras provide additional information in terms of multiple sampling of the visible spectrum, holding information that could be potentially useful for biometric applications. This paper investigates whether the performance of hyperspectral face recognition algorithms can be improved by considering single and multiple one-dimensional (1-D) projections of the whole spectral data along the spectral dimension. Three different projections are investigated and found by optimization: single-spectral band selection, nonnegative spectral band combination, and unbounded spectral band combination. Since 1-D projections can be performed directly on the imaging device with color filters, projections are also restricted to be physically plausible. The experiments are performed on a standard hyperspectral dataset and the obtained results outperform eight existing hyperspectral face recognition algorithms.

[1]  Chin-Teng Lin,et al.  Face recognition using nonparametric-weighted Fisherfaces , 2012, EURASIP J. Adv. Signal Process..

[2]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[3]  Bruce J. Tromberg,et al.  Comparison of Spectral-Only and Spectral/Spatial Face Recognition for Personal Identity Verification , 2009, EURASIP J. Adv. Signal Process..

[4]  LinLin Shen,et al.  Hyperspectral face recognition using 3D Gabor wavelets , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[5]  Raimondo Schettini,et al.  Two new von Kries based chromatic adaptation transforms found by numerical optimization , 2010 .

[6]  Roman Rosipal,et al.  Overview and Recent Advances in Partial Least Squares , 2005, SLSFS.

[7]  Horst Bischof,et al.  Weighted and robust learning of subspace representations , 2007, Pattern Recognit..

[8]  Raimondo Schettini,et al.  Adaptive Color Constancy Using Faces , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Raimondo Schettini,et al.  Color correction pipeline optimization for digital cameras , 2013, J. Electronic Imaging.

[10]  Simone Bianco.  Can Linear Data Projection Improve Hyperspectral Face Recognition? , 2015, CCIW.

[11]  Pang Ying Han,et al.  Eigenvector Weighting Function in Face Recognition , 2011 .

[12]  N. Ahmed,et al.  Discrete Cosine Transform , 1996 .

[13]  W. Zijlstra,et al.  Absorption spectra of human fetal and adult oxyhemoglobin, de-oxyhemoglobin, carboxyhemoglobin, and methemoglobin. , 1991, Clinical chemistry.

[14]  Quan Pan,et al.  Studies on Hyperspectral Face Recognition in Visible Spectrum With Feature Band Selection , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[15]  Arif Mahmood,et al.  Hyperspectral Face Recognition using 3D-DCT and Partial Least Squares , 2013, BMVC.

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

[17]  Sabine Süsstrunk,et al.  What is the space of spectral sensitivity functions for digital color cameras? , 2013, 2013 IEEE Workshop on Applications of Computer Vision (WACV).

[18]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[19]  Matti Pietikäinen,et al.  Face Recognition with Local Binary Patterns , 2004, ECCV.

[20]  Arif Mahmood,et al.  Hyperspectral Face Recognition With Spatiospectral Information Fusion and PLS Regression , 2015, IEEE Transactions on Image Processing.

[21]  Ammad Ali,et al.  Face Recognition with Local Binary Patterns , 2012 .

[22]  Stefan A. Robila,et al.  Toward hyperspectral face recognition , 2008, Electronic Imaging.

[23]  Michal Kawulok,et al.  Supervised relevance maps for increasing the distinctiveness of facial images , 2011, Pattern Recognit..

[24]  Erik G. Learned-Miller,et al.  Unsupervised Joint Alignment of Complex Images , 2007, 2007 IEEE 11th International Conference on Computer Vision.