Abstract
The extended sparse representation classifier (ESRC) is one of the state-of-the-art solutions for single sample face recognition, but it performs unsatisfactorily under varying illumination. There are two main reasons: one is that the mutual influences of the reflectance and illumination in intra-class variant bases of the ESRC are extreme under varying illumination, the other is that the specific identity information of the face in the generic set constrains the performance of ESRC, since the specific identity information of the generic face is redundant and should be removed. In this paper, the additive strategy is introduced to ESRC, which can efficiently eliminate aforementioned two issues. Two additive models: one is the reflectance and illumination additive (R&L) model and the other is the high-and low-frequency additive (H&L) model, are introduced to ESRC to obtain two new methods: R&L_ESRC and H&L_ESRC. Each method can be solved by a combined L1-minimization problem, and the final classification is determined by the sum of two weighting residuals: the reflectance and illumination residuals (or the high-and low-frequency residuals). In our experiments, the wavelet denoising (WDM) model and the logarithmic total variation (LTV) model are employed to extract facial features in R&L_ESRC and H&L_ESRC respectively. The performances of the proposed methods are verified on the Extended Yale B, CMU PIE, AR, ORL, and self-built Driver face databases. The experimental results illustrate that the proposed techniques outperform previous approaches under both normal and variant illumination conditions.



















Similar content being viewed by others
References
Adini Y, Moses Y, Ullman S (1997) Face recognition: the problem of compensating for changes in illumination direction. IEEE Trans Pattern Anal Mach Intell 19(7):721–732
Cao X, Shen W, Yu L, Wang Y, Yang J, Zhang Z (2012) Illumination invariant extraction for face recognition using neighboring wavelet coefficients. Pattern Recogn 45(4):1299–1305
Chang KI, Bowyer KW, Flynn PJ (2006) Multiple nose region matching for 3D face recognition under varying facial expression. IEEE Trans Pattern Anal Mach Intell 28(10):1695–1700
Chen W, Er MJ, Wu S (2006a) Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain, IEEE transactions on systems, man, and cybernetics. Part B: Cybern 36(2):458–466
Chen T, Yin W, Zhou XS, Comaniciu D, Huang TS (2006b) Total variation models for variable lighting face recognition. IEEE Trans Pattern Anal Mach Intell 28(9):1519–1527
Choi SI, Kim C, Choi CH (2007) Shadow compensation in 2D images for face recognition. Pattern Recogn 40(7):2118–2125
Deng W, Hu J, Guo J (2012) Extended SRC: Undersampled face recognition via intraclass variant dictionary. IEEE Trans Pattern Anal Mach Intell 34(9):1864–1870
Donoho DL, Tsaig Y (2008) Fast solution of L1-norm minimization problems when the solution may be sparse. IEEE Trans Inf Theory 54(11):4789–4812
Georghiades A, Belhumeur P, Kriegman D (2001) From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans Pattern Anal Mach Intell 23(6):643–660
Horn BKP (1997) Robot vision. MA, MIT Press, Cambridge
Hu C, Ye M, Zeng W, Lu X (2015a) An adaptive approximation image reconstruction method for single sample problem in face recognition using FLDA. Multimed Tools and Appl 74(23):10313–10334
Hu C, Ye M, Ji S, Zeng W, Lu X (2015b) A new face recognition method based on image decomposition for single sample per person problem. Neurocomputing 160:287–299
Ji Q, Zheng E, Yue X, Yu X, Lin Y (2015) Face recognition method based on HOG and DMMA from single training sample, Multimedia Tools and Applications: 1–15
Jiang X, Lai J (2015) Sparse and dense hybrid representation via dictionary decomposition for face recognition. IEEE Trans Pattern Anal Mach Intell 37(5):1067–1079
Jobson DJ, Rahman Z, Woodell G (1997) A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans Image Process 6(7):965–976
Kan M, Chan S, Zhou Y, Xu D, Chen X (2013) Adaptive discriminant learning for face recognition. Pattern Recogn 46(9):2497–2509
Lai Z, Dai D, Ren C, Huang K (2015) Multiscale logarithm difference edgemaps for face recognition against varying lighting conditions. IEEE Trans Image Process 24(6):1735–1747
Majumdar A, Ward RK (2008) Pseudo-Fisherface method for single image per person face recognition. In: Proceeding of IEEE international conference on acoustics, speech and signal processing p 989–992
Martinez AM (1998) The AR face database. CVC Technical Report 24
Ochoa-Villegas MA, Nolazco-Flores JA, Barron-Cano O, Kakadiaris IA (2015) Addressing the illumination challenge in two-dimensional face recognition: a survey. IET Comput Vis 9(6):978–992
Samaria FS, Harter AC (1994) Parameterisation of a stochastic model for human face identification. In: Proceedings of the second IEEE workshop on applications of computer vision, p 138–142
Shim H, Luo J, Chen T (2008) A subspace model-based approach to face relighting under unknown lighting and poses. IEEE Trans Image Process 17(8):1331–1341
Sim T, Baker S, Bsat M (2003) The CMU pose, illumination, and expression database. IEEE Trans Pattern Anal Mach Intell 25(12):1615–1618
Vezzetti E, Marcolin F, Fracastoro G (2014) 3D face recognition: an automatic strategy based on geometrical descriptors and landmarks. Robot Auton Syst 62(12):1768–1776
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features, In: Proceedings of IEEE computer society conference on computer vision and pattern recognition, p I-511-I-518
Wagner A, Wright J, Ganesh A, Zhou Z, Mobahi H, Ma Y (2012) Toward a practical face recognition system: robust alignment and illumination by sparse representation. IEEE Trans Pattern Anal Mach Intell 34(2):372–386
Wan B, Li W, Li Z, Liao Q (2013) Adaptive linear regression for single-sample face recognition. Neurocomputing 115:186–191
Wang B, Li W, Yang W, Liao Q (2011) Illumination normalization based on weber's law with application to face recognition. IEEE Signal Processing Lett 18(8):462–465
Xie X, Zheng W, Liao J, Yuen PC, Suen CY (2011) Normalization of face illumination based on large-and small-scale features. IEEE Trans Image Process 20(7):1807–1821
Xu W, Lee SH, Lee EJ (2015) A robust method for partially occluded face recognition. KSII Trans Internet Info Syst 9(7):2667–2682
Yang M, Zhang L, Yang J, Zhang D (2013a) Regularized robust coding for face recognition. IEEE Trans Image Process 22(5):1753–1766
Yang M, Gool L, Zhang L (2013b) Sparse variation dictionary learning for face recognition with a single training sample per person. In: Proceedings of IEEE international conference on computer vision, p 689–696
Zhang D, Chen S, Zhou Z (2005) A new face recognition method based on SVD perturbation for single example image per person. Appl Math Comput 163(2):895–907
Zhang T, Gang B, Yuan Y, Tang YY, Shang Z, Li D, Lang F (2009a) Multiscale facial structure representation for face recognition under varying illumination. Pattern Recogn 42(2):251–258
Zhang T, Tang Y, Fang B, Shang Z, Liu X (2009b) Face recognition under varying illumination using gradientfaces. IEEE Trans Image Process 18(11):2599–2606
Zhuang L, Yang AY, Zhou Z, Sastry SS, Ma Y (2013) Single-sample face recognition with image corruption and misalignment via sparse illumination transfer. In: Proceedings of IEEE conference on computer vision and pattern recognition, p 3546–3553
Zhuang L, Chan T, Yang AY, Sastry SS, Ma Y (2014) Sparse illumination learning and transfer for single-sample face recognition with image corruption and misalignment. Int J Comput Vis 114(2–3):272–287
Zou X, Kittler J, Messer K (2007) Illumination invariant face recognition: A survey, In: Proceeding of IEEE International Conference on Biometrics: Theory, Applications, and Systems, p 1–8
Acknowledgments
This work was supported by the National Key Science and Technology Pillar Program of China (No.2014BAG01B03), National Natural Science Foundation of China (No.61374194& No.61403081), Scientific Research Foundation of Graduate School of Southeast University (YBJJ1519), Natural Science Foundation of Jiangsu Province (No. BK20140638), and a Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hu, C., Lu, X., Ye, M. et al. Illumination robust single sample face recognition based on ESRC. Multimed Tools Appl 76, 26523–26550 (2017). https://doi.org/10.1007/s11042-016-4180-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-4180-x