Improved Sparse Representation Algorithm for Face Recognition Via Dense SIFT Feature Alignment
Zhou Quan Wei Xin Chen Jian-xin Zheng Bao-yu
(Key Laboratory of Ministry of Education for Broad Band Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunication, Nanjing 210003, China)
In order to address the non-rigid deformation (e.g., misalignment, poses, and expression) of facial images, this paper proposes a novel sparse representation face recognition algorithm using Dense Scale Invariant Feature Transform (SIFT) Feature Alignment (DSFA). The whole method consists of two steps: first, DSFA is employed as a generic transformation to roughly align training and testing samples; and then, input facial images are identified based on proposed sparse representation model. A novel coarse-to-fine scheme is designed to accelerate facial image alignment. The experimental results demonstrate the superiority of the proposed method over other methods on ORL, AR, and LFW datasets. The proposed approach improves 4.3% in terms of recognition accuracy and runs nearly 6 times faster than previous sparse approximation methods on three datasets.
Li S Z and Jain A K. Handbook of face recognition[M]. New York, Springer, 2011: 1-374.
[2]
Yang A Y, Zihan Z, Ganesh B A, et al.. Fast-minimization algorithms for robust face recognition[J]. IEEE Transactions on Image Processing, 2013, 22(8): 3234-3236.
[3]
Cament A L, Castillo L E, Perez J P, et al.. Fusion of local normalization and Gabor entropy weighted features for face identification[J]. Pattern Recognition, 2014, 47(2): 568-577.
[4]
Jonathon P P and Alice O J. Comparison of human and computer performance across face recognition experiments[J]. Image and Vision Computing, 2014, 32(1): 74-85.
[5]
Radtke V W P, Granger E, Sabourin R, et al.. Skew-sensitive boolean combination for adaptive ensembles-An application to face recognition in video surveillance[J]. Information Fusion, 2014, 20(10): 31-48.
[6]
Abdullah M F A, Sayeed S M, Sonai K M, et al.. Face recognition with symmetric local graph Structure[J]. Expert Systems with Applications, 2014, 41(14): 6131-6137.
Yin Fei, Jiao Li-cheng, and Yang Shu-yuan. Subspace label propagation and regularized discriminate analysis based single labeled image person face recognition[J]. Jounal of Electronics & Information Technology, 2014, 36(3): 610-616.
Zhao Zhen-hua and Hao Xiao-hong. Linear locality preserving and discriminating projection for face recognition [J]. Jounal of Electronics & Information Technology, 2013, 35(2): 463-467.
[9]
Ahonen T, Hadid A, and Pietikainen M. Face description with local binary patterns: Application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2037-2041
Zhang Jie-yu, Zhao Hong-ping, and Chen Shu. Face recognition based on weighted local binary pattern with adaptive threshold[J]. Jounal of Electronics & Information Technology, 2014, 36(6): 1327-1333.
[11]
Cootes T F, Edwards G J, and Taylor C J. Active appearance models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685.
[12]
Belhumeur P N, Hespanha J P, and Kriegman D J. Eigenfaces vs. fisherfaces: recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720
[13]
Naseem I, Togneri R, and Bennamoun M. Linear regression for face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(11): 2106-2112
[14]
Turk M and Pentland A. Eigenfaces for recognition[J]. Journal of Cognitive Neuroscience, 2010, 3(1): 71-86.
[15]
Bartlett M S, Movellan J R, and Sejnowski T J. Face recognition by independent component analysis[J]. IEEE Transactions on Neuro Network, 2002, 13(6): 1450-1464.
[16]
Wright J, Yang A Y, Ganesh A, et al.. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227
[17]
Peng Y, Ganesh A, Wright J, et al.. Rasl: Robust alignment by sparse and low-rank decomposition for linearly correlated images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 22330-2246.
[18]
Wagner A, Wright J, Ganesh A, et al.. Toward a practical face recognition system: Robust alignment and illumination by sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(2): 372-386.
[19]
Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[20]
Shekhovtsov A, Kovtun I, and Hlavac V. Efficient MRF Deformation Model for Non-Rigid Image Matching[C]. Proceedings of the IEEE Computer Vision and Pattern Recognition, Miami, FL, USA, 2007: 1-6.
[21]
Felzenszwalb P F and Huttenlocher D P. Efficient belief propagation for early vision[J]. International Journal of Computer Vision, 2006, 70(1): 41-54.
[22]
Boyd S and Vandenberghe L. Convex Optimization[M]. London, Cambridge University Press, 2004: 457-514.
[23]
Martinez A M. The AR face database[R]. CVC Tech. Rep. 1998.
[24]
Huang G B, Ramesh M, Berg T, et al.. Labeled faces in the wild: A database for studying face recognition in unconstrained environments[R]. University of Massachusetts, Amherst Tech. Rep. 7-49, 2007.
[25]
Viola P and Jones M J. Robust Real-Time Face Detection[J]. International Journal of Computer Vision, 2004, 57(3): 137-154.
