Full Text:   <970>

Summary:  <447>

CLC number: TP391

On-line Access: 2015-12-07

Received: 2015-03-19

Revision Accepted: 2015-08-10

Crosschecked: 2015-11-11

Cited: 3

Clicked: 2324

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Shuang Chen

http://orcid.org/0000-0001-7441-4749

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2015 Vol.16 No.12 P.1046-1058

http://doi.org/10.1631/FITEE.1500085


Face recognition based on subset selection via metric learning on manifold


Author(s):  Hong Shao, Shuang Chen, Jie-yi Zhao, Wen-cheng Cui, Tian-shu Yu

Affiliation(s):  School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, China; more

Corresponding email(s):   chenshuang19891129@gmail.com

Key Words:  Face recognition, Sparse representation, Manifold structure, Metric learning, Subset selection


Hong Shao, Shuang Chen, Jie-yi Zhao, Wen-cheng Cui, Tian-shu Yu. Face recognition based on subset selection via metric learning on manifold[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(12): 1046-1058.

@article{title="Face recognition based on subset selection via metric learning on manifold",
author="Hong Shao, Shuang Chen, Jie-yi Zhao, Wen-cheng Cui, Tian-shu Yu",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="16",
number="12",
pages="1046-1058",
year="2015",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1500085"
}

%0 Journal Article
%T Face recognition based on subset selection via metric learning on manifold
%A Hong Shao
%A Shuang Chen
%A Jie-yi Zhao
%A Wen-cheng Cui
%A Tian-shu Yu
%J Frontiers of Information Technology & Electronic Engineering
%V 16
%N 12
%P 1046-1058
%@ 2095-9184
%D 2015
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1500085

TY - JOUR
T1 - Face recognition based on subset selection via metric learning on manifold
A1 - Hong Shao
A1 - Shuang Chen
A1 - Jie-yi Zhao
A1 - Wen-cheng Cui
A1 - Tian-shu Yu
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 16
IS - 12
SP - 1046
EP - 1058
%@ 2095-9184
Y1 - 2015
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1500085


Abstract: 
With the development of face recognition using sparse representation based classification (SRC), many relevant methods have been proposed and investigated. However, when the dictionary is large and the representation is sparse, only a small proportion of the elements contributes to the l1-minimization. Under this observation, several approaches have been developed to carry out an efficient element selection procedure before SRC. In this paper, we employ a metric learning approach which helps find the active elements correctly by taking into account the interclass/intraclass relationship and manifold structure of face images. After the metric has been learned, a neighborhood graph is constructed in the projected space. A fast marching algorithm is used to rapidly select the subset from the graph, and SRC is implemented for classification. Experimental results show that our method achieves promising performance and significant efficiency enhancement.

This paper solves a practical problem in the face recognition application. The proposed framework is quite intuitive and efficient. Experiments conducted on several benchmark databases validate the effectiveness of the proposed method.

基于度量学习和子集选择的稀疏表示人脸识别算法

目的:针对传统基于稀疏表示分类的人脸识别算法计算复杂度高的劣势,通过分析人脸图像的流形结构,提出一种通过度量学习和子集选择的人脸识别算法,极大地加快基于稀疏表示的人脸识别速度,在不牺牲算法识别性能的前提下,使其可以达到实用的计算速度要求。
创新点:l1-人脸识别算法提出了一种更精确的字典选择框架,该框架主要包含一种考虑类内类间差的人脸流形结构和可沿流形结构进行子集选择的fast marching算法。
方法:在训练阶段,首先将度量学习引入到人脸识别问题中,利用度量学习产生一个线性投影矩阵,所有训练图像经该矩阵投影后能保持最小类内差与最大类间差。其次,结合人脸图像的流形结构进行建模,利用上述步骤学习得到的度量将所有训练图像构成一个无向带权值的连通邻接图,该图可充分表达训练样本在流形中的几何结构。在识别阶段,fast marching以被查询图像为基点在训练阶段得到的人脸流形结构上搜索子集,最终稀疏表示算法以子集为字典识别出被查询人脸图像的类别。
结论:使用通用数据库验证算法的识别准确率和计算效率。实验表明,文章所提出的算法能够有效的利用训练样本的类内和类间信息,达到可观的识别性能。该方法同时将识别速度提高到了可以实用的程度。

关键词:人脸识别;稀疏表示;流形空间;度量学习;子集选择

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Arandjelović, O., Shakhnarovich, G., Fisher, J., et al., 2005. Face recognition with image sets using manifold density divergence. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.581-588.

[2]Belkin, M., Niyogi, P., 2001. Laplacian eigenmaps and spectral techniques for embedding and clustering. NIPS, 14:585-591.

[3]Candès, E.J., 2008. The restricted isometry property and its implications for compressed sensing. Compt. Rend. Math., 346(9-10):589-592.

[4]Candès, E.J., Tao, T., 2007. The Dantzig selector: statistical estimation when p is much larger than n. Ann. Stat., 35(6):2313-2351.

[5]Deng, W.H., Hu, J.N., Guo, J., 2012. Extended SRC: undersampled face recognition via intraclass variant dictionary. IEEE Trans. Patt. Anal. Mach. Intell., 34(9):1864-1870.

[6]Efron, B., Hastie, T., Johnstone, I., et al., 2004. Least angle regression. Ann. Stat., 32(2):407-499.

[7]Georghiades, A.S., Belhumeur, P.N., Kriegman, D., 2001. From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Patt. Anal. Mach. Intell., 23(6):643-660.

[8]He, R., Zheng, W.S., Hu, B.G., 2011. Maximum correntropy criterion for robust face recognition. IEEE Trans. Patt. Anal. Mach. Intell., 33(8):1561-1576.

[9]He, R., Zheng, W.S., Hu, B.G., et al., 2013. Two-stage nonnegative sparse representation for large-scale face recognition. IEEE Trans. Neur. Netw. Learn. Syst., 24(1):35-46.

[10]He, R., Zheng, W.S., Tan, T.N., et al., 2014. Half-quadratic-based iterative minimization for robust sparse representation. IEEE Trans. Patt. Anal. Mach. Intell., 36(2):261-275.

[11]Jiang, Z.L., Lin, Z., Davis, L.S., 2011. Learning a discriminative dictionary for sparse coding via label consistent K-SVD. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.1697-1704.

[12]Lai, Z.H., Li, Y.J., Wan, M.H., et al., 2013. Local sparse representation projections for face recognition. Neur. Comput. Appl., 23(7):2231-2239.

[13]Liao, S.C., Jain, A.K., Li, S.Z., 2013. Partial face recognition: alignment-free approach. IEEE Trans. Patt. Anal. Mach. Intell., 35(5):1193-1205.

[14]Lu, J.W., Tan, Y.P., Wang, G., 2013. Discriminative multimanifold analysis for face recognition from a single training sample per person. IEEE Trans. Patt. Anal. Mach. Intell., 35(1):39-51.

[15]Martínez, A., Benavente, B., 1998. The AR Face Database. CVC Technical Report 24.

[16]Ortiz, E.G., Becker, B.C., 2014. Face recognition for web-scale datasets. Comput. Vis. Image Understand., 118:153-170.

[17]Patel, V.M., Wu, T., Biswas, S., et al., 2012. Dictionary-based face recognition under variable lighting and pose. IEEE Trans. Inform. Forens. Secur., 7(3):954-965.

[18]Phillips, P.J., Wechsler, H., Huang, J., et al., 1998. The FERET database and evaluation procedure for face-recognition algorithms. Image Vis. Comput., 16(5):295-306.

[19]Roweis, S.T., Saul, L.K., 2000. Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500):2323-2326.

[20]Sethian, J.A., 1999. Fast marching methods. SIAM Rev., 41(2):199-235.

[21]Seung, H.S., Lee, D.D., 2000. The manifold ways of perception. Science, 290(5500):2268-2269.

[22]Tenenbaum, J.B., de Silva, V., Langford, J.C., 2000. A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500):2319-2323.

[23]Tibshirani, R., 1996. Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B, 58(1):267-288.

[24]Vandenberghe, L., Boyd, S., 1996. Semidefinite programming. SIAM Rev., 38(1):49-95.

[25]Wagner, A., Wright, J., Ganesh, A., et al., 2012. Toward a practical face recognition system: robust alignment and illumination by sparse representation. IEEE Trans. Patt. Anal. Mach. Intell., 34(2):372-386.

[26]Wang, L.F., Wu, H.Y., Pan, C.H., 2015. Manifold regularized local sparse representation for face recognition. IEEE Trans. Circ. Syst. Video Technol., 25(4):651-659.

[27]Wang, R.P., Shan, S.G., Chen, X.L., et al., 2008. Manifold-manifold distance with application to face recognition based on image set. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.1-8.

[28]Weinberger, K.Q., Saul, L.K., 2009. Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res., 10:207-244.

[29]Wright, J., Yang, A.Y., Ganesh, A., et al., 2009. Robust face recognition via sparse representation. IEEE Trans. Patt. Anal. Mach. Intell., 31(2):210-227.

[30]Xu, Y., Zuo, W.M., Fan, Z.Z., 2012. Supervised sparse representation method with a heuristic strategy and face recognition experiments. Neurocomputing, 79:125-131.

[31]Xu, Y., Zhu, Q., Fan, Z.Z., et al., 2013. Using the idea of the sparse representation to perform coarse-to-fine face recognition. Inform. Sci., 238:138-148.

[32]Yang, M., Zhang, L., 2010. Gabor feature based sparse representation for face recognition with gabor occlusion dictionary. Proc. 11th European Conf. on Computer Vision, p.448-461.

[33]Yang, M., Zhang, D., Yang, J., 2011. Robust sparse coding for face recognition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.625-632.

[34]Yu, Z.P., Wu, Z.D., Zhang, J.W., 2013. An illumination robust algorithm for face recognition via SRC and Gradientfaces. Proc. 2nd Int. Conf. on Innovative Computing and Cloud Computing, p.36-40.

[35]Zhang, D., Yang, M., Feng, X.C., 2011. Sparse representation or collaborative representation: which helps face recognition? Proc. IEEE Int. Conf. on Computer Vision, p.471-478.

[36]Zhang, Q., Li, B.X., 2010. Discriminative K-SVD for dictionary learning in face recognition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.2691-2698.

[37]Zhou, T.Y., Tao, D.C., Wu, X.D., 2011. Manifold elastic net: a unified framework for sparse dimension reduction. Data Min. Knowl. Discov., 22(3):340-371.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE