Computer Science ›› 2017, Vol. 44 ›› Issue (2): 302-305.doi: 10.11896/j.issn.1002-137X.2017.02.051

Previous Articles     Next Articles

Sparse Orthogonal Procrustes Problem Based Regression for Face Recognition with Pose Variations

ZHANG Juan   

  • Online:2018-11-13 Published:2018-11-13

Abstract: Orthogonal Procrustes problem (OPP) is a popular technique to deal with matrix approximation problem.Recently,OPP was introduced into a regression model named orthogonal Procrustes problem based regression (OPPR) to handle facial pose variations and achieved interesting results.However,OPPR performs F-norm constraint on the error term,which makes the model sensitive to the noises (i.e.,illumination variations).To address this problem,in this paper,the F-norm constraint was replaced by the L1-norm constraint and the sparse orthogonal Procrustes problem based regression (SOPPR) model was proposed,which is more robust.The proposed model was then solved by an efficient alternating iterative algorithm.Experimental results on public face databases demonstrate the effectiveness of the proposed model for handling facial pose variations.

Key words: Orthogonal procrustes problem,Facial pose variations,Regression model

[1] WRIGHT J,YANG A,GANESH A,et al.Robust face recognition via sparse representation [J].IEEE Trans.PAMI,2009,31(2):210-227.
[2] NASEEM I,TOGNERI R,BENNAMOUN M.Linear regres-sion for face recognition [J].IEEE Trans.PAMI,2010,32(11):2106-2112.
[3] ZHANG L,YANG M,FENG X C.Sparse representation or collaborative representation which helps face recognition[C]∥ICCV.2011.
[4] DING C X,TAO D C.A comprehensive survey on pose-inva-riant face recognition [R].arXiv:1502.04383,2015.
[5] CHAI X J,SHAN S G,CHEN X L,et al.Locally linear regression for pose-invariant face recognition[J].IEEE Trans.on Ima-ge Processing,2007,16(7):1716-1725.
[6] SHARMA A,JACOBS D W.Bypassing synthesis:Pls for face recognition with pose,low-resolution and sketch[C]∥CVPR.2011.
[7] LI A N,SHAN S G,GAO W.Coupled bias-variance tradeoff forcross-pose face recognition [J].IEEE Trans.on Image Proces-sing,2012,21(1):305-315.
[8] ZHANG H C,ZHANG Y N,HUANG T.Pose-robust face re-cognition via sparse representation [J].Pattern Recognition,2013,46(5):1511-1521.
[9] TAI Y,YANG J,LUO L,et al.Orthogonal Procrustes Problem based Regression with Application to Face Recognition with Pose Variations[C]∥Iscide.2015.
[10] GREEN B.The orthogonal approximation of an oblique simple structure in factor analysis [J].Psychometrika,1952,17:429-440.
[11] GOWER J,DIJKSTERHUIS G.Procrustes problems [M].Oxford University Press,2004.
[12] VIKLANDS T.Algorithms for the weighted orthogonal pro-crustes problem and other least squares problems [D].UMEA University,2006.
[13] WAGNER A,WRIGHT J,GANESH A,et al.Towards a practical face recognition system:robust alignment and illumination by sparse representation[J].IEEE Trans.PAMI,2012,34:372-386.
[14] YU L B,ZHANG M,DING C.An efficient algorithm for L1-norm principal component analysis[C]∥ICASSP.2012
[15] YANG A,GANESH A,ZHOU Z,et al.Fast l1-minimization algorithms and application in robust face recognition [R].UC Berkeley,2010.
[16] SIM T,BAKER S,BSAT M.The cmu pose,illumination,andexpression database[J].IEEE Trans.PAMI,2003,25(12):1615-1618.
[17] GROSS R,MATTHEWS I,COHN J,et al.Multi-pie [J].Image and Vision Computing,2010,28:807-813.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!