计算机科学 ›› 2014, Vol. 41 ›› Issue (4): 309-313.
杜海顺,张旭东,侯彦东,金勇
DU Hai-shun,ZHANG Xu-dong,HOU Yan-dong and JIN Yong
摘要: 针对基于稀疏表示分类器(Sparse Representation-based Classification,SRC)的人脸识别方法用单位阵作误差字典不能很好地描述人脸图像噪声和误差以及由于训练样本不足可能造成字典不完备的问题,提出一种基于低秩恢复稀疏表示分类器(Low Rank Recovery Sparse Representation-based Classification,LRR_SRC)的人脸识别方法。该方法首先采用低秩矩阵恢复(LRR)算法将训练样本矩阵分解为一个低秩逼近矩阵和一个稀疏误差矩阵。然后,由低秩逼近矩阵和误差矩阵组成字典。在此基础上,得到测试样本在该字典下的稀疏表示。更进一步,基于测试样本的稀疏表示系数和字典,对测试样本进行类关联重构,并计算其类关联重构误差。最后,基于类关联重构误差,完成测试样本的分类识别。在YaleB和CMU PIE人脸数据库上的实验结果表明,提出的基于LRR_SRC的人脸识别方法具有较高的识别率。
[1] Vinje W E,Gallant J L.Sparse coding and decorrelation in primary visual cortex during natural vision [J].Science,2000,287(5456):1273-1276 [2] Elad M,Aharon M.Image denoising via sparse and redundantrepresentations over learned dictionaries [J].IEEE Trans.Image Processing,2006,15(12):336-3745 [3] Mairal J,Elad M,Sapiro G.Sparse representation for color ima-ge restoration [J].IEEE Trans.Image Processing,2008,17(1):53-69 [4] Mairal J,Bach F,Ponce J,et al.Nonlocal sparse models for image restoration [C]∥Proc.ICCV.2009:2272-2279 [5] Wang C,Yan S,Zhang L,et al.Multi-Label Sparse coding forautomatic image annotation [C]∥Proc.IEEE Conf.CVPR.2009:1643-1650 [6] Wright J,Ma Y,Mairal J,et al.Sparse Representation for Computer Vision and Pattern Recognition [J].Proc.IEEE,2010,98(6):1031-1044 [7] Wright J,Yang A Y,Ganesh A,et al.Robust Face Recognition via Sparse Representation [J].IEEE Trans.Pattern Anal.Mach.Intel.,2009,31(2):210-227 [8] Deng W H,Hu J,Guo J.Extended SRC:Undersampled FaceRecognition via Intra-Class Variant Dictionary [J].IEEE Trans.Pattern Anal.Mach.Intel.,2012,34(9):1864-1870 [9] Cai J,Candes E,Shen Z.A singular value thresholding algorithm for matrix completion [J].SIAM Journal of Optimization,2010,20(4):1956-1982 [10] Candes E,Li X D,Ma Y,et al.Robust principal component analysis? [J].Journal of the ACM,2011,58(3) [11] Figueiredo M,Nowak R,Wright S.Gradient projection forsparse reconstruction:Application to compressed sensing and other inverse problems [J].IEEE Journal of Selected Topics in Signal Processing,2007,1(4):586-597 [12] Malioutov D,Cetin M,Willsky A.Homotopy continuation for sparse signal representation[C]∥Proc.ICASSP.2005 [13] Beck A,Teboulle M.A fast iterative shrinkage-thresholding algorithm for linear in-verse problems[J].SIAM Journal on Imaging Sciences,2009(2):183-202 [14] Kim S-J,Koh K,Lustig M,et al.A method for large-scale l1-regularized least squares [J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):606-617 [15] Lin Z,Chen M,Wu L,et al.The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices [R].UIUC Tech.Rep.UILU-ENG-09-2215.2009 [16] Georghiades A S,Belhumeur P N,Kriegman D J,et al.From few to many:illumination cone models for face recognition under variable lighting and pose [J].IEEE Trans.Pattern Anal.Mach.Intelligence,2001,23(6):643-660 [17] Sim T,Baker S,Bsat M.The CMU pose,illumination,and expression database [J].IEEE Trans.Pattern Anal.Mach.Intell.,2003,25(12):1615-1618 |
No related articles found! |
|