局部稀疏表示的鲁棒PCA人脸识别
|
摘要
近来提出了一种基于误差分析的鲁棒PCA人脸识别算法,然而当字典增大时,低秩分解就变得很复杂。针对此问题提出了一种局部稀疏表示的鲁棒PCA人脸识别算法。根据稀疏表示系数之间的相似性,选取邻近样本组成新的字典,然后通过鲁棒PCA进行低秩人脸识别。通过Yale、ORL人脸数据的实验,表明该算法对光照、遮挡仍具有较好的鲁棒性,同时大大减少计算成本。另一方面也说明通过稀疏表示选取邻近样本的可行性。
Recent years, a robust PCA method based on error analysis has been used in the face recognition. When the dictionary size is large, the robust PCA decomposition process becomes complicated. So a kind of robust PCA face recognition algorithm based on sparse representation has been put forward according to the similarity of sparse coefficient between test and training samples in this paper. We select adjacent samples as a new dictionary, then complete the face recognition through the robust PCA. Using Yale, ORL face data, experiments show that the algorithm has good robustness on light and shade, and greatly reduces computation cost. On the other hand, it shows the feasibility by sparse representation select adjacent samples.
Recent years, a robust PCA method based on error analysis has been used in the face recognition. When the dictionary size is large, the robust PCA decomposition process becomes complicated. So a kind of robust PCA face recognition algorithm based on sparse representation has been put forward according to the similarity of sparse coefficient between test and training samples in this paper. We select adjacent samples as a new dictionary, then complete the face recognition through the robust PCA. Using Yale, ORL face data, experiments show that the algorithm has good robustness on light and shade, and greatly reduces computation cost. On the other hand, it shows the feasibility by sparse representation select adjacent samples.
引文
[1] Lee D, Seung H. Learning the parts of objects by non-negative matrix factorization [J]. Nature,1999,401(675):788-791.
[2] Belhumeur P, Hespanha J, Kriegman D. Eigenfaces vs Fisherfaces:recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[3] Wright J,Yang A, Ganesh A, et al. Robust face recognition via sparse representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227.
[4] Naseem I, Togneri R, Bennamounm. Linear regression for face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,32(11):2106-2112.
[5] Liu G, Lin Z, Yan S, et al. Robust recovery of subspace structures by low-rank representation [J].Pattern Analysis and Machine Intelligence, 2013,35(1):171-184.
[6] Luan Xiao, Fang Bin, Liu Ling-hui, et al. Extracting sparse error of robust PCA for face recognition in the presence of varying illumination and occlusion[J]. Pattern Recognition,2014,47(2): 495 -508.
[7] Yang A Y, Ganesh A, Sastry S S, et al. Fast L1 minimization algorithms and an application in robust face recognition: A review[C]// IEEE International conference on Image Processing. Colifornia, USA:IEEE Press,2010:1849-1852.
[8] Ortiz E G, Becker B C. Face recognition for webscale datasets[J]. Computer Vision and Image Understanding, 2014(118): 153-170.
[9] Mi Jian-xun. Face image recognition via collaborative representation on selected training samples[J]. Optik-International Journal for Light and Electron Optics,2013,124(18):3310-3313.
[10] Cheng Bin, Yang Jian-chao, Yan Shui-Cheng, et al. Learning with graph for image analysis[J]. IEEE Transactions on Image Processing, 2010, 19(4): 858-866.
[11] Wright J, Ganesh A, Rao S, et al. Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization[C]//Proceeding of Advanves in Neural Information Prcocessing Systems. Vancouver, Canada: NIPS 2009: 2080-2088.
[2] Belhumeur P, Hespanha J, Kriegman D. Eigenfaces vs Fisherfaces:recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[3] Wright J,Yang A, Ganesh A, et al. Robust face recognition via sparse representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227.
[4] Naseem I, Togneri R, Bennamounm. Linear regression for face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,32(11):2106-2112.
[5] Liu G, Lin Z, Yan S, et al. Robust recovery of subspace structures by low-rank representation [J].Pattern Analysis and Machine Intelligence, 2013,35(1):171-184.
[6] Luan Xiao, Fang Bin, Liu Ling-hui, et al. Extracting sparse error of robust PCA for face recognition in the presence of varying illumination and occlusion[J]. Pattern Recognition,2014,47(2): 495 -508.
[7] Yang A Y, Ganesh A, Sastry S S, et al. Fast L1 minimization algorithms and an application in robust face recognition: A review[C]// IEEE International conference on Image Processing. Colifornia, USA:IEEE Press,2010:1849-1852.
[8] Ortiz E G, Becker B C. Face recognition for webscale datasets[J]. Computer Vision and Image Understanding, 2014(118): 153-170.
[9] Mi Jian-xun. Face image recognition via collaborative representation on selected training samples[J]. Optik-International Journal for Light and Electron Optics,2013,124(18):3310-3313.
[10] Cheng Bin, Yang Jian-chao, Yan Shui-Cheng, et al. Learning with graph for image analysis[J]. IEEE Transactions on Image Processing, 2010, 19(4): 858-866.
[11] Wright J, Ganesh A, Rao S, et al. Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization[C]//Proceeding of Advanves in Neural Information Prcocessing Systems. Vancouver, Canada: NIPS 2009: 2080-2088.