登录 | 注册 | 充值 | 退出 | 公司首页 | 繁体中文 | 满意度调查
综合馆
融合整体与局部特征的低秩松弛协作表示
  • 摘要

    目前的人脸识别算法经常忽视训练过程中噪声的影响,训练数据受到污染时识别性能会明显下降.针对该问题,提出了融合整体与局部特征的低秩松弛协作表示的人脸识别算法.通过低秩分解抑制训练样本的稀疏噪声,得到更加有效的人脸信息.利用松弛协作表示得到判别性更强的编码系数,增强人脸识别系统的判别性.为进一步提高识别率,提取局部特征的同时引入整体特征,运用整体特征和局部特征共同表示人脸图像.实验结果表明,尽管训练过程、测试过程都受到噪声污染,提出的算法对有光照、遮挡及表情变化的正面人脸图像的识别具有很好的鲁棒性,比现有的识别算法拥有更高的识别率.

  • 作者

    张盼  练秋生  Zhang Pan  Lian Qiusheng 

  • 作者单位

    燕山大学信息科学与工程学院 河北秦皇岛 066004

  • 刊期

    2014年12期 ISTIC EI PKU

  • 关键词

    人脸识别  低秩分解  松弛协作表示  整体特征  局部特征  face recognition  low rank decomposition  relaxed collaborative representation  global features  local features 

参考文献
  • [1] He Xiaofei;Yan Shuicheng;Hu Yuxiao. Face recognition using laplacianfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,03
  • [2] Wright J;Yang A;Ganesh A. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,02
  • [3] Gao Shenghua;Tsang I W;Chia L. Kernel sparse representation for image classification and face recognition. Berlin:Springer-Verlag, 2010
  • [4] Yang Meng;Zhang Lei. Gabor feature based sparse representation for face recognition with gabor occlusion dictionary. Berlin:Springer-Verlag, 2010
  • [5] Cheng Bin;Yang Jianchao;Yan Shuichen. Learning with l1-graph for image analysis. IEEE Transactions on Image Processing, 2010,04
  • [6] Zhang Lei;Yang Meng;Feng Xiangchu. Sparse representation or collaborative representation:Which helps face recognition. Piscataway,NJ:IEEE, 2011
  • [7] Yang Meng;Zhang Lei;Wang Shenlong. Relaxed collaborative representation for pattern classification. Los Alamitos,CA:IEEE Computer Society, 2012
  • [8] Zhou Chenlin;Chen Minming;Ma Yi. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices,UILU-ENG-09-2215. Urbana,Illinois:Department of Electrical and Computer Engineering,University of Illinois at Urbana-Champaign, 2009
  • [9] Zhou Chenlin;Ganesh A;Wright J. Fast convex optimization algorithms for exact recovery of a corrupted lowrank matrix,UILU-ENG-09-2214. Urbana,Illinois:Department of Electrical and Computer Engineering,University of Illinois at Urbana-Champaign, 2009
  • [10] Belhumeur P N;Hespanha J P;Kriegman D J. Eigenfaces vs fisherfaces recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,07
  • [11] Wright J;Ganesh A;Rao S. Robust principal component analysis:Exact recovery of corrupted low-rank matrices via convex optimization. New York:Curran Associates Inc, 2009
  • [12] Zheng Zhonglong;Zhang Haixin;Jia Jiong. Low-rank matrix recovery with discriminant regularization. Berlin:Springer-Verlag, 2013
  • [13] Chen Chih-Fan;Wei Chia-Po;Wang Yu-Chiang Frank. Low-rank matrix recovery with structural incoherence for robust face recognition. Los Alamitos,CA:IEEE Computer Society, 2012
  • [14] Cand'es E;Li Xiaodong;Ma Yi. Robust principa component analysis. Journal of the Association for Computing Machinery, 2011,03
  • [15] Ke Qifa;Kanade T. Robust l1 norm factorization in the presence of outliers and missing data by alternative convex programming. Los Alamitos,CA:IEEE Computer Society, 2005
  • [16] 边肇祺;张学工. 模式识别. 北京:清华大学出版社, 2000
  • [17] Jolliffe I T. Principal Component Analysis. Berlin:Springer-Verlag, 1986
  • [18] Kim C;Oh J;Choi C. Combined subspace method using global and local features for face recognition. Piscataway,NJ:IEEE, 2005
  • [19] Turk M;Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 1991,01
查看更多︾
相似文献 查看更多>>
3.80.223.123