基于稀疏表示与特征融合的人脸识别方法Face recognition method based on sparse representation and feature fusion
木立生,吕迎春
摘要(Abstract)：
针对人脸识别在有遮挡、表情、光照的变化或受到噪声污染时鲁棒性变差问题,提出一种基于稀疏表示与特征融合的人脸识别算法。首先采用低秩恢复算法得到训练样本和测试样本的干净人脸图像,提取干净人脸图像的LBP,HOG,Gabor三种特征向量;然后对部分训练样本进行SRC分类测试,根据SRC的识别结果与分类残差定义一个损失函数,再利用正则化最小二乘法计算出使损失函数最小的权重向量;最后根据该权重向量重构规则化残差进行分类。在ORL,Extended Yale B和AR数据库上进行实验,结果表明,该算法优于利用单一特征识别的方法,并且对光照、噪声、遮挡等因素产生的影响有较好的泛化性能。
关键词(KeyWords)： 人脸识别;稀疏表示;低秩恢复;特征融合;鲁棒性;泛化性能
基金项目(Foundation): 国家自然科学基金资助项目(51279122)~~
作者(Author): 木立生,吕迎春
DOI: 10.16652/j.issn.1004-373x.2018.09.018
参考文献(References)：
- [1]WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE transactions on pattern analysis and machine intelligence,2009,31(2):210-227.
- [2]胡正平,白帆,王蒙,等.有监督低秩子空间恢复的正则鲁棒稀疏表示人脸识别算法[J].信号处理,2016,32(11):1299-1307.HU Z P,BAI F,WANG M,et al.Regularized robust sparse representation face recognition algorithm based on supervised low-rank subspace recovery[J].Journal of signal processing,2016,32(11):1299-1307.
- [3]YANG M,ZHANG L,YANG J,et al.Robust sparse coding for face recognition[C]//2011 IEEE Conference on Computer Vision&Pattern Recognition.Colorado Springs:IEEE,2011:625-632.
- [4]WEN Y,LIU W,YANG M,et al.Regularized robust coding for face recognition[J].Computer science,2012,22(5):1753-1766.
- [5]汤镇宇,孟凡荣,王志晓.基于稀疏表示的快速l2-范数人脸识别方法[J].计算机应用研究,2016,33(9):2831-2836.TANG Z Y,MENG F R,WANG Z X.Fast face recognition with regularized least square via sparse representation[J].Application research of computers,2016,33(9):2831-2836.
- [6]CANDES E J,LI X D,MA Y,et al.Robust principal component analysis[J].Journal of the ACM,2011,58(3):2-37.
- [7]LIU G C,LIN Z C,YAN S C,et al.Robust recovery of subspace structures by low-rank representation[J].IEEE transactions on pattern analysis and machine intelligence,2013,35(1):171-184.
- [8]关学忠,王文锋,张新城,等.基于小波变换和多特征融合算法的人脸识别[J].计算机工程与应用,2016,52(12):201-204.GUAN X Z,WANG W F,ZHANG X C,et al.Face recognition method based on wavelet transform and multi-feature fusion algorithm[J].Computer engineering and applications,2016,52(12):201-204.
- [9]SHAO Y,TANG C,XIAO M,et al.Fusing facial texture features for face recognition[J].Proceedings of the National Academy of Sciences India,2016,88(3):1-9.
- [10]杨赛,赵春霞,刘凡.多核学习融合局部和全局特征的人脸识别算法[J].电子学报,2016,44(10):2344-2350.YANG S,ZHAO C X,LIU F.Fusion of local and global features using multiple kernel learning for face recognition[J].Acta electronic sinica,2016,44(10):2344-2350.
- [11]YANG Y,SONG J,HUANG Z,et al.Multi-feature fusion via hierarchical regression for multimedia analysis[J].IEEE transactions on multimedia,2013,15(3):572-581.