[1]虞 涛,童 莹,曹雪虹.基于迭代加权低秩分解的遮挡人脸识别算法[J].计算机技术与发展,2019,29(06):42-46.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 009]
　YU Tao,TONG Ying,CAO Xue-hong.An Occlusion Face Recognition Algorithm Based on Iteratively Reweighted Robust Principal Component[J].,2019,29(06):42-46.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 009]
点击复制

基于迭代加权低秩分解的遮挡人脸识别算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年06期
页码:
42-46
栏目:
智能、算法、系统工程
出版日期:
2019-06-10

文章信息/Info

Title:
An Occlusion Face Recognition Algorithm Based on Iteratively Reweighted Robust Principal Component
文章编号:
1673-629X(2019)06-0042-05
作者:
虞 涛1 ; 童 莹2 ; 曹雪虹2
1. 南京邮电大学 通信与信息工程学院,江苏 南京 210003;2. 南京工程学院 通信工程学院,江苏 南京 211167
Author(s):
YU Tao1 ; TONG Ying2 ; CAO Xue-hong2
1. School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China; 2. School of Communication Engineering,Nanjing Institute of Technology,Nanjing 211167,China
关键词:
迭代加权低秩分解; 稀疏表示; 人脸识别; 遮挡矩阵
Keywords:
iteratively reweighted robust principal component analysis; sparse representation; face recognition; occlusion matrix
分类号:
TP273
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 06. 009
摘要:
针对传统低秩矩阵分解算法得出的稀疏矩阵中既包含遮挡因素和噪声因素的问题,提出基于迭代加权低秩分解的遮挡人脸识别算法。 首先,利用迭代加权低秩分解算法分别提取各类训练样本中包含的遮挡和噪声因素。 然后针对测试样本和训练样本遮挡情况有差异的问题,利用迭代加权低秩分解算法提取测试样本中包含遮挡所掩盖的信息。 最后将每类训练样本的低秩矩阵、遮挡矩阵、噪声矩阵和测试样本中的遮挡向量构造新的联合字典,将测试样本表示为新的联合字典的稀疏线性组合,利用稀疏逼近计算残差,通过得到的系数进行分类判别。 实验结果表明,基于迭代加权低秩分解的遮挡人脸识别算法在 AR 和 Extended Yale B 库上的识别率得到提高,相比其他方法有较好的识别结果,验证了该算法的有效性,对于遮挡情况具有很好的鲁棒性。
Abstract:
Aiming at the problem that the sparse matrix obtained by the traditional low rank matrix decomposition algorithm contains both occlusion factors and noise factors,we propose an occlusion face recognition algorithm based on iteratively reweighted robust principal component analysis. First,the iteratively reweighted robust principal component analysis is used to extract the occlusion and noise factors contained in each training sample. Then,for the problem that the test sample and the training sample have different occlusion conditions,the iteratively reweighted robust principal component analysis is used to extract the information covered by the occlusion contained in the test sample. Finally,low-rank matrix,occlusion matrix,noise matrix and occlusion vector in the test sample of each type of training samples are constructed into a new joint dictionary,and the test samples are represented as sparse linear combinations of the new joint dictionary,and the residuals are calculated by sparse approximation. The classification is determined by the obtained coefficients. The experiment shows that the recognition rate of the proposed algorithm is improved on AR and Extended Yale B library. Compared with other methods,it has better recognition results,which is proved to be effect,and is robust to occlusion.

相似文献/References:

[1]朱伟冬 胡剑凌.基于马氏距离的稀疏表示分类算法[J].计算机技术与发展,2011,(11):27.
　ZHU Wei-dong,HU Jian-ling.Sparse Representation Classification Algorithm Based on Mahalanobis Distance[J].,2011,(06):27.
[2]王韦刚 庄伟胤.基于NIOS Ⅱ的图像压缩感知[J].计算机技术与发展,2012,(04):12.
　WANG Wei-gang,ZHUANG Wei-yin.Compressed Sensing of Image Based on NIOS Ⅱ[J].,2012,(06):12.
[3]葛广重,杨敏.基于稀疏表示的单幅图像超分辨率重建[J].计算机技术与发展,2013,(09):113.
　GE Guang-zhong,YANG Min.Single Image Super-resolution Reconstruction Based on Sparse Representation[J].,2013,(06):113.
[4]赵海峰,于雪敏,邹际祥,等.基于L1范数主成分分析的颅脑图像恢复[J].计算机技术与发展,2014,24(01):231.
　ZHAO Hai-feng[],YU Xue-min[],ZOU Ji-xiang[],et al.Cerebral Image Recovery Based on L1-norm Principal Component Analysis[J].,2014,24(06):231.
[5]陈静,邱晓晖,孙娜. 基于二维Gabor小波与SPP算法的人脸识别研究[J].计算机技术与发展,2014,24(11):110.
　CHEN Jing,QIU Xiao-hui,SUN Na. Research on Face Recognition Based on 2 D Gabor Wavelet and SPP Algorithm[J].,2014,24(06):110.
[6]姚刚,杨敏. 稀疏子空间聚类的惩罚参数自调整交替方向法[J].计算机技术与发展,2014,24(11):131.
　YAO Gang,YANG Min. Alternating Direction Method of Self-adjusting Penalty Parameters of Sparse Subspace Clustering[J].,2014,24(06):131.
[7]徐静妹,李 雷.基于稀疏表示和支持向量机的人脸识别算法[J].计算机技术与发展,2018,28(02):59.[doi:10．3969/j．issn．1673－629X．2018．02．014]
　XU Jingmei,LI Lei.A Face Recognition Algorithm Based on Sparse Ｒepresentation and Support Vector Machine[J].,2018,28(06):59.[doi:10．3969/j．issn．1673－629X．2018．02．014]
[8]钱阳,李雷. 一种基于新型KPCA算法的视频压缩感知算法[J].计算机技术与发展,2015,25(10):101.
　QIAN Yang,LI Lei. A Video Compressed Sensing Algorithm Based on Novel KPCA[J].,2015,25(06):101.
[9]余琨,荆晓远,吴飞,等. 基于竞争聚集的K-SVD字典学习算法[J].计算机技术与发展,2015,25(11):44.
　YU Kun,JING Xiao-yuan,WU Fei,et al. K-SVD Dictionary Learning Algorithm Based on Competitive Agglomeration[J].,2015,25(06):44.
[10]于云,周伟栋. 基于稀疏表示的鲁棒性说话人识别系统[J].计算机技术与发展,2015,25(12):41.
　YU Yun,ZHOU Wei-dong. Robust Speaker Recognition System Based on Sparse Representation[J].,2015,25(06):41.

更新日期/Last Update: 2019-06-10