南京理工大学学报（自然科学版）2017，Vol.41Issue(4)：460-465,6.DOI:10.14177/j.cnki.32-1397n.2017.41.04.010
低秩鲁棒性主成分分析的遮挡人脸识别
Occlusion face recognition based on robust principal component analysis and low rank
摘要
Abstract
In order to improve the recognition accuracy of occlusion face,a novel occlusion face recognition algorithm combining robust principal component analysis and low rank is proposed.Firstly,face images are collected and are correspondingly pretreated,and secondly the face samples are decomposed by using robust principal component analysis to obtain low rank data matrix and sparse error matrix,and face images of training samples and testing samples are established.At last face is weighted and recognized according to the error matrix,the classic face database is used to carried out simulation experiment.The results show that the proposed algorithm has improved the occluded face recognition accuracy significantly,effectively reduces the error rate of the occluded face,and has better robustness.关键词
鲁棒性主成分分析/模式识别/遮挡人脸/低秩映射/误识率Key words
robust principal component analysis/pattern recognition/occlusion face/low rank mapping/error rate分类
信息技术与安全科学引用本文复制引用
唐娴,黄军伟..低秩鲁棒性主成分分析的遮挡人脸识别[J].南京理工大学学报（自然科学版）,2017,41(4):460-465,6.基金项目
河南省教育科学"十二五"规划项目(2014JKGHC-0155) （2014JKGHC-0155）
