南京邮电大学学报（自然科学版）2017，Vol.37Issue(2)：51-56,6.DOI:10.14132/j.cnki.1673-5439.2017.02.009
基于协作表示的人脸表情识别
Facial expression recognition based on collaborative representation
摘要
Abstract
Aiming at the high computational complexity for solving sparse representation coefficients by using l1 norm minimization in sparse representation based classification (SRC) algorithm,this paper proposes a collaborative representation based classification (CRC) algorithm for facial expression recognition.Firstly,the normalized face image is divided into many non-overlapped sub-blocks,the feature vector for each sub-block is extracted using the uniform local binary pattern(LBP) operator and is weighted according to the information entropy of each sub-block image.A joint feature vector for describing the face image is obtained by concatenating the weighted feature vectors of all sub-blocks.Then,the principal component analysis (PCA) method is used to reduce the dimensions of the feature vector of test samples and training samples.Finally,the CRC algorithm is used to classify the test sample into seven categories:anger,disgust,fear,neutral,happy,sad,and surprised.The experimental results on JAFFE database demonstrate the effectiveness of the proposed algorithm.The recognition rate of CRC algorithm is almost the same as that of SRC algorithm,but the computational complexity is greatly reduced,and the recognition time is about 1/60 of SRC algorithm.关键词
人脸表情识别/协作表示/稀疏表示/局部二值模式/主成分分析Key words
facial expression recognition/collaborative representation/sparse representation/local binary pattern/principal component analysis分类
信息技术与安全科学引用本文复制引用
卢官明,石婉婉,李霞,张正言,闫静杰..基于协作表示的人脸表情识别[J].南京邮电大学学报（自然科学版）,2017,37(2):51-56,6.基金项目
国家自然科学基金(61071167,61501249)、江苏省重点研发计划(BE2016775)、江苏省自然科学基金(BK20150855)、江苏省高校自然科学研究面上项目(15KJB510022)和江苏省普通高校研究生科研创新计划(KYLX15_0827,KYLX16_0660)资助项目 （61071167,61501249）
