基于叠加协同表示分类的人脸识别  

Face recognition based on superposed collaborative representation based classification

作　　者：林国军 蒋行国 杨明中 李兆飞 解梅[3] LIN Guo-jun;JIANG Xing-guo;YANG Ming-zhong;LI Zhao-fei;XIE Mei(School of Automation & Information Engineering, Sichuan University of Science & Engineering, Zigong 643000, China;School of Electronic Engineering, Chengdu Technological University, Chengdu 611730, China;School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China)

机构地区：[1]四川轻化工大学自动化与信息工程学院,四川自贡643000 [2]成都工业学院电子工程学院,四川成都611730 [3]电子科技大学电子工程学院,四川成都611731

出　　处：《液晶与显示》2020年第2期161-166,共6页Chinese Journal of Liquid Crystals and Displays

基　　金：四川省教育厅项目(No.17ZB0302);四川轻化工大学科研项目(No.2019RC11,No.2019RC12)~~

摘　　要：针对叠加稀疏表示分类(SSRC)计算复杂度大的问题,利用协同表示分类(CRC)的计算复杂度比SRC少得多且识别率相似于SRC的优点,提出基于叠加协同表示分类(SCRC)的人脸识别。基于原型和变化的表示模型,在SCRC中,利用类质心和样本与质心的差异来构造成字典,可以显著地改善CRC的性能。实验结果表明,利用基于原型和变化的表示模型,协同表示在人脸识别中能起作用,甚至字典基在非受控和每类只有一个样本的条件下被汇集,协同表示也具有很好的性能。与其他算法相比,SCRC在大幅降低计算复杂度的同时保证了识别率。For the problem of the high computational complexity of the superposed sparse representation based classification(SSRC),the advantages of the collaborative representation based classification(CRC)that has significantly less complexity than SRC is used and its recognition rate is similar to SRC.The face recognition based on superposed collaborative representation based classification(SCRC)is proposed.Based on a prototype plus variation model,the dictionary is assembled by the class centroids and the sample-to-centroid differences in the SCRC,which can leads to a substantial improvement on CRC.The experimental results show that,if the proposed prototype plus variation representation model is applied,the collaborative representation plays a crucial role in face recognition,and performs well even when the dictionary bases are collected under uncontrolled conditions and only a single sample per classes is available.Compared with the other algorithms,SCRC greatly reduces the computational complexity and ensures the recognition rates.

关 键 词：人脸识别 协同表示 稀疏表示 字典 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]