近邻系数协同强化人脸图像子空间聚类法  

Nearest neighbor coefficient cooperative reinforcement subspace clustering method for face image

作　　者：许毅强 夏靖波[1] 简彩仁[1] 翁谦[2] XU Yiqiang;XIA Jingbo;JIAN Cairen;WENG Qian(Tan Kah Kee College,Xiamen University,Zhangzhou,Fujian 363105,China;College of Computer and Data Science,Fuzhou University,Fuzhou,Fujian 350108,China)

机构地区：[1]厦门大学嘉庚学院,福建漳州363105 [2]福州大学计算机与大数据学院,福建福州350108

出　　处：《福州大学学报（自然科学版）》2022年第5期581-586,共6页Journal of Fuzhou University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(41801324);福建省自然科学基金资助项目(2019J01244,2020J01039);福建省中青年教师教育科研项目(AT210631)。

摘　　要：针对最小二乘回归子空间聚类法没有考虑近邻样本对求解表示系数的影响这一不足,提出近邻系数协同强化子空间聚类法.该方法利用近邻样本相似导致表示系数接近的思想定义近邻系数协同强化项.通过近邻样本的系数强化表示系数,从而得到更能反映样本相似度的相似矩阵,进而提高聚类准确率.在6个人脸图像数据集上的实验表明,该方法是有效的.Least square regression subspace clustering method does not consider the influence of the nearest neighbor samples on solving the representation coefficient,the nearest neighbor coefficient cooperative reinforcement subspace clustering method is proposed.The proposed method defines the cooperative reinforcement term of neighbor coefficients by using the idea that the similarity of neighbor samples leads to the similarity of representation coefficients.The proposed method can improve the clustering accuracy by using the similarity matrix which can better reflect the similarity of samples.Experiments on six face image datasets show that this method is effective.

关 键 词：近邻系数 协同强化 人脸图像 子空间聚类 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论] TP371[自动化与计算机技术—计算机科学与技术]