图正则化稀疏判别非负矩阵分解  

Graph-regularized, sparse discriminant, non-negative matrix factorization

作　　者：徐慧敏 陈秀宏[1] XU Huimin;CHEN Xiuhong(School of Digital Media,Jiangnan University,Wuxi 214000,China)

机构地区：[1]江南大学数字媒体学院

出　　处：《智能系统学报》2019年第6期1217-1224,共8页CAAI Transactions on Intelligent Systems

基　　金：2018年江苏省研究生科研创新计划项目(KYCX18_1871)

摘　　要：非负矩阵分解是一种流行的数据表示方法,利用图正则化约束能有效地揭示数据之间的局部流形结构。为了更好地提取图像特征,给出了一种基于图正则化的稀疏判别非负矩阵分解算法(graph regularization sparse discriminant non-negative matrix factorization,GSDNMF-L2,1)。利用同类样本之间的稀疏线性表示来构建对应的图及权矩阵;以L2,1范数进行稀疏性约束;以最大间距准则为优化目标函数,利用数据集的标签信息来保持数据样本之间的流形结构和特征的判别性,并给出了算法的迭代更新规则。在若干图像数据集上的实验表明,GSDNMF-L2,1在特征提取方面的分类精度优于各对比算法。Non-negative matrix factorization is a popular data representation method.Using graph regularization con-straints can effectively reveal the local manifold structure between data.In order to better extract image features,a graph-regularized,sparse-discriminant,non-negative matrix factorization algorithm is proposed in this paper.The sparse linear representation between similar samples was used to construct the corresponding graph and weight matrix.The ob-jective function using the maximum margin criterion with L2,1-norm constraint was optimized,using the tag informa-tion of the dataset to maintain the manifold structure of samples and discrimination of characteristics,and the iterative update rules of the algorithm are given.Experiments were carried out on the ORL,AR,and COIL20 datasets.Com-pared with other algorithms,GSDNMF-L2,1 showed higher classification accuracy in feature extraction.

关 键 词：非负矩阵分解 特征提取 降维 流形学习 最大间距准则 判别信息 稀疏约束 线性表示 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]