基于自适应近邻图嵌入的局部鉴别投影算法  

Neighborhood Graph Embedding Based Local Adaptive Discriminant Projection

作　　者：王永茂[1,2] 徐正光[1] 赵珊[2] 

机构地区：[1]北京科技大学自动化学院,北京100083 [2]河南理工大学计算机科学与技术学院,焦作454000

出　　处：《电子与信息学报》2013年第3期633-638,共6页Journal of Electronics & Information Technology

基　　金：教育部科学技术研究重点项目(210128);河南省教育厅科学技术研究项目(12B520021)资助课题

摘　　要：针对局部Fisher鉴别分析(LFDA)中样本近邻点个数对于最优投影方向的影响以及在度量类间离差度时未考虑不同类别样本近邻点的两点不足之处,该文提出一种基于自适应近邻图嵌入的局部鉴别投影算法,根据样本分布以及样本间的相似度自适应计算类内和类间近邻点,依据类内类间近邻点的个数定义局部类内与类间离差矩阵中的权值矩阵,通过最大化局部类间离差度最小化局部类内离差度,得到最优低维子空间。该算法不仅能够保持样本的局部信息,而且能够保持样本的鉴别信息,在人工数据以及标准数据库上的实验表明该方法是有效的。As a dimensionality reduction algorithm, Local Fisher Discriminant Analysis （LFDA） is faced with two problems： （1） how to select the favorable neighborhood size which may have effect on the optimal projection direction and （2） the neglect of neighborhood relationships between samples of different classes. In order to overcome the drawback of LFDA, a novel dimensionality reduction algorithm called neighborhood graph embedding based Local Adaptive Discriminant Projection （LADP） is proposed in this paper. First, LADP adaptively estimates within-class and between-class neighborhood set according to samples＇ distribution and similarity. Then local weighted matrices are defined depending on the neighborhood size. Ultimately optimal embedding subspace is gained by maximizing local between-class scatter and minimizing local within-class scatter. LADP can preserve both local information and discriminant information. The experimental results of the toy example and real-word data validate the effectiveness of the proposed algorithm.

关 键 词：模式识别 降维 自适应近邻图 局部Fisher鉴别分析 分类识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]