基于图的有监督判别投影  

Graph-based supervised discriminant projection

作　　者：徐伟[1] 王正群[1] 周中侠[1] 李峰[1] 

机构地区：[1]扬州大学信息工程学院,江苏扬州225009

出　　处：《计算机工程与设计》2013年第3期970-973,988,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(61175111);江苏省自然科学基金项目(BK2009184);江苏省高校自然科学基金项目(10KJB510027)

摘　　要：无监督鉴别投影没有利用样本类别标签,所以没有利用样本的鉴别信息。该文在无监督鉴别投影算法的基础上提出了基于图的有监督判别投影(graph-based supervised discriminant projection,GSDP)算法,利用吸引图和排斥图设计目标函数进行特征抽取,建立吸引图的目的是使同类但不是近邻的样本互相吸引,建立排斥图的目的是击退近邻但不是同类的样本。在Feret,Yale和Orl这3个标准人脸库上的大量实验表明了该算法的有效性。Unsupervised discriminant projection algorithm is a kind of supervised algorithm, which does not use label informa tion, so it does not use discriminant information of samples. A graphbased supervised discriminant projection algorithm based on unsupervised discriminant projection algorithm is presented. The algorithm use repulsion graphs and affinity graphs to extract feature. The purpose of using affinity graphs is to make two samples which are in the same class but not nearby attractive and the purpose of constracting repulsion graphs is to repel two samples which are nearby and in different class. The experiments on Fe ret, Yale and Orl face image datebase show the effectiveness of the proposed algorithm.

关 键 词：降维 无监督鉴别投影 吸引图 排斥图 人脸识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]