最小化相关性的二维主成分分析  

Correlation Minimized Based 2-Dimensional Principal Component Analysis

作　　者：严慧[1] 金忠[1] 杨静宇[1] 

机构地区：[1]南京理工大学计算机科学与技术学院,南京210094

出　　处：《模式识别与人工智能》2010年第1期7-10,共4页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金重点项目(No.60632050);国家自然科学基金项目(No.606472060;60473039);国家863计划项目(No.2006AA01Z119)资助

摘　　要：指出在二维主成分分析中,特征向量的任意两个分量之间是相关的,并给出此相关性的数学表达,进一步提出最小化相关性的二维主成分分析.该方法改进二维主成分分析的目标函数,最大化特征向量间总体散度的同时,最小化特征向量各分量间的相关性.最后,在Yale标准人脸库上的实验结果表明,文中方法有较强的特征抽取能力,在识别性能上优于二维主成分分析及对角二维主成分分析.It is indicated that two components belonging to the feature vector are correlated and the corresponding mathematical expression （2DPCA） is presented. The correlation minimized based 2-dimensional principal component analysis is proposed. It maximizes the total scatter of the feature vectors meanwhile minimizes the correlations of arbitrary two components belonging to the feature vector. The experimental results on Yale face database indicate that the proposed method has powerful ability of feature extraction and higher face recognition rates than 2DPCA and DiaPCA.

关 键 词：二维主成分分析 相关性 最小化相关性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]