一种新的核广义鉴别特征抽取方法  

New kernel generalized optimal feature extraction method

作　　者：徐春明[1] 张天平[1] 王正群[1] 王向东[1] 

机构地区：[1]扬州大学信息工程学院

出　　处：《计算机应用》2005年第9期2134-2136,2142,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(60074013)

摘　　要：在基于核的广义鉴别特征模型的基础上,提出了一种新的核广义鉴别特征抽取方法。利用空间变换的有关理论,使得变换后的核总体散布矩阵满足非奇异性;同时通过核共轭特征抽取方法,抽取满足核共轭正交条件的特征向量,使抽取的特征满足统计不相关性。在ORL人脸库上的实验表明了所提方法的有效性,达到了比核鉴别分析等方法更好的识别效果。Based on the theory of kernel generalized optimal feature extracted mode, a new method for the corresponding mode was proposed. Firstly space transform method was used to transform initial kernel between class scatter matrix and kernel total scatter matrix, so the kernel total scatter matrix became positive definition. At the same time, by the means of kernel tmcorrelated feature vectors extraction, the feature vectors got were statistical uncorrelated. To verify the effectiveness of this method, experiment was tested on ORL face databases and the result showed that the face recognition method proposed is more available than other methods such as kernel discriminant analysis.

关 键 词：广义鉴别分析 核广义鉴别分析 人脸识别 特征抽取 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]