一种改进的核特征抽取方法及其在人脸识别中的应用  

An Improved Kernel Feature Extraction Method and its Application to Face Recognition

作　　者：林宇生[1] 郑宇杰[1] 杨静宇[1] 

机构地区：[1]南京理工大学计算机科学与技术系,南京210094

出　　处：《计算机辅助设计与图形学学报》2008年第1期61-65,共5页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(60472060,60503026,60705020)

摘　　要：首先利用核函数技术将原始样本隐式地映射到高维特征空间;然后在高维空间里利用再生核理论建立基于Fisher鉴别极小准则的2个等价模型;最后在该空间的核类间散布矩阵的非零空间和零空间中应用Fisher极小鉴别准则求取核鉴别矢量.在人脸库上的实验结果验证了该算法的有效性.The kernel trick is used firstly to project the original samples into an implicit space called feature space by nonlinear kernel mapping, then two equivalent models based on Fisher discriminant minimal criterion are established by the theory of reproducing kernel in the feature space. Finally, Fisher discriminant minimal criterion is carried out in the null space and non-null space going between kernel-class scatter of feature space, to obtain the optimal database show the effectiveness of the algorithm kernel discriminant vectors. Experimental results on face proposed.

关 键 词：特征抽取 核函数 人脸识别 零空间 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]