A Kernel-Based Nonlinear Representor with Application to Eigenface Classification  

作　　者：张晶 刘本永 谭浩 

机构地区：[1]The Information Center of Sichuan Radio and Television University Chengdu 610073 China School of Computer Science and Technology, UESTC Chengdu 610054 China [2]School of Electronic Engineering, UESTC Chengdu 610054 China [3]School of Computer Science and Technology, UESTC Chengdu 610054 China

出　　处：《Journal of Electronic Science and Technology of China》2004年第2期19-22,共4页中国电子科技（英文版）

摘　　要：This paper presents a classifier named kernel-based nonlinear representor (KNR) for optimal representation of pattern features. Adopting the Gaussian kernel, with the kernel width adaptively estimated by a simple technique, it is applied to eigenface classification. Experimental results on the ORL face database show that it improves performance by around 6 points, in classification rate, over the Euclidean distance classifier.This paper presents a classifier named kernel-based nonlinear representor (KNR) for optimal representation of pattern features. Adopting the Gaussian kernel, with the kernel width adaptively estimated by a simple technique, it is applied to eigenface classification. Experimental results on the ORL face database show that it improves performance by around 6 points, in classification rate, over the Euclidean distance classifier.

关 键 词：kernel based nonlinear representor face recognition EIGENFACES Gaussian kernel euclidean distance classifier 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]