二维类内差异信息保持的人脸识别  

Two-dimensional Intra-class Diversity Preserving for Face Recognition

作　　者：孔爱祥[1] 王成儒[1] 

机构地区：[1]燕山大学信息科学与工程学院,河北秦皇岛066004

出　　处：《光电工程》2012年第10期65-70,共6页Opto-Electronic Engineering

摘　　要：为了使增强的Fisher鉴别准则(EFDC)避免因PCA降维带来的鉴别信息丢失问题,本文将其进行二维推广,提出基于二维类内差异信息保持(2D-IDP)的人脸识别方法,该方法建立了一个鲁棒性更强的鉴别准则,使得投影后不同类的样本点尽量远离的同时,类内紧致性和差异信息都得到有效保持,避免了过学习现象的产生。同时对EFDC近邻图中的参数t作了重新定义,使其能根据不同的输入样本自适应的变化,避免了t选择不当导致的识别性能下降的问题。在YALE和AR人脸库上的实验表明了本文方法的有效性。In order to make Enhanced Fisher Disriminant Criterion（EFDC） avoid of impairing the discriminating information caused by PCA dimension reduction,based on EFDC,a method of two-dimensional Intra-class Diversity Preserving（2D-IDP） for face recognition is proposed.In this method,we built a more robust discriminate criterion which can make the data points of different class as distant as possible and simultaneously preserve the intra-class compactness and variation,and thus avoid the over-fitting problem.At the same time,we redefined parameter t in the neighbor graph of EFDC which made it change adaptively according to different samples.Thus it avoided the problem of performance degradation caused by inappropriate choice of t.Experiments on YALE and AR face database verify the effectiveness of the proposed method.

关 键 词：类内差异信息 Fisher线性鉴别准则 特征提取 人脸识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]