基于样本扩展和线性子空间特征提取的单样本人脸识别  

Single Sample Face Recognition with Virtual Samples and Linear Subspace Feature Extraction

作　　者：孟一飞[1] 袁雪[1] 魏学业[1] 秦飞舟[2] 覃庆努[1] 

机构地区：[1]北京交通大学电子信息工程学院,北京100044 [2]宁夏大学物理电气信息学院,银川750021

出　　处：《应用科学学报》2013年第5期488-494,共7页Journal of Applied Sciences

基　　金：国家自然科学基金(No.61301186);高等学校博士学科点专项科研基金(No.20110009120003);北京交通大学校基金(No.W11JB00460)资助

摘　　要：针对单训练样本情况下的人脸识别问题,提出一种虚拟样本扩展方法.利用光照模板映射将单一样本扩展为一组虚拟样本,从而增强单训练样本的分类信息.采用主成分分析(principal component analysis,PCA)对扩展的虚拟样本进行降维,并用Fisher鉴别变换作二次特征抽取,然后用最近邻分类器识别人脸图像.所提方法在人脸图像库Yale B和Extended Yale B上进行试验,用PCA+LDA方法把扩展图像作为训练集对测试图像进行特征提取和识别.相对于以单样本图像为训练集的PCA特征提取,该方法显著提高了识别率.A method of reference model illumination mapping is proposed to deal with the problem of one sample per person. To enhance the classification information of single training sample, we extend virtual images generated from the given single training image. Using discrete wavelet transform （DWT）, the low-frequency band is processed to map the illumination information from the reference model to create a virtual sam- ple. Principle-component-analysis plus linear-discriminant-analysis （PCA^LDA） is performed on the virtual training set to extract features. Experiments are performed on the Yale B and extended Yale B facial image database. The results show that, compared with the PCA feature extraction with single sample, recognition rate is significantly higher using the proposed method.

关 键 词：人脸识别 单人单样本 主成分分析 线性鉴别分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]