一种基于半监督学习的2DPCA人脸识别方法  

A semi-supervised learning based 2DPCA face recognition method

作　　者：李凯[1] 徐治平[1] 

机构地区：[1]河北大学数学与计算机学院,河北保定071002

出　　处：《河北大学学报（自然科学版）》2013年第4期413-419,共7页Journal of Hebei University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61073121);河北省自然科学基金资助项目(F2012201014)

摘　　要：结合半监督学习中的自学习技术以及二维主成分分析(two-dimensional principal component analysis-2DPCA)方法,提出了一种基于半监督学习的人脸识别方法.在二维主成分分析的基础上,利用少量具有类别标签的样本训练分类器,然后利用半监督学习中的自学习技术,对未知类别标签的人脸样本进行分类,并将具有高置信度的人脸样本加入到训练集中,以此增加训练集中的人脸样本数量.在ORL人脸库和Yale人脸库的实验结果,表明了提出方法的有效性.By combining self-training method of the semi-supervised learning with two-dimensional principal component analysis （2DPCA）, a semi-supervised learning based face recognition method was proposed. On the basis of two-dimensional principal component analysis, few labeled samples were used to obtain classifier. Then unlabeled samples were classified through the classifier. And according to the selftraining method of semi-supervised learning, the face samples with the highest confidence were added to the training set in order to increase the number of face samples in training set. Experimental results on ORL face database and Yale face database showed the effectiveness of the presented method.

关 键 词：人脸识别 半监督学习 二维主成分分析法(2DPCA) 特征提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]