基于小波树和二维主元分析的人脸识别  

Face Recognition Based on Wavelet Tree and Two-dimensional Principal Component Analysis

作　　者：刘悦婷[1] 

机构地区：[1]兰州文理学院电子信息工程学院,甘肃兰州730000

出　　处：《佳木斯大学学报（自然科学版）》2015年第1期109-112,共4页Journal of Jiamusi University：Natural Science Edition

基　　金：甘肃省自然科学基金项目(1112RJZA028)

摘　　要：为提高人脸识别率,结合小波树和子空间分析中的二维主元分析,提出基于小波树和二维主元分析的人脸识别算法(WTMPCA).该算法先利用小波变换公式,在人脸图像上计算出一个小波近似分量和三个细节分量;分层次重组小波近似分量,得到新样本集;最后在此样本集上使用二维主元分析进行人脸识别.ORL和CAS-PEAL-R1人脸库的实验结果表明,与基于图像矩阵的二维主元分析(2D-PCA)相比较,WTMPCA方法的人脸识别率为96%,对光照条件、脸部表情变化有良好的鲁棒性.In order to improve the face recognition rate , this paper proposed face recognition based on wavelet tree and two -dimensional principal component analysis （WTMPCA）.The algorithm calculated a wave-let approximation coefficient and three detail components in face images with the help of the wavelet transform formula.Then, the wavelet approximation coefficients were recombine hierarchically .In the end, a new sample set and complete face recognition was gotten using two -dimensional principal component analysis .The simula-tion results of experiments on the ORL and CAS -PEAL-R1 face database show that compared with two -di-mensional principal component analysis （2D-PCA） based on image matrix , the new algorithm has a high recog-nition rate of 96%and better robustness to illumination condition and face expression change .

关 键 词：小波树 二维主元分析 人脸识别 小波变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]