结合小波局部特征与LDA的人脸识别  

Face Recognition of Combining DWT Based Local Features and LDA

作　　者：曹智鑫 蔡茂国[1] 陈剑勇[1] 

机构地区：[1]深圳大学计算机与软件学院,广东深圳518060

出　　处：《电视技术》2014年第19期184-187,共4页Video Engineering

基　　金：国家自然科学基金项目(61170283)

摘　　要：提出了一种小波局部特征结合LDA(线性判别分析)的人脸识别算法。首先对图像分块,选取包含图像信息量多的区域进行小波变换并提取特征,将小波分解得到的低频部分利用LDA投影求得人脸识别特征,最后利用最近邻分类器对图像进行分类。在ORL和Yale人脸数据库上进行实验,结果表明使用小波局部特征结合LDA的方法可达到较高的识别率。A face recognition algorithm based on local features of DWT （ Discrete Wavelet Transform） is proposed. Firstly, the image is divided into several blocks, and the image area which contains more information is selected for wavelet transform to extract features, and then the approximate wavelet coefficients which are the high-scale low-frequency components of the signal are utilized to be projected by LDA to capture recognition fea- tures. Finally, the nearest neighbor classifier is used to perform face classification. The experimental results on ORL and Yale face databases show that the algorithm proposed achieve high recognition rate.

关 键 词：小波变换 LDA 最近邻分类器 人脸识别 

分 类 号：TN911.73[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]