| 结合2DWT和Fisherfaces的人脸特征提取新方法 |
| |
| 引用本文： | 刘金清,范群贞,吴庆祥.结合2DWT和Fisherfaces的人脸特征提取新方法[J].微计算机应用,2011,32(11):14-19. |
| |
| 作者姓名： | 刘金清 范群贞 吴庆祥 |
| |
| 作者单位： | 1. 福建师范大学物理与光电信息科技学院省光子技术重点实验室 福州350007
2. 福建师范大学物理与光电信息科技学院省光子技术重点实验室 福州350007;福建农林大学金山学院 福州350002 |
| |
| 基金项目： | 国家自然科学基金(61179011); 福建省自然科学基金资助项目(2010J01327) |
| |
| 摘 要： | 针对人脸表情变化对人脸识别的影响,提出一种结合小波变换(DWT)、特征脸方法(PCA)和线性判别法(LDA)的人脸特征提取新方法.首先将人脸图像通过二维小波变换(2DWT)提取其低频分量,然后将低频图像经过PCA变换映射到一个低维空间,最后在低维空间中利用LDA方法进行人脸特征的提取.通过此方法,采用ORL人脸库和Yale人脸库进行测试,我们可实现更准确的特征提取,并有效解决表情变化对人脸识别的影响问题.实验结果显示,本文方法在提高人脸识别率的同时,也提高了人脸识别速度.
|
| 关 键 词： | 特征提取 人脸表情识别 小波变换( DWT) 特征脸方法(PCA) 线性判别法(LDA) |
A Novel Method of Face Feature Extraction Based on 2DWT and Fisherfaces |
| |
| LIU Jinqing
,
FAN Qunzhen
,
WU Qingxiang.A Novel Method of Face Feature Extraction Based on 2DWT and Fisherfaces[J].Microcomputer Applications,2011,32(11):14-19. |
| |
| Authors: | LIU Jinqing FAN Qunzhen WU Qingxiang |
| |
| Affiliation: | LIU Jinqing1,FAN Qunzhen1,2,WU Qingxiang1(1School of Physics and Opto-Electronics Technology,Fujian Normal University,Provincial Key Laboratory of Photonics Technology,Fuzhou 350007,China,2Jinshan College of Fujian Agriculture and Forestry University,Fuzhou,350002,China) |
| |
| Abstract: | A novel method of Face Feature extraction is presented for the impact of the Face Recognition by Facial Expression changing,which combines Discrete Wavelet Transform(DWT)with newer Principal Components Analysis(PCA)and Linear Discriminant Analysis(LDA).A face image was first extracted into the low-frequency components image using two-dimensional Discrete Wavelet Transform(2DWT),then,with the PCA was used to map the low-frequency components image into a low-dimensional feature space,and finally,with the LDA ... |
| |
| Keywords: | feature extraction Face Expression recognition Discrete Wavelet Transform(DWT) Principal Components Analysis(PCA) Linear Discriminant Analysis(LDA) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
