华南理工大学学报(自然科学版) ›› 2004, Vol. 32 ›› Issue (8): 5-8,17.

• • 上一篇    下一篇

人脸识别中一种新的Gabor 特征提取方法

万峰 杜明辉   

  1. 华南理工大学 电子与信息学院‚广东 广州510640
  • 收稿日期:2004-02-13 出版日期:2004-08-20 发布日期:2015-09-09
  • 通信作者: 万峰(1976-)‚男‚博士‚主要从事数字图像处理的研究. E-mail:f.wan@263.net
  • 作者简介:万峰(1976-)‚男‚博士‚主要从事数字图像处理的研究.

A New Gabor Feature Extraction Method for Face Recognition

Wan Feng  Du Ming-hui   

  1. College of Electronic&Information Engineering‚South China Univ.of Tech.‚Guangzhou510640‚Guangdong‚China
  • Received:2004-02-13 Online:2004-08-20 Published:2015-09-09
  • Contact: 万峰(1976-)‚男‚博士‚主要从事数字图像处理的研究. E-mail:f.wan@263.net
  • About author:万峰(1976-)‚男‚博士‚主要从事数字图像处理的研究.

摘要: 为了有效利用 Gabor 特征进行人脸识别‚提出一种新的 Gabor 特征提取方法.首先利用类别可分离性判据评价 Gabor 展开系数的分类能力‚选择最有利于识别的 Gabor展开系数构造新的 Gabor 特征.然后对人脸不同局部位置处采样点的分类能力进行评价‚选择分类能力最强的位置提取特征点.最后就新的 Gabor 特征对光照和表情变化的适应性进行测试.实验结果表明‚新的特征提取方法能够在小样本条件下有效提高识别率‚减少特征数量‚并对环境变化具有一定的适应能力.

关键词: 人脸识别, Gabor 特征, 特征提取

Abstract:  To utilize the Gabor feature for efficient face recognition‚a new Gabor feature extraction method was pro-posed.Firstly‚a criterion with discriminating power was used to evaluate the classification ability of the Gabor coeffi -cients‚and the Gabor coefficients most favorable to the recognition were selected to construct new Gabor features.Then‚the classification abilities of different local positions in the face were evaluated‚and feature points were chosenat the positions with the strongest discriminating power.Finally‚the adaptability of the new Gabor feature to illumina-tion and expression was tested.Experiment results show that‚with small samples‚the new feature extraction method can effectively increase the recognition rate‚reduce the number of features‚and is of certain adaptability to the envi -ronments.

Key words: face recognition, Gabor feature, feature extraction

中图分类号: