计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (28): 10-11.

• 博士论坛 • 上一篇    下一篇

基于傅里叶变换特征遗传算法的人脸识别

陈绵书,陈贺新,孙中华   

  1. 吉林大学 南岭校区通信学院,长春 130025
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-10-01 发布日期:2007-10-01
  • 通讯作者: 陈绵书

Face recognition based on Fourier features selected by GA algorithm

CHEN Mian-shu,CHEN He-xin,SUN Zhong-hua   

  1. Department of Communication,Nanling Distract,JLU,Changchun 130025,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-10-01 Published:2007-10-01
  • Contact: CHEN Mian-shu

摘要: 提出了一种基于傅里叶变换特征遗传算法的人脸识别方法。首先对人脸图像进行傅里叶变换,并去掉不包含识别信息的零频率分量。然后以人脸图像傅里叶变换的模作为描述人脸模式的特征,考虑到并不是所有傅里叶特征都包含较好的分类信息,应用遗传算法进行特征选取。实验结果表明:给出的方法不仅具有较好的识别性能,而且可以在一定程度上减少人脸模式的存储空间。

关键词: 人脸识别, 傅里叶变换, 遗传算法

Abstract: In this paper,we propose a new face recognition method based on Fourier features selected by GA algorithm.First,we derive the Fourier transform of a face image,and set the value at frequency(0,0) to zero.Then we take the modules of the Fourier transform to represent a face image.Considering that not all the Fourier features contain better classifying information,we employ GA algorithm to select the features appropriate for classification.The experiment results show that the method in this paper is promising and the storage of face pattern is less.

Key words: face recognition, Fourier transform, GA algorithm