计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (36): 13-15.

• 博士论坛 • 上一篇    下一篇

基于Gabor变换和双方向PCA的人脸识别

聂祥飞1,2,谭泽富1,郭 军2   

  1. 1.重庆三峡学院 物理与电子工程学院,重庆 404000
    2.北京邮电大学 信息工程学院,北京 100876
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-12-21 发布日期:2007-12-21
  • 通讯作者: 聂祥飞

Face recognition based on Gabor transform and bidirectional PCA

NIE Xiang-fei1,2,TAN Ze-fu1,GUO Jun2   

  1. 1.School of Physics and Electronic Engineering,Chongqing Three Gorges University,Chongqing 404000,China
    2.School of Information Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-21 Published:2007-12-21
  • Contact: NIE Xiang-fei

摘要: 提出了一种可以解决小样本问题的人脸识别新算法。算法首先把人脸图像经过Gabor小波变换后得到的每个输出图像都看成是独立的样本,从而大大增加了每一类人脸样本的样本数。然后采用双方向PCA算法来提取人脸特征,并专门设计了针对人脸特征矩阵的最近邻分类器和最小距离分类器来进行分类判决。在ORL人脸库和FERET人脸库中的实验结果表明,算法能有效地解决人脸识别中的小样本问题,甚至当每类训练样本数仅为1时,也能得到较高的识别率。

关键词: 人脸识别, 小样本问题, 双方向PCA, Gabor变换

Abstract: A novel face recognition algorithm which can solve the Small Sample Size(SSS) problem is presented.Firstly,the sample size of each subject is increased greatly by regarding every output image after taking Gabor wavelet transform as an independent sample.Secondly,bidirectional PCA method is adopted for face feature extraction.Special nearest neighbor classifier and minimum distance classifier based on face feature matrix are designed for classification,respectively.The experimental results on ORL face database and FERET face database show that the proposed method can alleviate the SSS problem effectively,and can get a good performance even when the training sample size of each subject is only 1.

Key words: face recognition, Small Sample Size(SSS) problem, bidirectional PCA, Gabor transform