计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (15): 182-184.

• 图形、图像、模式识别 • 上一篇    下一篇

基于支持向量机的人脸识别系统的研究

曾阳艳1,2,叶柏龙2   

  1. 1.湖南商学院,长沙 410205
    2.湖南大学 软件学院,长沙 410082
  • 收稿日期:2007-08-29 修回日期:2007-11-23 出版日期:2008-05-21 发布日期:2008-05-21
  • 通讯作者: 曾阳艳

Face recognition based on support vector machines

ZENG Yang-yan1,2,YE Bo-long2   

  1. 1.Hunan Business College,Changsha 410205,China
    2.School of Software,Hunan University,Changsha 410082,China
  • Received:2007-08-29 Revised:2007-11-23 Online:2008-05-21 Published:2008-05-21
  • Contact: ZENG Yang-yan

摘要: 首先利用PCA进行人脸图像特征提取,然后将此特征数据作为分类器的输入数据。采用的分类器是利用所谓“相似性”方法构造的多个二类SVM分类器,为了提高识别正确率,在多个SVM的输出之后又增加了一级神经网络训练器。以ORL人脸库做的实验中得到了很好的识别效果。

关键词: 人脸识别, PCA, SVM, 神经网络

Abstract: At first,this paper make use of PCA to extract the feature information of images,then make the feature data to be the input information of classifier.The classifier is used so called “similar to” to construct a number of SVM,in order to improve recognition accuracy rate,added a neural network training device.The recognition experiment result show a good performance in ORL face database.

Key words: face recogniton, PCA, SVM, neural network