English

应用科学学报 ›› 2002, Vol. 20 ›› Issue (4): 377-381.

• 论文 • 上一篇    下一篇

基于特征的弹性图匹配人脸识别算法

孙大瑞, 吴乐南   

  1. 东南大学无线电工程系, 江苏南京 210096
  • 收稿日期:2001-05-25 修回日期:2002-04-11 出版日期:2002-12-31 发布日期:2002-12-31
  • 作者简介:孙大瑞(1975-),男,河北景县人,博士生;吴乐南(1952-),安徽枞阳人,教授,博导.

Feature-Based Face Recognition by Elastic Graph Matching

SUN Da-rui, WU Le-nan   

  1. Department of Radio Engineering, Southeast University, Nanjing 210096, China
  • Received:2001-05-25 Revised:2002-04-11 Online:2002-12-31 Published:2002-12-31

PDF

116

被引次数

65

摘要： 提出一种基于特征的弹性图匹配人脸识别算法(FEGM).它包括两个步骤,首先利用Gabor进行人脸特征(如眼、鼻子、嘴等)的检测、定位,提取一组Gabor小波系数矢量;然后在代价函数的约束下,对各个特征都执行弹性图匹配,并使总体代价函数尽可能的小,从而得到联合识别结果.在Yale人脸库上的实验表明,识别率确实得到提高.

关键词: 弹性图匹配, 特征提取, Gabor变换, 人脸识别

Abstract: A feature-based elastic graph matching algorithm (FEGM) on the basis of the Lades' elastic graph matching face recognition algorithm is proposed in this paper. It includes two steps. First, the face feature such as eye, nose, mouth are localized by Gabor transforms, and a group of feature vectors composed by Gabor coefficients is extracted. Then the FEGM algorithm is performed to make the total cost function as small as possible, recognition result on Yale face database shows that recognition rate has been improved substantially.

Key words: face recognition, elastic graph matching, feature extraction, Gabor transform

中图分类号: