计算机工程 ›› 2010, Vol. 36 ›› Issue (06): 206-209.doi: 10.3969/j.issn.1000-3428.2010.06.070

• 人工智能及识别技术 • 上一篇    下一篇

基于改进联合模型的人脸表情识别

赵 浩,吴小俊   

  1. (江南大学信息工程学院,无锡 214122)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2010-03-20 发布日期:2010-03-20

Facial Expression Recognition Based on Improved United Model

ZHAO Hao, WU Xiao-jun

  

  1. (School of Information Engineering, Jiangnan University, Wuxi 214122)
  • Received:1900-01-01 Revised:1900-01-01 Online:2010-03-20 Published:2010-03-20

摘要: 在联合主动表观模型和主动形状模型的基础上,充分挖掘标定点之间的联系,提出一种局部纹理模型构建方法。通过改进匹配算法提高特征点的定位精度和匹配速度。将该算法提取到的人脸表情特征输入最近邻分类器,分类结果表明其识别率较高。

关键词: 主动表观模型, 联合模型, 最近邻分类器, 识别率

Abstract: On the basis of the idea of unifying Active Appearance Model(AAM) and Active Shape Model(ASM), this paper mines the relation of peg points fully and proposes a method to construct local vein model. It modifies the matching algorithm to improve location precision and matching speed of feature point. Facial expression feature obtained by this algorithm is input to the nearest neighbor classifier. Classification results indicate the high recognition rate of the algorithm.

Key words: Active Appearance Model(AAM), united model, nearest neighbor classifier, recognition rate

中图分类号: