计算机应用 ›› 2011, Vol. 31 ›› Issue (06): 1605-1608.DOI: 10.3724/SP.J.1087.2011.01605

• 图形图像技术 • 上一篇    下一篇

融合独立分量分析与支持向量聚类的人脸表情识别方法

周书仁1,梁昔明2   

  1. 1. 长沙理工大学 计算机与通信工程学院,长沙 410114
    2. 中南大学 信息科学与工程学院, 长沙 410083
  • 收稿日期:2010-11-19 修回日期:2011-01-05 发布日期:2011-06-20 出版日期:2011-06-01
  • 通讯作者: 周书仁
  • 作者简介:周书仁(1975-),男,江西都昌人,讲师,博士,主要研究方向:人工智能、模式识别、情感计算;
    梁昔明(1967-),男,湖南汨罗人,教授,博士生导师,博士,主要研究方向:人工智能、模式识别、图像处理、智能设计。
  • 基金资助:
    国家自然科学基金资助项目;湖南省自然科学基金项目;湖南省科技计划项目

Facial expression recognition algorithm fused ICA and support vector clustering

ZHOU Shuren1,LIANG Ximing2   

  1. 1. School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha Hunan 410114, China
    2. School of Information Science and Engineering, Central South University, Changsha Hunan 410083, China
  • Received:2010-11-19 Revised:2011-01-05 Online:2011-06-20 Published:2011-06-01
  • Contact: ZHOU Shuren

摘要: 针对人脸表情特征提取及自动聚类问题,提出了融合独立分量分析(ICA)与支持向量聚类(SVC)的人脸表情识别方法。采用ICA方法进行人脸表情的特征提取,然后采用混合因子分析(MFA)的交互参数调整方法得到局部约束支持向量聚类(LCSVC)的半径,有效降低了表情类别聚类边缘的部分干扰,这比单独采用支持向量聚类(SVC)方法效果要好。测试样本时通过比较新旧半径的值进行判决,实验结果表明该方法是有效的。

关键词: 表情识别, 独立分量分析, 局部约束支持向量聚类, 混合因子分析

Abstract: A new method of facial expression recognition is proposed, which is based on Independent Component Analysis (ICA) and Support Vector Clustering (SVC), which aims at solving the problem of features extraction of facial expression and auto-clustering. First, the facial expression features were extracted by ICA, and then the radius of Locally Constrained Support Vector Clustering (LCSVC) could be acquired according to the adjustment of inter-parameter Mixture of Factor Analysis (MFA) method. This clustering method effectively restrained the disturber of the clustering boundary region and also was better than the one that only uses SVC. The test sample is classified by a comparison with the difference between new and old radius, and the experimental results show that the proposed method is effective and successful.

Key words: expression recognition, Independent Component Analysis (ICA), Locally Constrained Support Vector Clustering (LCSVC), Mixture of Factor Analysis (MFA)