计算机工程与应用 ›› 2014, Vol. 50 ›› Issue (17): 164-168.

• 图形图像处理 • 上一篇    下一篇

基于生物启发特征和SVM的人脸表情识别

穆国旺1,王  阳2,郭  蔚1   

  1. 1.河北工业大学 理学院,天津 300401
    2.中共唐山市路南区委 组织部,河北 唐山 063000
  • 出版日期:2014-09-01 发布日期:2014-09-12

Facial expression recognition using biologically inspired features and SVM

MU Guowang1, WANG Yang2, GUO Wei1   

  1. 1.School of Science, Hebei University of Technology, Tianjin 300401, China
    2.Department of Organization, Committee of Chinese Communist Party in Lunan District, Tangshan, Hebei 063000, China
  • Online:2014-09-01 Published:2014-09-12

摘要: 将C1特征应用于静态图像人脸表情识别,提出了一种新的基于生物启发特征和SVM的表情识别算法。提取人脸图像的C1特征,利用PCA+LDA方法对特征进行降维,用SVM进行分类。在JAFFE和Extended Cohn-Kanade(CK+)人脸表情数据库上的实验结果表明,该算法具有较高的识别率,是一种有效的人脸表情识别方法。

关键词: 人脸表情识别, 物启发特征(BIF), C1特征, 支持向量机

Abstract: C1 features are introduced to facial expression recognition for static images, and a new algorithm for facial expression recognition based on Biologically Inspired Features(BIFs) and SVM is proposed. C1 features of the facial images are extracted, PCA+LDA method is used to reduce the dimensionality of the C1 features, SVM is used for classification of the expression. The experiments on the JAFFE and Extended Cohn-Kanade (CK+) facial expression data sets show the effectiveness and the good performance of the algorithm.

Key words: facial expression recognition, Biologically Inspired Features(BIF), C1 features, Support Vector Machine(SVM)