中国邮电高校学报(英文)

• Others • 上一篇    下一篇

Facial expression feature extraction using hybrid PCA and LBP

罗元,吴彩明,张毅   

  1. 重庆邮电大学
  • 收稿日期:2012-07-24 修回日期:2012-12-09 出版日期:2013-04-30 发布日期:2013-04-26
  • 通讯作者: 吴彩明 E-mail:wucaiming485@163.com
  • 基金资助:

    This work was supported by the National Natural Science Foundation of China (51075420), International Science & Technology Cooperation Program of China (2010DFA12160) and Program for Science and Technology Research Project of Chongqing (CSTC, 2010AA2055).

Facial expression feature extraction using hybrid PCA and LBP

  • Received:2012-07-24 Revised:2012-12-09 Online:2013-04-30 Published:2013-04-26
  • Contact: Cai-Ming WU E-mail:wucaiming485@163.com
  • Supported by:

    This work was supported by the National Natural Science Foundation of China (51075420), International Science & Technology Cooperation Program of China (2010DFA12160) and Program for Science and Technology Research Project of Chongqing (CSTC, 2010AA2055).

摘要:

In order to recognize facial expression accurately, the paper proposed a hybrid method of principal component analysis (PCA) and local binary pattern (LBP). Firstly, the method of eight eyes segmentation was introduced to extract the effective area of facial expression image, which can reduce some useless information to subsequent feature extraction. Then PCA extracted the global grayscale feature of the whole facial expression image and reduced the data size at the same time. And LBP extracted local neighbor texture feature of the mouth area, which contributes most to facial expression recognition. Fusing the global and local feature will be more effective for facial expression recognition. Finally, support vector machine (SVM) used the fusion feature to complete facial expression recognition. Experiment results show that, the method proposed in this paper can classify different expressions more effectively and can get higher recognition rate than the traditional recognition methods.

关键词:

facial expression recognition, PCA, LBP, eight eyes segmentation, SVM

Abstract:

In order to recognize facial expression accurately, the paper proposed a hybrid method of principal component analysis (PCA) and local binary pattern (LBP). Firstly, the method of eight eyes segmentation was introduced to extract the effective area of facial expression image, which can reduce some useless information to subsequent feature extraction. Then PCA extracted the global grayscale feature of the whole facial expression image and reduced the data size at the same time. And LBP extracted local neighbor texture feature of the mouth area, which contributes most to facial expression recognition. Fusing the global and local feature will be more effective for facial expression recognition. Finally, support vector machine (SVM) used the fusion feature to complete facial expression recognition. Experiment results show that, the method proposed in this paper can classify different expressions more effectively and can get higher recognition rate than the traditional recognition methods.

Key words:

facial expression recognition, PCA, LBP, eight eyes segmentation, SVM