计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (5): 143-144.DOI: 10.3778/j.issn.1002-8331.2010.05.043

• 图形、图像、模式识别 • 上一篇    下一篇

基于矩阵模式的人脸表情识别

黄 勇   

  1. 柳州运输职业技术学院 电子工程系,广西 柳州 545007
  • 收稿日期:2008-08-22 修回日期:2008-11-10 出版日期:2010-02-11 发布日期:2010-02-11
  • 通讯作者: 黄 勇

Facial expression recognition based on matrix pattern

HUANG Yong   

  1. Department of Electronic Engineering,Liuzhou Transport Vocational Technical College,Liuzhou,Guangxi 545007,China
  • Received:2008-08-22 Revised:2008-11-10 Online:2010-02-11 Published:2010-02-11
  • Contact: HUANG Yong

摘要: 提出了一种基于矩阵模式的人脸表情识别方法。该算法直接将人脸表情图像矩阵作为矩阵模式,并结合传统PCA和FLDA进行表情特征提取,称之为MatPCA和MatFLDA。与2DPCA等不同,该算法既利用图像矩阵中的行向量间的信息,也充分利用列向量间的信息,尽可能地保留了原始的表情信息。基于JAFFE和CED-WYU(1.0)两个表情数据库的识别结果表明,基于矩阵模式的特征提取方法能有效地提高识别率并节省计算时间。

关键词: 矩阵主元分析, 矩阵线性判决分析, 表情识别

Abstract: A facial expression recognition method based on matrix pattern is proposed.This algorithm extracts expression feature for facial expression image by first matrixing it into a matrix pattern and then applying the matrixed versions of PCA and FLDA,named MatPCA and MatFLDA.Unlike 2DPCA,it takes full advantage of the information between rows and columns of the image matrix,and thus remains the original expression information as much as possible.Experimental result on JAFFE and CED-WYU(1.0) shows that it is an effective method for improving the recognition accuracy and saving much computational time.

Key words: Matrix PCA(MatPCA), Matrix FLDA(MatFLDA), expression recognition

中图分类号: