Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (26): 182-183.DOI: 10.3778/j.issn.1002-8331.2010.26.056

• 图形、图像、模式识别 • Previous Articles     Next Articles

Non-negative matrix factorization and its applications in facial expression recognition

HUANG Yong   

  1. Department of Electronic Engineering,Liuzhou Railway Vocational Technical College,Liuzhou,Guangxi 545007,China
  • Received:2009-02-24 Revised:2009-04-21 Online:2010-09-11 Published:2010-09-11
  • Contact: HUANG Yong


黄 勇   

  1. 柳州铁道职业技术学院 电子工程系,广西 柳州 545007
  • 通讯作者: 黄 勇

Abstract: A facial expression recognition method based on 2-Dimensional Non-negative Matrix Factorization(2DNMF) is proposed in this paper.2DNMF,which regards the 2D original expression images as 2D matrices and represents them with a set of 2D bases via appling NMF.Unlike NMF,2DNMF takes full advantage of the information between rows and columns of the image,thus remains the original expression information as much as possible.Experimental result on CED-WYU(1.0)and JAFFE shows that it is an effective method for improving the recognition accuracy and effectiveness.

Key words: Non-negative Matrix Factorization(NMF), 2-Dimensional Non-negative Matrix Factorization(2DNMF), expression recognition

摘要: 提出了一种基于二维非负矩阵因子的人脸表情识别方法。该算法直接将2维人脸表情图像矩阵作为2维矩阵并结合NMF进行表情特征提取,称之为2DNMF。与NMF等不同,2DNMF充分利用表情图像矩阵中的行向量间的信息和列向量间的信息,尽可能地保留了原始的表情信息。基于CED-WYU(1.0)和JAFFE两个表情数据库的识别结果表明,基于2维非负矩阵因子的特征提取方法能有效地提高识别率及效率。

关键词: 非负矩阵因子, 2维非负矩阵因子, 表情识别

CLC Number: