跳到主要导航 跳到搜索 跳到主要内容

Facial expression recognition based on 2D Gabor transforms and SVM

  • Liu Chunhui*
  • , Zhao Zheng
  • , Gao Feng
  • *此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In the facial expression recognition, a dimension disaster will arise when taking the coefficient of Gabor transforms as the expression eigenvectors. To avoid this issue we draw grids on facial region, making the mean coefficient value of Gabor transforms of each gird as the eigenvectors. Furthermore we classify the expression by constructing the multi-class C-SVC, improved the accuracy and speed of the algorithm by dropping the redundant features using sequential backward selection. The experimental result proves the superiority of the algorithm we proposed to other algorithms.

源语言英语
主期刊名Information Technology for Manufacturing Systems II
238-242
页数5
DOI
出版状态已出版 - 2011
已对外发布
活动2011 International Conference on Information Technology for Manufacturing Systems, ITMS 2011 - Shanghai, 中国
期限: 7 5月 20118 5月 2011

出版系列

姓名Applied Mechanics and Materials
58-60
ISSN(印刷版)1660-9336
ISSN(电子版)1662-7482

会议

会议2011 International Conference on Information Technology for Manufacturing Systems, ITMS 2011
国家/地区中国
Shanghai
时期7/05/118/05/11

指纹

探究 'Facial expression recognition based on 2D Gabor transforms and SVM' 的科研主题。它们共同构成独一无二的指纹。

引用此