跳到主要导航 跳到搜索 跳到主要内容

Expression intensity recognition based on multilayer hybrid classifier

  • Xia Mao*
  • , Chongping Wang
  • , Yuli Xue
  • *此作品的通讯作者
  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In this paper, an automatic system for recognizing expression intensity is proposed. Modified Active Appearance Model (MAAM) is utilized to extract facial feature points (FFPs), and then, according to the FFPs' position, the sequence is preprocessed. Coarse-to-fine pyramid algorithm is employed to track FFPs for extracting 23 optical flow vectors, and eliminating the error caused by rigid movement of head. Expression intensity is recognized by multilayer hybrid classifier. Support Vector Machine (SVM) classifies the expression in the form of optical flow vectors, and KNN classifier recognizes the intensity. We conduct the experiments on Cohn-Kanade expression database and the result shows good effect.

源语言英语
主期刊名Intelligent Autonomous Systems 12 - Proceedings of the 12th International Conference, IAS 2012
出版商Springer Verlag
739-748
页数10
版本VOL. 2
ISBN(印刷版)9783642339318
DOI
出版状态已出版 - 2013
活动12th International Conference on Intelligent Autonomous Systems, IAS 2012 - Jeju Island, 韩国
期限: 26 6月 201229 6月 2012

出版系列

姓名Advances in Intelligent Systems and Computing
编号VOL. 2
194 AISC
ISSN(印刷版)2194-5357

会议

会议12th International Conference on Intelligent Autonomous Systems, IAS 2012
国家/地区韩国
Jeju Island
时期26/06/1229/06/12

指纹

探究 'Expression intensity recognition based on multilayer hybrid classifier' 的科研主题。它们共同构成独一无二的指纹。

引用此