跳到主要导航 跳到搜索 跳到主要内容

A hybrid algorithm of facial feature point location based on improved MR-ASM and AAM

  • Zhang Sicong*
  • , Wu Lifang
  • , He Xiaoguang
  • , Tian Jie
  • *此作品的通讯作者
  • Beijing University of Technology
  • Chinese Academy of Sciences

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Accurate and robust location of feature point is a difficult and complicated issue in face recognition. This paper proposes a facial feature point location algorithm based on improved Multi-Resolution- Active Shape Models (MR-ASM) and Active Appearance Models (AAM). There are three main achievements of our algorithm: 1, we unify MR-ASM and AAM together to improve facial feature point location. 2, AAM is improved so that it has the same implementation framework as ASM. 3, the MR-ASM is adjusted to figure out more robust parameters. Experimental results prove that our algorithm is more accurate than traditional MR-ASM.

源语言英语
主期刊名8th International Conference on Signal Processing, ICSP 2006
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(印刷版)0780397371, 9780780397378
DOI
出版状态已出版 - 2006
已对外发布
活动8th International Conference on Signal Processing, ICSP 2006 - Guilin, 中国
期限: 16 11月 200620 11月 2006

出版系列

姓名International Conference on Signal Processing Proceedings, ICSP
3

会议

会议8th International Conference on Signal Processing, ICSP 2006
国家/地区中国
Guilin
时期16/11/0620/11/06

指纹

探究 'A hybrid algorithm of facial feature point location based on improved MR-ASM and AAM' 的科研主题。它们共同构成独一无二的指纹。

引用此