Presentation 2013-03-14
Study of Robust Facial Feature Localization by Modified Active Shape Model
Yan Li, Dan Luo, Ohya Jun,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a modified Active Shape Model (ASM), which is featured by the following two modules: (1)A flexible method that automatically generates training set and does not require time-consuming manual operations, which are required by the conventional ASM; (2)Two-step fitting that consists of the initial global (rough)fitting for the entire face and the subsequent local (precise)fitting for each facial component, where both fittings are based on ASM. Experiments demonstrate that more accurate location results were obtained by the proposed method than the conventional ASM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Feature extraction / Active Shape Model / Training set / Shape Fitting / Face / Facial component / Localization
Paper # PRMU2012-202
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/3/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study of Robust Facial Feature Localization by Modified Active Shape Model
Sub Title (in English)
Keyword(1) Feature extraction
Keyword(2) Active Shape Model
Keyword(3) Training set
Keyword(4) Shape Fitting
Keyword(5) Face
Keyword(6) Facial component
Keyword(7) Localization
1st Author's Name Yan Li
1st Author's Affiliation Graduated School of Global Information and Telecommunication Studies, Waseda University()
2nd Author's Name Dan Luo
2nd Author's Affiliation Graduated School of Global Information and Telecommunication Studies, Waseda University
3rd Author's Name Ohya Jun
3rd Author's Affiliation Graduated School of Global Information and Telecommunication Studies, Waseda University
Date 2013-03-14
Paper # PRMU2012-202
Volume (vol) vol.112
Number (no) 495
Page pp.pp.-
#Pages 6
Date of Issue