Presentation 2003/12/11
Facial expression analysis by Kernel Eigenspace Method based on Class features (KEMC) using non-linear basis for separation of expression-classes
Yohei KOSAKA, Kazunori KOTANI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the facial expression recognition by analyzing feature-vectors with linear transformation, the accuracy of recognition is depending on expression-classes. The accuracy falls sharply when the feature vector of the expression-class has a distribution with difficult linear separation in the feature-space. This paper describes a new method of facial expression analysis and recognition by using non-linear transformation for separating each expression-classes. Our new method, namely KEMC, consists of the non-linear transformation defined by kernel functions for transforming higher dimensional space and EMC (Eigenspace Method based on Class features). This paper also shows experimental results of facial expression classification bv KEMC.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # CS2003-127,IE2003-117
Date of Issue

Conference Information
Committee IE
Conference Date 2003/12/11(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 Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Facial expression analysis by Kernel Eigenspace Method based on Class features (KEMC) using non-linear basis for separation of expression-classes
Sub Title (in English)
Keyword(1)
1st Author's Name Yohei KOSAKA
1st Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology()
2nd Author's Name Kazunori KOTANI
2nd Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
Date 2003/12/11
Paper # CS2003-127,IE2003-117
Volume (vol) vol.103
Number (no) 513
Page pp.pp.-
#Pages 6
Date of Issue