Presentation 2004/3/11
Facial Expression Recognition Using Fisher Weight Maps
Yusuke SHINOHARA, Nobuyuki OTSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, much research has been done on face image analysis. There are two major approaches: local-feature-based and image-vector-based. We propose a hybrid of these two approaches. First, local features are computed at each pixel hi an image. Secondly, these features are integrated with a weight map to obtain a feature vector. The optimal weight map, called a Fisher weight map, is found by maximizing the Fisher discriminant criterion of feature vectors. Finally, the face image is classified based on the feature vector. Our experiments on facial expression recognition demonstrate the effectiveness of Fisher weight maps for objectively quantifying the importance of each facial area for classification of expressions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Facial Expression Recognition / Discriminant Criterion / Fisher Weight Maps / Higher-order Local Auto-Correlation Features
Paper # PRMU2003-269
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/3/11(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Facial Expression Recognition Using Fisher Weight Maps
Sub Title (in English)
Keyword(1) Facial Expression Recognition
Keyword(2) Discriminant Criterion
Keyword(3) Fisher Weight Maps
Keyword(4) Higher-order Local Auto-Correlation Features
1st Author's Name Yusuke SHINOHARA
1st Author's Affiliation Graduate School of Information Science and Technology, University of Tokyo()
2nd Author's Name Nobuyuki OTSU
2nd Author's Affiliation Graduate School of Information Science and Technology, University of Tokyo:National Institute of Advanced Industrial Science and Technology (AIST)
Date 2004/3/11
Paper # PRMU2003-269
Volume (vol) vol.103
Number (no) 737
Page pp.pp.-
#Pages 6
Date of Issue