Presentation 2003/1/17
Development of Face Identification System using Synthesized Images of Face Expression
Takashi KUMAKURA, Minoru NAKAYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes face identification method using synthesized imges of face expression from neutral face images to improve the performance. Three expression features, smile, anger and scream, were extracted from actual expression face images by the eigen space method. Synthesized face images based on these features were added on loarning data for personal identification model with support vector machines (SVM). The performance of this model was significantly higer than model without expression face images, but significantly lower than model using actual expression images. The results suggested that identification performance also significantly depended on facial emotions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Personal Identification / expressive Face / eigenspace method / Support Vector Machine / grayscale image
Paper # HCS2002-34
Date of Issue

Conference Information
Committee HCS
Conference Date 2003/1/17(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 Human Communication Science (HCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development of Face Identification System using Synthesized Images of Face Expression
Sub Title (in English)
Keyword(1) Personal Identification
Keyword(2) expressive Face
Keyword(3) eigenspace method
Keyword(4) Support Vector Machine
Keyword(5) grayscale image
1st Author's Name Takashi KUMAKURA
1st Author's Affiliation Tokyo Institute of Technology Graduate School of Decision Science and Technology()
2nd Author's Name Minoru NAKAYAMA
2nd Author's Affiliation Tokyo Institute of Technology Graduate School of Decision Science and Technology
Date 2003/1/17
Paper # HCS2002-34
Volume (vol) vol.102
Number (no) 598
Page pp.pp.-
#Pages 6
Date of Issue