Presentation 2003/11/14
A Deformable Template Matching Based Face Recognition System using Prior Information on Facial Expressions
Atsushi MATSUI, Simon CLIPPINGDALE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We introduce two statistical models to handle deformation of input faces due to facial expression for the face recognition using deformable template matching. These models utilize a covariance matrix of feature point locations, and linear approximation of each correlation between variation of node locations and Gabor wavelet coefficients. We carried out an evaluation on a test set of 10 persons in 3 conditions; "neutral", "smiling", and "talking". The result shows that our new models successfully reduce ID-error-rate from 47.2% to 36.7% on the "smiling" data, and do from 24.2% to 15.6% on the "talking" data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face Recognition / Deformable Template Matching / Facial Expressions / Variance Covariance Matrix
Paper # PRMU2003-161,HIP2003-67
Date of Issue

Conference Information
Committee HIP
Conference Date 2003/11/14(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 Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Deformable Template Matching Based Face Recognition System using Prior Information on Facial Expressions
Sub Title (in English)
Keyword(1) Face Recognition
Keyword(2) Deformable Template Matching
Keyword(3) Facial Expressions
Keyword(4) Variance Covariance Matrix
1st Author's Name Atsushi MATSUI
1st Author's Affiliation Science & Technical Research Laboratories, Japan Broadcasting Corporation()
2nd Author's Name Simon CLIPPINGDALE
2nd Author's Affiliation Science & Technical Research Laboratories, Japan Broadcasting Corporation
Date 2003/11/14
Paper # PRMU2003-161,HIP2003-67
Volume (vol) vol.103
Number (no) 455
Page pp.pp.-
#Pages 5
Date of Issue