Presentation 1997/1/24
Recognition of facial expressions using 2-D DCT and neural network
N.P. Chandrasiri, Yegui XIAO, Yoshiaki TADOKORO, Masaomi ODA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A considerable number of studies have been made on facial expression (FE) recognition techniques that are oriented to applications in pshycological and engineering fields. However, almost all of them are based on the extraction of movements of facial muscles in some local areas, which proves to be a difficult and costly task to perform in practise. In this paper, a new technique is proposed which is based on the use of the discrete cosine transform (DCT) of the whole facial image and a feedforward neural network. This technique is applied to a database consisting of samples of 60 persons, each having 5 normalized FE images. 40 person's FE images are used for training the network and 20 person's FE images are used for testing its generalization performance. As a result, the network gave 100% recognition rate for trained samples and maximum recognition rate of 95% for testing samples.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Human interface / Facial expressions recognition / Discrete cosine transform / Neural network
Paper # PRMU96-153
Date of Issue

Conference Information
Committee PRMU
Conference Date 1997/1/24(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) Recognition of facial expressions using 2-D DCT and neural network
Sub Title (in English)
Keyword(1) Human interface
Keyword(2) Facial expressions recognition
Keyword(3) Discrete cosine transform
Keyword(4) Neural network
1st Author's Name N.P. Chandrasiri
1st Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology()
2nd Author's Name Yegui XIAO
2nd Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology
3rd Author's Name Yoshiaki TADOKORO
3rd Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology
4th Author's Name Masaomi ODA
4th Author's Affiliation ATR Human Information Processing Research Laboratories
Date 1997/1/24
Paper # PRMU96-153
Volume (vol) vol.96
Number (no) 492
Page pp.pp.-
#Pages 7
Date of Issue