Recognition of six basic facial expressions by feature-points tracking using RBF neural network and fuzzy inference system

Author

Seyedarabi, Hadi ; Aghagolzadeh, Ali ; Khanmohammadi, Sohrab

Volume

2

fYear

2004

fDate

30-30 June 2004

Firstpage

1219

Abstract

Face expression recognition is useful for designing new interactive devices offering the possibility of new ways for human to interact with computer systems. In this paper, we develop a facial expression recognition system, based on the facial features extracted from facial characteristic points in frontal image sequences. Selected facial feature points were automatically tracked using a cross-correlation based optical flow, and extracted feature vectors were used to classify expressions, using RBF neural networks and a fuzzy inference system (FIS). Then, recognition results from two classifiers were compared with each other. Success rates were about 91.6% using RBF and 89.1% using FIS classifiers

Keywords

correlation methods; emotion recognition; feature extraction; fuzzy reasoning; image classification; image sequences; radial basis function networks; FIS classifier; RBF neural network; basic facial expression recognition; cross-correlation based optical flow; expression classification; facial characteristic points; facial feature extraction; feature vectors; feature-points tracking; frontal image sequences; fuzzy inference systems; interactive devices; Character recognition; Face recognition; Facial features; Fuzzy neural networks; Fuzzy systems; Humans; Image recognition; Image sequences; Neural networks; Optical computing;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on

Conference_Location

Taipei

Print_ISBN

0-7803-8603-5

Type

conf

DOI

10.1109/ICME.2004.1394441

Filename

1394441