An Optical Flow Feature-Based Robust Facial Expression Recognition with HMM from Video

Title
An Optical Flow Feature-Based Robust Facial Expression Recognition with HMM from Video
Authors
송병철
Keywords
Optical flows, Principal component analysis (PCA), Generalized discriminant analysis (GDA), Hidden Markov models (HMMs)
Issue Date
2013
Publisher
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL
Series/Report no.
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL ; Vol9 no.4 Startpage 1409 Endpage 1421
Abstract
In this work, a novel method is proposed to recognize several facial expressions from time-sequential facial expression images. To produce robust facial expression features, optical flow extraction is utilized which are further improved by Principal Component Analysis (PCA) and Generalized Discriminant Analysis (GDA). Using these features, discrete Hidden Markov Models (HMMs) are utilized to model different facial expressions. Performance of our proposed FER system is compared against the conventional approaches and the proposed approach significantly improves the performance yielding the mean recognition rate of 99.16% whereas the conventional methods yield 82.92% at best.
URI
http://dspace.inha.ac.kr/handle/10505/34303
ISSN
1349-4198
Appears in Collections:
College of Engineering(공과대학) > Electronic Engineering (전자공학) > Local Access Journals, Paper, Reports (전자공학 논문, 보고서)

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse