Exploring human visual system: study to aid the development of automatic facial expression recognition framework - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Exploring human visual system: study to aid the development of automatic facial expression recognition framework

(1) , (1) , (2) , (1)
1
2

Abstract

This paper focus on understanding human visual system when it decodes or recognizes facial expressions. Results presented can be exploited by the computer vision research community for the development of robust descriptor based on human visual system for facial expressions recognition. We have conducted psycho-visual experimental study to find which facial region is perceptually more attractive or salient for a particular expression. Eye movements of 15 observers were recorded with an eye-tracker in free viewing conditions as they watch a collection of 54 videos selected from Cohn-Kanade facial expression database, showing six universal facial expressions. The results of the study shows that for some facial expressions only one facial region is perceptually more attractive than others. Other cases shows the attractiveness of two to three facial regions. This paper also proposes a novel framework for automatic recognition of expressions which is based on psycho-visual study.
Fichier principal
Vignette du fichier
CVPR2012gesture_Khan.pdf (1.48 Mo) Télécharger le fichier
Vignette du fichier
Poster_WorkShop_CVPR_2012.pdf (1.31 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Other

Dates and versions

ujm-00714091 , version 1 (03-07-2012)

Identifiers

  • HAL Id : ujm-00714091 , version 1

Cite

Rizwan Ahmed Khan, Alexandre Meyer, Hubert Konik, Saïda Bouakaz. Exploring human visual system: study to aid the development of automatic facial expression recognition framework. Conference on Computer Vision and Pattern Recognition(CVPR), Workshop on Gesture Recognition, Jun 2012, Rhode Island, United States. pp.49-54. ⟨ujm-00714091⟩
239 View
392 Download

Share

Gmail Facebook Twitter LinkedIn More