PHOTOGENIC FACIAL EXPRESSION DISCRIMINATION

Luana Bezerra Batista, Herman Martins Gomes, João Marques de Carvalho

2006

Abstract

Facial Expression Recognition Systems (FERS) are usually applied to human-machine interfaces, enabling services that require identification of the emotional state of the user. This paper presents a new approach to the facial expression recognition problem, by addressing the question of whether or not it is possible to classify previously labeled photogenic and non-photogenic face images, based on their appearance. A Multi-Layer Perceptron (MLP) is trained with PCA representations of the face images to learn the relationships between facial expressions and the concept of a good photography of the face of a person. In the experiments, the generalization performances using MLP and Support Vector Machines (SVM) were analyzed. The results have shown that Principal Component Analysis (PCA) combined with MLP represent a promising approach to the problem.

Paper Citation

in Harvard Style

Bezerra Batista L., Martins Gomes H. and Marques de Carvalho J. (2006). PHOTOGENIC FACIAL EXPRESSION DISCRIMINATION . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 972-8865-40-6, pages 166-171. DOI: 10.5220/0001370901660171

in Bibtex Style

@conference{visapp06,
author={Luana Bezerra Batista and Herman Martins Gomes and João Marques de Carvalho},
title={PHOTOGENIC FACIAL EXPRESSION DISCRIMINATION},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2006},
pages={166-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001370901660171},
isbn={972-8865-40-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - PHOTOGENIC FACIAL EXPRESSION DISCRIMINATION
SN - 972-8865-40-6
AU - Bezerra Batista L.
AU - Martins Gomes H.
AU - Marques de Carvalho J.
PY - 2006
SP - 166
EP - 171
DO - 10.5220/0001370901660171