Computer Vision; Deep Learning; Facial expression recognition; GPU acceleration
Résumé :
[en] Inspired by recent successes of deep learning in computer vision, we propose a novel application of deep convolutional neural networks to facial expression recognition, in particular smile recognition. A smile recognition test accuracy of 99.45% is achieved for the Denver Intensity of Spontaneous Facial Action (DISFA) database, significantly outperforming existing approaches based on hand-crafted features with accuracies ranging from 65.55% to 79.67%. The novelty of this approach includes a comprehensive model selection of the architecture parameters, allowing to find an appropriate architecture for each expression such as smile. This is feasible because all experiments were run on a Tesla K40c GPU, allowing a speedup of factor 10 over traditional computations on a CPU.
Disciplines :
Sciences informatiques
Auteur, co-auteur :
GLAUNER, Patrick ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Deep Learning For Smile Recognition
Date de publication/diffusion :
2016
Nom de la manifestation :
12th Conference on Uncertainty Modelling in Knowledge Engineering and Decision Making (FLINS 2016)
Lieu de la manifestation :
Roubaix, France
Date de la manifestation :
from 24-08-2016 to 26-08-2016
Manifestation à portée :
International
Titre de l'ouvrage principal :
Proceedings of the 12th International FLINS Conference (FLINS 2016)
