Learning Sparse Face Features : Application to Face Verification

Pierre Buyssens 1 Marinette Revenu 1
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : We present a low resolution face recognition technique based on a Convolutional Neural Network approach. The network is trained to reconstruct a reference per subject image. In classical feature-based approaches, a first stage of features extraction is followed by a classification to perform the recognition. In classical Convolutional Neural Network approaches, features extraction stages are stacked (interlaced with pooling layers) with classical neural layers on top to form the complete architecture of the network. This paper addresses two questions : 1. Does a pretraining of the filters in an unsupervised manner improve the recognition rate compared to the one with filters learned in a purely supervised scheme ? 2. Is there an advantage of pretraining more than one feature extraction stage ? We show particularly that a refinement of the filters during the supervised training improves the results.
Type de document :
Communication dans un congrès
ICPR, Aug 2010, Istanbul, Turkey. pp.670-673, 2010, 〈10.1109/ICPR.2010.169〉
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00805785
Contributeur : Image Greyc <>
Soumis le : mardi 9 avril 2013 - 12:22:01
Dernière modification le : mardi 5 juin 2018 - 10:14:42
Document(s) archivé(s) le : jeudi 11 juillet 2013 - 15:05:22

Fichier

Pierre_Buyssens_ICPR2010.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Citation

Pierre Buyssens, Marinette Revenu. Learning Sparse Face Features : Application to Face Verification. ICPR, Aug 2010, Istanbul, Turkey. pp.670-673, 2010, 〈10.1109/ICPR.2010.169〉. 〈hal-00805785〉

Partager

Métriques

Consultations de la notice

140

Téléchargements de fichiers

109