Titre
Multiple Local Curvature Gabor Binary Patterns for Facial Action Recognition
Type
article de conférence/colloque
Institution
Externe
Série
Lecture Notes in Computer Science
Auteur(s)
Yüe, A.
Auteure/Auteur
Nuri, M.
Auteure/Auteur
Thiran, J.P.
Auteure/Auteur
Liens vers les personnes
Titre du livre ou conférence/colloque
HBU 2013, International Workshop on Human Behavior Understanding, in conjunction with ACM Multimedia
Statut éditorial
Publié
Date de publication
2013
Volume
8212
Première page
136
Dernière page/numéro d’article
147
Langue
anglais
Résumé
Curvature Gabor features have recently been shown to be
powerful facial texture descriptors with applications on
face recognition. In this paper we introduce their use in
facial action unit (AU) detection within a novel
framework that combines multiple Local Curvature Gabor
Binary Patterns (LCGBP) on different filter sizes and
curvature degrees. The proposed system uses the distances
of LCGBP histograms between neutral faces and AU
containing faces combined with an AU-specific feature
selection and classification process. We achieve 98.6%
overall accuracy in our tests with the extended
Cohn-Kanade database, which is higher than achieved
previously by any state-of-the-artmethod.
powerful facial texture descriptors with applications on
face recognition. In this paper we introduce their use in
facial action unit (AU) detection within a novel
framework that combines multiple Local Curvature Gabor
Binary Patterns (LCGBP) on different filter sizes and
curvature degrees. The proposed system uses the distances
of LCGBP histograms between neutral faces and AU
containing faces combined with an AU-specific feature
selection and classification process. We achieve 98.6%
overall accuracy in our tests with the extended
Cohn-Kanade database, which is higher than achieved
previously by any state-of-the-artmethod.
PID Serval
serval:BIB_617B1CD800CB
Date de création
2014-01-06T19:46:02.753Z
Date de création dans IRIS
2025-05-20T15:18:10Z
Fichier(s)![Vignette d'image]()
En cours de chargement...
Nom
BIB_617B1CD800CB.P001.pdf
Version du manuscrit
preprint
Taille
512.02 KB
Format
Adobe PDF
PID Serval
serval:BIB_617B1CD800CB.P001
Somme de contrôle
(MD5):33e8c5e8671d9b52d82adce792e9eb66