CO-OCCURRENCES OF ADAPTED FEATURES FOR ...
Type de document :
Partie d'ouvrage
DOI :
Titre :
CO-OCCURRENCES OF ADAPTED FEATURES FOR OBJECT RECOGNITION ACROSS ILLUMINATION CHANGES
Auteur(s) :
Muselet, Damien [Auteur]
Macaire, Ludovic [Auteur]
LAGIS-SI
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Postaire, Jack-Gérard [Auteur]
Macaire, Ludovic [Auteur]
LAGIS-SI
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Postaire, Jack-Gérard [Auteur]
Éditeur(s) ou directeur(s) scientifique(s) :
Wojciechowski
K.and Smolka
B.and Palus
H.and Kozera
R.S.and Skarbek
W.and Noakes
L.
K.and Smolka
B.and Palus
H.and Kozera
R.S.and Skarbek
W.and Noakes
L.
Titre de l’ouvrage :
Computer Vision and Graphics: International Conference, ICCVG 2004, Warsaw, Poland, September 2004, Proceedings
Éditeur :
Springer Netherlands
Date de publication :
2006
ISBN :
978-1-4020-4179-2
Discipline(s) HAL :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Résumé en anglais : [en]
In this paper, we propose an original approach which allows to recognize objects in color images acquired under uncontrolled illumination conditions. For each pair of images to compare, the scheme consists in evaluating ...
Lire la suite >In this paper, we propose an original approach which allows to recognize objects in color images acquired under uncontrolled illumination conditions. For each pair of images to compare, the scheme consists in evaluating specific color features adapted to this pair. These adapted features are evaluated so that the distributions of adapted colors in the two images are similar only when they contain the same object. Then we propose to analyze the spatial co-occurrences between the adapted features to compute the image indices. Experimental tests on a public image database show the efficiency of this approach in the context of object recognition across illumination changes.Lire moins >
Lire la suite >In this paper, we propose an original approach which allows to recognize objects in color images acquired under uncontrolled illumination conditions. For each pair of images to compare, the scheme consists in evaluating specific color features adapted to this pair. These adapted features are evaluated so that the distributions of adapted colors in the two images are similar only when they contain the same object. Then we propose to analyze the spatial co-occurrences between the adapted features to compute the image indices. Experimental tests on a public image database show the efficiency of this approach in the context of object recognition across illumination changes.Lire moins >
Langue :
Anglais
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :