Title :

CO-OCCURRENCES OF ADAPTED FEATURES FOR OBJECT RECOGNITION ACROSS ILLUMINATION CHANGES

Author(s) :

Muselet, Damien [Auteur]
Macaire, Ludovic [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
LAGIS-SI
Postaire, Jack-Gérard [Auteur]

Scientific editor(s) :

Wojciechowski
K.and Smolka
B.and Palus
H.and Kozera
R.S.and Skarbek
W.and Noakes
L.

Book title :

Computer Vision and Graphics: International Conference, ICCVG 2004, Warsaw, Poland, September 2004, Proceedings

Publisher :

Springer Netherlands

Publication date :

2006

ISBN :

978-1-4020-4179-2

HAL domain(s) :

Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]

English abstract : [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 ...
Show more >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.Show less >

Language :

Anglais

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL