CO-OCCURRENCES OF ADAPTED FEATURES FOR OBJECT RECOGNITION ACROSS ILLUMINATION CHANGES - Archive ouverte HAL
Chapitre D'ouvrage Année : 2006

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

Damien Muselet
Jack-Gérard Postaire
  • Fonction : Auteur

Résumé

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.
Fichier non déposé

Dates et versions

hal-01940042 , version 1 (29-11-2018)

Identifiants

Citer

Damien Muselet, Ludovic Macaire, Jack-Gérard Postaire. CO-OCCURRENCES OF ADAPTED FEATURES FOR OBJECT RECOGNITION ACROSS ILLUMINATION CHANGES. Wojciechowski, K.and Smolka, B.and Palus, H.and Kozera, R.S.and Skarbek, W.and Noakes, L. Computer Vision and Graphics: International Conference, ICCVG 2004, Warsaw, Poland, September 2004, Proceedings, Springer Netherlands, pp.7--12, 2006, 978-1-4020-4179-2. ⟨10.1007/1-4020-4179-9_2⟩. ⟨hal-01940042⟩
24 Consultations
0 Téléchargements

Altmetric

Partager

More