Matching Local Invariant Features: How Can Contextual Information Help? - Université Jean-Monnet-Saint-Étienne Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Matching Local Invariant Features: How Can Contextual Information Help?

Résumé

Local invariant features are a powerful tool for finding correspondences between images since they are robust to cluttered background, occlusion and viewpoint changes. However, they suffer the lack of global information and fail to resolve ambiguities that can occur when an image has multiple similar regions. Considering some global information will clearly help to achieve better performances. The question is which information to use and how to use it. While previous approaches use context for description, this paper shows that better results are obtained if contextual information is included in the matching process. We compare two different methods which use context for matching and experiments show that a relaxation based approach gives better results.
Fichier principal
Vignette du fichier
article_ec_sipmcs.pdf (558.16 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

ujm-00374347 , version 1 (08-04-2009)

Identifiants

Citer

Dro Desire Sidibe, Philippe Montesinos, Stefan Janaqi. Matching Local Invariant Features: How Can Contextual Information Help?. 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services., Jun 2007, Maribor, Slovenia. pp.503-506, ⟨10.1109/IWSSIP.2007.4381151⟩. ⟨ujm-00374347⟩
211 Consultations
196 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More