Curvature based corner detector for discrete, noisy and multi-scale contours

Bertrand Kerautret 1 Jacques-Olivier Lachaud 2 Benoît Naegel 3
1 ADAGIO - Applying Discrete Algorithms to Genomics and Imagery
LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
3 QGAR - Querying Graphics through Analysis and Recognition
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Estimating curvature on digital shapes is known to be a difficult problem even in high resolution images 10,19. Moreover the presence of noise contributes to the insta- bility of the estimators and limits their use in many computer vision applications like corner detection. Several recent curvature estimators 16,13,15, which come from the dis- crete geometry community, can now process damaged data and integrate the amount of noise in their analysis. In this paper, we propose a comparative evaluation of these estimators, testing their accuracy, efficiency, and robustness with respect to several type of degradations. We further compare the best one with the visual curvature proposed by Liu et al. 14, a recently published method from the computer vision community. We finally propose a novel corner detector, which is based on curvature estimation, and we provide a comprehensive set of experiments to compare it with many other classical cor- ner detectors. Our study shows that this corner detector has most of the time a better behavior than the others, while requiring only one parameter to take into account the noise level. It is also promising for multi-scale shape description.
Type de document :
Article dans une revue
International Journal of Shape Modeling, World Scientific Publishing, 2008, 14 (2), pp.127-145. 〈http://www.worldscinet.com/ijsm/14/1402/S0218654308001117.html〉. 〈10.1142/S0218654308001117〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00437575
Contributeur : Bertrand Kerautret <>
Soumis le : lundi 28 mars 2011 - 14:26:41
Dernière modification le : jeudi 11 janvier 2018 - 06:21:01
Document(s) archivé(s) le : mercredi 29 juin 2011 - 02:21:42

Fichier

Kerautret09b-1.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Bertrand Kerautret, Jacques-Olivier Lachaud, Benoît Naegel. Curvature based corner detector for discrete, noisy and multi-scale contours. International Journal of Shape Modeling, World Scientific Publishing, 2008, 14 (2), pp.127-145. 〈http://www.worldscinet.com/ijsm/14/1402/S0218654308001117.html〉. 〈10.1142/S0218654308001117〉. 〈inria-00437575〉

Partager

Métriques

Consultations de la notice

265

Téléchargements de fichiers

330