Graph-based Image Segmentation Using Weighted Color Patch

Abstract : Constructing a discriminative affinity graph plays an essential role in graph-based image segmentation, and feature directly influences the discriminative power of the affinity graph. In this paper, we propose a new method based on the weighted color patch to compute the weight of edges in an affinity graph. The proposed method intends to incorporate both color and neighborhood information by representing pixels with color patches. Furthermore, we assign both local and global weights adaptively for each pixel in a patch in order to alleviate the over-smooth effect of using patches. The normalized cut (NCut) algorithm is then applied on the resulting affinity graph to find partitions. We evaluate the proposed method on the Prague color texture image benchmark and the Berkeley image segmentation database. The extensive experiments show that our method is competitive compared to the other standard methods with multiple evaluation metrics.
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing (ICIP), Sep 2013, Melbourne, Australia. pp.4064-4068, 2013
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00833305
Contributeur : Simon Masnou <>
Soumis le : vendredi 26 juillet 2013 - 13:46:33
Dernière modification le : vendredi 10 novembre 2017 - 17:00:03
Document(s) archivé(s) le : dimanche 27 octobre 2013 - 02:00:14

Fichier

ICIP_weightedColorPatch-hal.pd...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00833305, version 1

Citation

Xiaofang Wang, Chao Zhu, Charles-Edmond Bichot, Simon Masnou. Graph-based Image Segmentation Using Weighted Color Patch. IEEE International Conference on Image Processing (ICIP), Sep 2013, Melbourne, Australia. pp.4064-4068, 2013. 〈hal-00833305〉

Partager

Métriques

Consultations de la notice

300

Téléchargements de fichiers

369