A graph-cut approach to image segmentation using an affinity graph based on l0−sparse representation of features

Abstract : We propose a graph-cut based image segmentation method by constructing an affinity graph using l0 sparse representation. Computing first oversegmented images, we associate with all segments, that we call superpixels, a collection of features. We find the sparse representation of each set of features over the dictionary of all features by solving a l0-minimization problem. Then, the connection information between superpixels is encoded as the non-zero representation coefficients, and the affinity of connected superpixels is derived by the corresponding representation error. This provides a l0 affinity graph that has interesting properties of long range and sparsity, and a suitable graph cut yields a segmentation. Experimental results on the BSD database demonstrate that our method provides perfectly semantic regions even with a constant segmentation number, but also that very competitive quantitative results are achieved.
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. pp.4019-4023, 2013
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00833278
Contributeur : Simon Masnou <>
Soumis le : vendredi 26 juillet 2013 - 13:43:37
Dernière modification le : vendredi 21 octobre 2016 - 09:26:40
Document(s) archivé(s) le : dimanche 27 octobre 2013 - 02:55:10

Fichier

SR-hal.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00833278, version 1

Citation

Xiaofang Wang, Huibin Li, Charles-Edmond Bichot, Simon Masnou, Liming Chen. A graph-cut approach to image segmentation using an affinity graph based on l0−sparse representation of features. IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. pp.4019-4023, 2013. <hal-00833278>

Partager

Métriques

Consultations de
la notice

411

Téléchargements du document

983