Waterpixels: Superpixels based on the watershed transformation

Abstract : Many sophisticated segmentation algorithms rely on a first low-level segmentation step where an image is partitioned into homogeneous regions with enforced compactness and adherence to object boundaries. These regions are called " su-perpixels ". While the marker controlled watershed transformation should in principle be well suited for this type of application , it has never been seriously tested in this setup, and comparisons to other methods were not made with the best possible settings. Here, we provide a scheme for applying the watershed transform for superpixel generation, where we use a spatially regularized gradient to achieve a tunable trade-off between superpixel regularity and adherence to object boundaries. We quantitatively evaluate our method on the Berkeley segmenta-tion database and show that we achieve comparable results to a previously published state-of-the art algorithm, while avoiding some of the arbitrary postprocessing steps the latter requires .
Type de document :
Communication dans un congrès
IEEE International Conference On Image Processing, Oct 2014, Paris, France. 2014, <10.1109/ICIP.2014.7025882>
Liste complète des métadonnées


https://hal-mines-paristech.archives-ouvertes.fr/hal-01139797
Contributeur : Etienne Decencière <>
Soumis le : mardi 7 avril 2015 - 09:52:25
Dernière modification le : mardi 12 septembre 2017 - 11:40:58
Document(s) archivé(s) le : mardi 18 avril 2017 - 11:56:17

Fichier

2014.icip.machairas.al.waterpi...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Vaïa Machairas, Etienne Decencière, Thomas Walter. Waterpixels: Superpixels based on the watershed transformation. IEEE International Conference On Image Processing, Oct 2014, Paris, France. 2014, <10.1109/ICIP.2014.7025882>. <hal-01139797>

Partager

Métriques

Consultations de
la notice

327

Téléchargements du document

983