Waterpixels: Superpixels based on the watershed transformation - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Waterpixels: Superpixels based on the watershed transformation


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 .
Fichier principal
Vignette du fichier
2014.icip.machairas.al.waterpixels.pdf (2.33 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01139797 , version 1 (07-04-2015)



Vaïa Machairas, Etienne Decencière, Thomas Walter. Waterpixels: Superpixels based on the watershed transformation. IEEE International Conference On Image Processing, Oct 2014, Paris, France. ⟨10.1109/ICIP.2014.7025882⟩. ⟨hal-01139797⟩
388 Consultations
1842 Téléchargements



Gmail Facebook X LinkedIn More