SCALP: Superpixels with Contour Adherence using Linear Path

Abstract : Superpixel decomposition methods are generally used as a pre-processing step to speed up image processing tasks. They group the pixels of an image into homogeneous regions while trying to respect existing contours. For all state-of-the-art superpixel decomposition methods, a trade-off is made between 1) computational time, 2) adherence to image contours and 3) regularity and compactness of the decomposition. In this paper, we propose a fast method to compute Superpixels with Contour Adherence using Linear Path (SCALP) in an iterative clustering framework. The distance computed when trying to associate a pixel to a superpixel during the clustering is enhanced by considering the linear path to the superpixel barycenter. The proposed framework produces regular and compact superpixels that adhere to the image contours. We provide a detailed evaluation of SCALP on the standard Berkeley Segmentation Dataset. The obtained results outperform state-of-the-art methods in terms of standard superpixel and contour detection metrics.
Type de document :
Communication dans un congrès
23rd International Conference on Pattern Recognition (ICPR 2016), Dec 2016, Cancun, Mexico. <http://www.icpr2016.org/site/>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01349569
Contributeur : Rémi Giraud <>
Soumis le : mardi 20 septembre 2016 - 22:52:16
Dernière modification le : jeudi 22 septembre 2016 - 01:04:26

Fichier

Giraud_ICPR_2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01349569, version 3

Collections

Citation

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. SCALP: Superpixels with Contour Adherence using Linear Path. 23rd International Conference on Pattern Recognition (ICPR 2016), Dec 2016, Cancun, Mexico. <http://www.icpr2016.org/site/>. <hal-01349569>

Partager

Métriques

Consultations de
la notice

262

Téléchargements du document

159