Evaluation Framework of Superpixel Methods with a Global Regularity Measure

Abstract : In the superpixel literature, the comparison of state-of-the-art methods can be biased by the non-robustness of some metrics to decomposition aspects, such as the superpixel scale. Moreover, most recent decomposition methods allow to set a shape regularity parameter, which can have a substantial impact on the measured performances. In this paper, we introduce an evaluation framework, that aims to unify the comparison process of superpixel methods. We investigate the limitations of existing metrics, and propose to evaluate each of the three core decomposition aspects: color homogeneity, respect of image objects and shape regularity. To measure the regularity aspect, we propose a new global regularity measure (GR), which addresses the non-robustness of state-of-the-art metrics. We evaluate recent superpixel methods with these criteria, at several superpixel scales and regularity levels. The proposed framework reduces the bias in the comparison process of state-of-the-art superpixel methods. Finally, we demonstrate that the proposed GR measure is correlated with the performances of various applications.
Type de document :
Pré-publication, Document de travail
Journal of Electronic Imaging (JEI), Special issue on Superpixels for Image Processing and Comput.. 2017
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01519635
Contributeur : Rémi Giraud <>
Soumis le : vendredi 9 juin 2017 - 00:37:07
Dernière modification le : mardi 20 juin 2017 - 01:33:15

Fichier

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

Identifiants

  • HAL Id : hal-01519635, version 1

Collections

Citation

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. Evaluation Framework of Superpixel Methods with a Global Regularity Measure. Journal of Electronic Imaging (JEI), Special issue on Superpixels for Image Processing and Comput.. 2017. <hal-01519635>

Partager

Métriques

Consultations de
la notice

84

Téléchargements du document

18