ROBUST SHAPE REGULARITY CRITERIA FOR SUPERPIXEL EVALUATION

Abstract : Regular decompositions are necessary for most superpixel-based object recognition or tracking applications. So far in the literature, the regularity or compactness of a superpixel shape is mainly measured by its circularity. In this work, we first demonstrate that such measure is not adapted for super-pixel evaluation, since it does not directly express regularity but circular appearance. Then, we propose a new metric that considers several shape regularity aspects: convexity, balanced repartition, and contour smoothness. Finally, we demonstrate that our measure is robust to scale and noise and enables to more relevantly compare superpixel methods.
Type de document :
Pré-publication, Document de travail
2017
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01510062
Contributeur : Rémi Giraud <>
Soumis le : mardi 18 avril 2017 - 23:25:40
Dernière modification le : vendredi 21 avril 2017 - 01:05:17

Fichier

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

Identifiants

  • HAL Id : hal-01510062, version 1

Collections

Citation

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. ROBUST SHAPE REGULARITY CRITERIA FOR SUPERPIXEL EVALUATION. 2017. <hal-01510062>

Partager

Métriques

Consultations de
la notice

18

Téléchargements du document

13