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
IEEE International Conference on Image Processing (ICIP). 2017
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01510062
Contributeur : Rémi Giraud <>
Soumis le : samedi 20 mai 2017 - 15:40:43
Dernière modification le : lundi 5 juin 2017 - 16:21:04

Fichier

Giraud_SRC_ICIP17.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité - Pas d'utilisation commerciale 4.0 International License

Identifiants

  • HAL Id : hal-01510062, version 2

Collections

Citation

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. Robust Shape Regularity Criteria for Superpixel Evaluation. IEEE International Conference on Image Processing (ICIP). 2017. <hal-01510062>

Partager

Métriques

Consultations de
la notice

81

Téléchargements du document

69