Robust Shape Regularity Criteria for Superpixel Evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Robust Shape Regularity Criteria for Superpixel Evaluation

Résumé

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.
Fichier principal
Vignette du fichier
Giraud_SRC_ICIP17.pdf (2.47 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Domaine public
Loading...

Dates et versions

hal-01510062 , version 2 (20-05-2017)

Licence

Domaine public

Identifiants

  • HAL Id : hal-01510062 , version 2

Citer

Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. Robust Shape Regularity Criteria for Superpixel Evaluation. IEEE International Conference on Image Processing (ICIP'17), Sep 2017, Beijing, China. pp.3455-3459. ⟨hal-01510062⟩

Collections

CNRS IMB INSMI ANR
445 Consultations
363 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More