Robust Shape Regularity Criteria for Superpixel Evaluation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Giraud, Rémi, Ta, Vinh-Thong, Papadakis, Nicolas
Format: Preprint
Publié: 2019
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909795335798784
author Giraud, Rémi
Ta, Vinh-Thong
Papadakis, Nicolas
author_facet Giraud, Rémi
Ta, Vinh-Thong
Papadakis, Nicolas
contents 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 superpixel 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.
format Preprint
id arxiv_https___arxiv_org_abs_1903_07146
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Robust Shape Regularity Criteria for Superpixel Evaluation
Giraud, Rémi
Ta, Vinh-Thong
Papadakis, Nicolas
Computer Vision and Pattern Recognition
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 superpixel 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.
title Robust Shape Regularity Criteria for Superpixel Evaluation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/1903.07146