Afficher la notice abrégée

Evaluation Framework of Superpixel Methods with a Global Regularity Measure

hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorGIRAUD, Rémi
hal.structure.identifierInstitut Polytechnique de Bordeaux [Bordeaux INP]
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorTA, Vinh-Thong
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPAPADAKIS, Nicolas
dc.date.accessioned2024-04-04T03:10:00Z
dc.date.available2024-04-04T03:10:00Z
dc.date.issued2017-07-06
dc.identifier.issn1017-9909
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/193656
dc.description.abstractEnIn 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.
dc.description.sponsorshipGeneralized Optimal Transport Models for Image processing - ANR-16-CE33-0010
dc.language.isoen
dc.publisherSPIE and IS&T
dc.title.enEvaluation Framework of Superpixel Methods with a Global Regularity Measure
dc.typeArticle de revue
dc.subject.halInformatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
dc.subject.halInformatique [cs]/Traitement des images
bordeaux.journalJournal of Electronic Imaging
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.peerReviewedoui
hal.identifierhal-01519635
hal.version1
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-01519635v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Journal%20of%20Electronic%20Imaging&rft.date=2017-07-06&rft.eissn=1017-9909&rft.issn=1017-9909&rft.au=GIRAUD,%20R%C3%A9mi&TA,%20Vinh-Thong&PAPADAKIS,%20Nicolas&rft.genre=article


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée