Show simple item record

hal.structure.identifierShandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China
dc.contributor.authorChen, Da
hal.structure.identifierShandong First Medical University
dc.contributor.authorZhu, Jian
hal.structure.identifierThe Chinese University of Hong Kong
dc.contributor.authorZhang, Xinxin
hal.structure.identifierShandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China
dc.contributor.authorShu, Minglei
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorCohen, Laurent D.
HAL ID: 738939
dc.date.accessioned2021-11-04T10:46:56Z
dc.date.available2021-11-04T10:46:56Z
dc.date.issued2021
dc.identifier.issn1057-7149
dc.identifier.urihttps://basepub.dauphine.psl.eu/handle/123456789/22172
dc.language.isoenen
dc.subjectGeodesic pathen
dc.subjectEikonal equationen
dc.subjectasymmetric Finsler metricen
dc.subjectregion-based homogeneityen
dc.subjectinteractive image segmentationen
dc.subject.ddc515en
dc.titleGeodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancementen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenMinimal paths are considered as a powerful and efficient tool for boundary detection and image segmentation due to its global optimality and well-established numerical solutions such as fast marching algorithm. In this paper, we introduce a flexible interactive image segmentation model based on the minimal geodesic framework in conjunction with region-based homogeneity enhancement. A key ingredient in our model is the construction of Finsler geodesic metrics, which are capable of integrating anisotropic and asymmetric edge features, region-based homogeneity and/or curvature regularization. This is done by exploiting an implicit method to incorporate the region-based homogeneity information to the metrics used. Moreover, we also introduce a way to build objective simple closed contours, each of which is treated as the concatenation of two disjoint open paths. Experimental results prove that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.en
dc.relation.isversionofjnlnameIEEE Transactions on Image Processing
dc.relation.isversionofjnlvol30en
dc.relation.isversionofjnldate2021-05
dc.relation.isversionofjnlpages5138 - 5153en
dc.relation.isversionofdoi10.1109/TIP.2021.3078106en
dc.identifier.urlsitehttps://arxiv.org/pdf/2008.06909.pdfen
dc.relation.isversionofjnlpublisherIEEE - Institute of Electrical and Electronics Engineersen
dc.subject.ddclabelAnalyseen
dc.relation.forthcomingnonen
dc.description.ssrncandidatenon
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewedouien
dc.date.updated2021-11-04T10:37:25Z
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record