Show simple item record

dc.contributor.authorPont Tuset, Jordi
dc.contributor.authorMarqués Acosta, Fernando
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2014-04-02T13:19:45Z
dc.date.available2014-04-02T13:19:45Z
dc.date.created2013
dc.date.issued2013
dc.identifier.citationPont, J.; Marques, F. Measures and meta-measures for the supervised evaluation of image segmentation. A: IEEE Conference on Computer Vision and Pattern Recognition. "CVRP 2013: 2013 IEEE Conference on Computer Vision and Pattern Recognition: proceedings: 23-28 June 2013: Portland, Oregon, USA". Portland, Oregon: IEEE Computer Society Publications, 2013, p. 2131-2138.
dc.identifier.isbn978-0-7695-4989-7
dc.identifier.urihttp://hdl.handle.net/2117/22498
dc.description.abstractThis paper tackles the supervised evaluation of image segmentation algorithms. First, it surveys and structures the measures used to compare the segmentation results with a ground truth database, and proposes a new measure: the precision-recall for objects and parts. To compare the goodness of these measures, it defines three quantitative meta-measures involving six state of the art segmentation methods. The meta-measures consist in assuming some plausible hypotheses about the results and assessing how well each measure reflects these hypotheses. As a conclusion, this paper proposes the precision-recall curves for boundaries and for objects-and-parts as the tool of choice for the supervised evaluation of image segmentation. We make the datasets and code of all the measures publicly available.
dc.format.extent8 p.
dc.language.isoeng
dc.publisherIEEE Computer Society Publications
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subject.lcshImage segmentation
dc.subject.lcshImage processing -- Digital techniques
dc.subject.otherBenchmark testing
dc.subject.otherContext
dc.subject.otherCurrent measurement
dc.subject.otherDatabases
dc.subject.otherImage segmentation
dc.subject.otherObject detection
dc.subject.otherPartitioning algorithms
dc.titleMeasures and meta-measures for the supervised evaluation of image segmentation
dc.typeConference report
dc.subject.lemacImatges -- Processament -- Tècniques digitals
dc.subject.lemacVídeo digital
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi10.1109/CVPR.2013.277
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6619121&tag=1
dc.rights.accessOpen Access
local.identifier.drac12911669
dc.description.versionPostprint (published version)
local.citation.authorPont, J.; Marques, F.
local.citation.contributorIEEE Conference on Computer Vision and Pattern Recognition
local.citation.pubplacePortland, Oregon
local.citation.publicationNameCVRP 2013: 2013 IEEE Conference on Computer Vision and Pattern Recognition: proceedings: 23-28 June 2013: Portland, Oregon, USA
local.citation.startingPage2131
local.citation.endingPage2138


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder