Please use this identifier to cite or link to this item: https://hdl.handle.net/10316/27747
DC FieldValueLanguage
dc.contributor.authorMartins, P.-
dc.contributor.authorCarvalho, P.-
dc.contributor.authorGatta, C.-
dc.date.accessioned2014-12-02T14:17:00Z-
dc.date.available2014-12-02T14:17:00Z-
dc.date.issued2014-02-
dc.identifier.citationMARTINS, P.; CARVALHO, P.; GATTA, C. - Context-aware features and robust image representations. "Journal of Visual Communication and Image Representation". ISSN 1047-3203. Vol. 25 Nº. 2 (2014) p. 339-348por
dc.identifier.issn1047-3203-
dc.identifier.urihttps://hdl.handle.net/10316/27747-
dc.description.abstractLocal image features are often used to efficiently represent image content. The limited number of types of features that a local feature extractor responds to might be insufficient to provide a robust image representation. To overcome this limitation, we propose a context-aware feature extraction formulated under an information theoretic framework. The algorithm does not respond to a specific type of features; the idea is to retrieve complementary features which are relevant within the image context. We empirically validate the method by investigating the repeatability, the completeness, and the complementarity of context-aware features on standard benchmarks. In a comparison with strictly local features, we show that our context-aware features produce more robust image representations. Furthermore, we study the complementarity between strictly local features and context-aware ones to produce an even more robust representation.por
dc.language.isoengpor
dc.publisherElsevierpor
dc.rightsopenAccesspor
dc.subjectLocal featurespor
dc.subjectKeypoint extractionpor
dc.subjectImage content descriptorspor
dc.subjectImage representationpor
dc.subjectVisual saliencypor
dc.subjectInformation theorypor
dc.subjectKernel estimatorspor
dc.subjectComplementaritypor
dc.titleContext-aware features and robust image representationspor
dc.typearticlepor
degois.publication.firstPage339por
degois.publication.lastPage348por
degois.publication.issue2por
degois.publication.titleJournal of Visual Communication and Image Representationpor
dc.relation.publisherversionhttp://www.sciencedirect.com/science/article/pii/S1047320313001867por
dc.peerreviewedYespor
dc.identifier.doi10.1016/j.jvcir.2013.10.006-
degois.publication.volume25por
uc.controloAutoridadeSim-
item.openairetypearticle-
item.languageiso639-1en-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.grantfulltextopen-
item.fulltextCom Texto completo-
crisitem.author.researchunitCISUC - Centre for Informatics and Systems of the University of Coimbra-
crisitem.author.parentresearchunitFaculty of Sciences and Technology-
crisitem.author.orcid0000-0002-9847-0590-
Appears in Collections:I&D CISUC - Artigos em Revistas Internacionais
Files in This Item:
Show simple item record

SCOPUSTM   
Citations

5
checked on Mar 25, 2024

WEB OF SCIENCETM
Citations 10

4
checked on Mar 2, 2024

Page view(s) 5

1,099
checked on Mar 26, 2024

Download(s)

327
checked on Mar 26, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.