Visual word spatial arrangement for image retrieval and classification

dc.creatorPenatti, OAB
dc.creatorSilva, FB
dc.creatorValle, E
dc.creatorGouet-Brunet, V
dc.creatorTorres, RD
dc.date2014
dc.dateFEB
dc.date2014-08-01T18:16:53Z
dc.date2015-11-26T17:54:16Z
dc.date2014-08-01T18:16:53Z
dc.date2015-11-26T17:54:16Z
dc.date.accessioned2018-03-29T00:37:53Z
dc.date.available2018-03-29T00:37:53Z
dc.identifierPattern Recognition. Elsevier Sci Ltd, v. 47, n. 2, n. 705, n. 720, 2014.
dc.identifier0031-3203
dc.identifier1873-5142
dc.identifierWOS:000329413000019
dc.identifier10.1016/j.patcog.2013.08.012
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/76577
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/76577
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1290745
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionWe present word spatial arrangement (WSA), an approach to represent the spatial arrangement of visual words under the bag-of-visual-words model. It lies in a simple idea which encodes the relative position of visual words by splitting the image space into quadrants using each detected point as origin. WSA generates compact feature vectors and is flexible for being used for image retrieval and classification, for working with hard or soft assignment, requiring no pre/post processing for spatial verification. Experiments in the retrieval scenario show the superiority of WSA in relation to Spatial Pyramids. Experiments in the classification scenario show a reasonable compromise between those methods, with Spatial Pyramids generating larger feature vectors, while WSA provides adequate performance with much more compact features. As WSA encodes only the spatial information of visual words and not their frequency of occurrence, the results indicate the importance of such information for visual categorization. (C) 2013 Elsevier Ltd. All rights reserved.
dc.description47
dc.description2
dc.description705
dc.description720
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionSamsung
dc.descriptionMicrosoft Research
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionFAPESP [2009/10554-8, 2009/05951-8, 2012/16172-2]
dc.descriptionCNPq [484254/2012-0, 306580/2012-8]
dc.languageen
dc.publisherElsevier Sci Ltd
dc.publisherOxford
dc.publisherInglaterra
dc.relationPattern Recognition
dc.relationPattern Recognit.
dc.rightsfechado
dc.rightshttp://www.elsevier.com/about/open-access/open-access-policies/article-posting-policy
dc.sourceWeb of Science
dc.subjectVisual words
dc.subjectSpatial arrangement
dc.subjectImage retrieval
dc.subjectImage classification
dc.subjectObject Recognition
dc.titleVisual word spatial arrangement for image retrieval and classification
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución