dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorMansano, A.
dc.creatorMatsuoka, J. A.
dc.creatorAfonso, L. C S
dc.creatorPapa, João Paulo
dc.creatorFaria, F.
dc.creatorDa, R.
dc.date2014-05-27T11:27:18Z
dc.date2016-10-25T18:40:04Z
dc.date2014-05-27T11:27:18Z
dc.date2016-10-25T18:40:04Z
dc.date2012-12-01
dc.date.accessioned2017-04-06T02:04:11Z
dc.date.available2017-04-06T02:04:11Z
dc.identifierBrazilian Symposium of Computer Graphic and Image Processing, p. 324-329.
dc.identifier1530-1834
dc.identifierhttp://hdl.handle.net/11449/73833
dc.identifierhttp://acervodigital.unesp.br/handle/11449/73833
dc.identifier10.1109/SIBGRAPI.2012.52
dc.identifier2-s2.0-84872385646
dc.identifierhttp://dx.doi.org/10.1109/SIBGRAPI.2012.52
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/894617
dc.descriptionThe efficiency in image classification tasks can be improved using combined information provided by several sources, such as shape, color, and texture visual properties. Although many works proposed to combine different feature vectors, we model the descriptor combination as an optimization problem to be addressed by evolutionary-based techniques, which compute distances between samples that maximize their separability in the feature space. The robustness of the proposed technique is assessed by the Optimum-Path Forest classifier. Experiments showed that the proposed methodology can outperform individual information provided by single descriptors in well-known public datasets. © 2012 IEEE.
dc.languageeng
dc.relationBrazilian Symposium of Computer Graphic and Image Processing
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectDescriptor Combination
dc.subjectEvolutionary algorithms
dc.subjectImage classification
dc.subjectCombined informations
dc.subjectData sets
dc.subjectDescriptors
dc.subjectFeature space
dc.subjectFeature vectors
dc.subjectOptimization problems
dc.subjectOptimum-path forests
dc.subjectVisual properties
dc.subjectVector spaces
dc.titleImproving image classification through descriptor combination
dc.typeOtro


Este ítem pertenece a la siguiente institución