Progressive randomization: Seeing the unseen

dc.creatorRocha, A
dc.creatorGoldenstein, S
dc.date2010
dc.dateMAR
dc.date2014-11-14T12:30:23Z
dc.date2015-11-26T17:15:04Z
dc.date2014-11-14T12:30:23Z
dc.date2015-11-26T17:15:04Z
dc.date.accessioned2018-03-29T00:03:18Z
dc.date.available2018-03-29T00:03:18Z
dc.identifierComputer Vision And Image Understanding. Academic Press Inc Elsevier Science, v. 114, n. 3, n. 349, n. 362, 2010.
dc.identifier1077-3142
dc.identifierWOS:000275485000005
dc.identifier10.1016/j.cviu.2009.10.002
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/70498
dc.identifierhttp://www.repositorio.unicamp.br/handle/REPOSIP/70498
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/70498
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1281952
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionIn this paper, we introduce the progressive randomization (PR): a new image meta-description approach suitable for different image inference applications such as broad class Image Categorization Forensics and, Steganalysis. The main difference among PR and the state-of-the-art algorithms is that it is based on progressive perturbations on pixel values of images. With such perturbations, PR captures the image class separability allowing us to successfully infer high-level information about images. Even when only a limited number of training examples are available, the method still achieves good separability, and its accuracy increases with the size of the training set. We validate the method using two different inference scenarios and four image databases. (C) 2009 Elsevier Inc. All rights reserved.
dc.description114
dc.description3
dc.description349
dc.description362
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionFAPESP [05/58103-3, 07/52015-0, 08/08681-9]
dc.descriptionCNPq [309254/2007-8, 472402/2007-2, 551007/2007-9]
dc.languageen
dc.publisherAcademic Press Inc Elsevier Science
dc.publisherSan Diego
dc.publisherEUA
dc.relationComputer Vision And Image Understanding
dc.relationComput. Vis. Image Underst.
dc.rightsfechado
dc.rightshttp://www.elsevier.com/about/open-access/open-access-policies/article-posting-policy
dc.sourceWeb of Science
dc.subjectImage inference
dc.subjectProgressive randomization
dc.subjectImage categorization
dc.subjectImage forensics
dc.subjectSteganalysis
dc.subjectScene Classification
dc.subjectRepresentation
dc.subjectPhotographs
dc.subjectShape
dc.titleProgressive randomization: Seeing the unseen
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución