Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/320363
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE ESTADUAL DE CAMPINASpt_BR
dc.identifier.isbn1556-6021pt
dc.contributor.authorunicampRocha, Anderson de Rezendept_BR
dc.contributor.authorunicampTorres, Ricardo da Silvapt_BR
dc.contributor.authorunicampPedrini, Héliopt_BR
dc.contributor.authorunicampCarvalho, Tiago José dept_BR
dc.typeArtigopt_BR
dc.titleIlluminant-based transformed spaces for image forensicspt_BR
dc.contributor.authorCarvalho, Tiagopt_BR
dc.contributor.authorFaria, Fábio A.pt_BR
dc.contributor.authorPedrini, Héliopt_BR
dc.contributor.authorTorres, Ricardo da S.pt_BR
dc.contributor.authorRocha, Andersonpt_BR
unicamp.author.emailtjose@ic.unicamp.br; ffaria@unifesp.br; helio@ic.unicamp.br; rtorres@ic.unicamp.br; anderson@ic.unicamp.brpt_BR
dc.subjectCiência forense digitalpt_BR
dc.subjectAprendizado de máquinapt_BR
dc.subjectMedidas de diversidadept_BR
dc.subjectAnálise forense de imagempt_BR
dc.subjectDescritorespt_BR
dc.subject.otherlanguageDigital forensic sciencept_BR
dc.subject.otherlanguageMachine learningpt_BR
dc.subject.otherlanguageDiversity mesuarept_BR
dc.subject.otherlanguageForensic image analysispt_BR
dc.subject.otherlanguageDescriptorspt_BR
dc.description.abstractIn this paper, we explore transformed spaces, represented by image illuminant maps, to propose a methodology for selecting complementary forms of characterizing visual properties for an effective and automated detection of image forgeries. We combine statistical telltales provided by different image descriptors that explore color, shape, and texture features. We focus on detecting image forgeries containing people and present a method for locating the forgery, specifically, the face of a person in an image. Experiments performed on three different open-access data sets show the potential of the proposed method for pinpointing image forgeries containing people. In the two first data sets (DSO-1 and DSI-1), the proposed method achieved a classification accuracy of 94% and 84%, respectively, a remarkable improvement when compared with the state-of-the-art methods. Finally, when evaluating the third data set comprising questioned images downloaded from the Internet, we also present a detailed analysis of target images.en
dc.description.abstractIn this paper, we explore transformed spaces, represented by image illuminant maps, to propose a methodology for selecting complementary forms of characterizing visual properties for an effective and automated detection of image forgeries. We combine statpt_BR
dc.relation.ispartofIEEE transactions on information forensics and securitypt_BR
dc.publisher.cityPiscataway, NJpt_BR
dc.publisher.countryEstados Unidospt_BR
dc.publisherInstitute of Electrical and Electronics Engineerspt_BR
dc.date.issued2016pt_BR
dc.date.monthofcirculationApr.pt_BR
dc.identifier.citationIeee Transactions On Information Forensics And Security. IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, n. 11, n. 4, p. 720 - 733.pt_BR
dc.language.isoengpt_BR
dc.description.volume11pt_BR
dc.description.issuenumber4pt_BR
dc.description.issuesupplementpt_BR
dc.description.issuepartpt_BR
dc.description.issuespecialpt_BR
dc.description.firstpage720pt_BR
dc.description.lastpage733pt_BR
dc.rightsfechadopt_BR
dc.rightsFechadopt_br
dc.sourceWOSpt_BR
dc.identifier.issn1556-6013pt_BR
dc.identifier.eissn1556-6021pt_BR
dc.identifier.wosidWOS:000370734700005pt_BR
dc.identifier.doi10.1109/TIFS.2015.2506548pt_BR
dc.identifier.urlhttps://ieeexplore.ieee.org/document/7349174pt_BR
dc.description.sponsorshipCAPES - COORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIORpt_BR
dc.description.sponsorshipFAPESP - FUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE SÃO PAULOpt_BR
dc.description.sponsorshipCNPQ - CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICOpt_BR
dc.description.sponsorship1Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)pt_BR
dc.description.sponsorship1Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)pt_BR
dc.description.sponsordocumentnumber0214-13-2pt_BR
dc.description.sponsordocumentnumber2010/05647-4; 2010/14910-0; 2011/22749-8pt_BR
dc.description.sponsordocumentnumber140916/2012-1; 477662/2013-7; 307113/2012-4; 304352/2012-8pt_BR
dc.date.available2016-12-06T18:31:43Z-
dc.date.accessioned2016-12-06T18:31:43Z-
dc.description.provenanceMade available in DSpace on 2016-12-06T18:31:43Z (GMT). No. of bitstreams: 1 000370734700005.pdf: 4347581 bytes, checksum: 32289b566191e12feaf8b197dd423598 (MD5) Previous issue date: 2016 Bitstreams deleted on 2021-01-04T14:26:12Z: 000370734700005.pdf,. Added 1 bitstream(s) on 2021-01-04T14:27:15Z : No. of bitstreams: 1 000370734700005.pdf: 4425415 bytes, checksum: f8b9f11ffd6535ecdb00a43fda9f02ff (MD5)en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/320363-
dc.description.conferencenomept_BR
dc.contributor.departmentDepartamento de Sistemas de Informaçãopt_BR
dc.contributor.departmentDepartamento de Sistemas de Informaçãopt_BR
dc.contributor.departmentDepartamento de Sistemas de Informaçãopt_BR
dc.contributor.departmentsem informaçãopt_BR
dc.contributor.unidadeInstituto de Computaçãopt_BR
dc.contributor.unidadeInstituto de Computaçãopt_BR
dc.contributor.unidadeInstituto de Computaçãopt_BR
dc.contributor.unidadeInstituto de Computaçãopt_BR
dc.subject.keywordDigital forensicspt_BR
dc.subject.keywordSplicing detectionpt_BR
dc.subject.keywordIlluminant mapspt_BR
dc.subject.keywordImage descriptorspt_BR
dc.subject.keywordMachine learningpt_BR
dc.subject.keywordDiversity measurespt_BR
dc.identifier.source000370734700005pt_BR
dc.creator.orcid0000-0002-4236-8218pt_BR
dc.creator.orcid0000-0001-9772-263Xpt_BR
dc.creator.orcid0000-0003-0125-630Xpt_BR
dc.creator.orcid0000-0002-7779-1950pt_BR
dc.type.formArtigopt_BR
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
000370734700005.pdf4.32 MBAdobe PDFView/Open


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