Illuminant-Based Transformed Spaces for Image Forensics

Página do item simplificado
dc.citation.issue4
dc.citation.volume11
dc.contributor.authorCarvalho, Tiago
dc.contributor.authorFaria, Fabio A. [UNIFESP]
dc.contributor.authorPedrini, Helio
dc.contributor.authorTorres, Ricardo da S.
dc.contributor.authorRocha, Anderson
dc.coveragePiscataway
dc.date.accessioned2020-08-21T16:59:46Z
dc.date.available2020-08-21T16:59:46Z
dc.date.issued2016
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.affiliationUniv Estadual Campinas, Inst Comp, RECOD Lab, BR-13083970 Campinas, SP, Brazil
dc.description.affiliationUniv Fed Sao Paulo, GIBIS Lab, BR-04021001 Sao Paulo, Brazil
dc.description.affiliationUnifespUniv Fed Sao Paulo, GIBIS Lab, BR-04021001 Sao Paulo, Brazil
dc.description.sourceWeb of Science
dc.description.sponsorshipCoordination for the Improvement of Higher Education Personnel
dc.description.sponsorshipMicrosoft Research
dc.description.sponsorshipCAPES DeepEyes Project
dc.description.sponsorshipSao Paulo Research Foundation
dc.description.sponsorshipBrazilian National Research Council
dc.description.sponsorshipInstituto Federal de Educacao, Ciencia e Tecnologia do Sudeste de Minas Gerais
dc.description.sponsorshipUniversity of Campinas
dc.description.sponsorshipIDCAPES: 0214-13-2
dc.description.sponsorshipIDFAPESP: 2010/05647-4
dc.description.sponsorshipIDFAPESP: 2010/14910-0
dc.description.sponsorshipIDFAPESP: 2011/22749-8
dc.description.sponsorshipIDCNPq: 140916/2012-1
dc.description.sponsorshipIDCNPq: 477662/2013-7
dc.description.sponsorshipIDCNPq: 307113/2012-4
dc.description.sponsorshipIDCNPq: 304352/2012-8
dc.format.extent720-733
dc.identifierhttp://dx.doi.org/10.1109/TIFS.2015.2506548
dc.identifier.citationIeee Transactions On Information Forensics And Security. Piscataway, v. 11, n. 4, p. 720-733, 2016.
dc.identifier.doi10.1109/TIFS.2015.2506548
dc.identifier.fileWOS000370734700005.pdf
dc.identifier.issn1556-6013
dc.identifier.urihttps://repositorio.unifesp.br/handle/11600/57761
dc.identifier.wosWOS:000370734700005
dc.language.isoeng
dc.publisherIeee-Inst Electrical Electronics Engineers Inc
dc.relation.ispartofIeee Transactions On Information Forensics And Security
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectDigital forensicsen
dc.subjectsplicing detectionen
dc.subjectilluminant mapsen
dc.subjectimage descriptorsen
dc.subjectmachine learningen
dc.subjectdiversity measuresen
dc.titleIlluminant-Based Transformed Spaces for Image Forensicsen
dc.typeinfo:eu-repo/semantics/article
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
WOS000370734700005.pdf
Tamanho:
4.16 MB
Formato:
Adobe Portable Document Format
Descrição:
Baixar
Coleções
ICT - Artigos