Illuminant-Based Transformed Spaces for Image Forensics
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNIFESP |
Texto Completo: | https://repositorio.unifesp.br/handle/11600/57761 http://dx.doi.org/10.1109/TIFS.2015.2506548 |
Resumo: | In 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. |
id |
UFSP_c373708d7a9437d08d227d87b978ccb9 |
---|---|
oai_identifier_str |
oai:repositorio.unifesp.br:11600/57761 |
network_acronym_str |
UFSP |
network_name_str |
Repositório Institucional da UNIFESP |
repository_id_str |
3465 |
spelling |
Carvalho, TiagoFaria, Fabio A. [UNIFESP]Pedrini, HelioTorres, Ricardo da S.Rocha, Anderson2020-08-21T16:59:46Z2020-08-21T16:59:46Z2016Ieee Transactions On Information Forensics And Security. Piscataway, v. 11, n. 4, p. 720-733, 2016.1556-6013https://repositorio.unifesp.br/handle/11600/57761http://dx.doi.org/10.1109/TIFS.2015.2506548WOS000370734700005.pdf10.1109/TIFS.2015.2506548WOS:000370734700005In 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.Coordination for the Improvement of Higher Education PersonnelMicrosoft ResearchCAPES DeepEyes ProjectSao Paulo Research FoundationBrazilian National Research CouncilInstituto Federal de Educacao, Ciencia e Tecnologia do Sudeste de Minas GeraisUniversity of CampinasUniv Estadual Campinas, Inst Comp, RECOD Lab, BR-13083970 Campinas, SP, BrazilUniv Fed Sao Paulo, GIBIS Lab, BR-04021001 Sao Paulo, BrazilUniv Fed Sao Paulo, GIBIS Lab, BR-04021001 Sao Paulo, BrazilCAPES: 0214-13-2FAPESP: 2010/05647-4FAPESP: 2010/14910-0FAPESP: 2011/22749-8CNPq: 140916/2012-1CNPq: 477662/2013-7CNPq: 307113/2012-4CNPq: 304352/2012-8Web of Science720-733engIeee-Inst Electrical Electronics Engineers IncIeee Transactions On Information Forensics And SecurityDigital forensicssplicing detectionilluminant mapsimage descriptorsmachine learningdiversity measuresIlluminant-Based Transformed Spaces for Image Forensicsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlePiscataway114info:eu-repo/semantics/openAccessreponame:Repositório Institucional da UNIFESPinstname:Universidade Federal de São Paulo (UNIFESP)instacron:UNIFESPORIGINALWOS000370734700005.pdfapplication/pdf4357062${dspace.ui.url}/bitstream/11600/57761/1/WOS000370734700005.pdfbc6b19ef75faef5ef75f7958e7b42a5fMD51open accessTEXTWOS000370734700005.pdf.txtWOS000370734700005.pdf.txtExtracted texttext/plain72404${dspace.ui.url}/bitstream/11600/57761/8/WOS000370734700005.pdf.txt7d85dccd73d9223d535da06070396bceMD58open accessTHUMBNAILWOS000370734700005.pdf.jpgWOS000370734700005.pdf.jpgIM Thumbnailimage/jpeg7868${dspace.ui.url}/bitstream/11600/57761/10/WOS000370734700005.pdf.jpg8add40b6d6ddf92b59299849531f7c67MD510open access11600/577612023-06-05 19:08:12.105open accessoai:repositorio.unifesp.br:11600/57761Repositório InstitucionalPUBhttp://www.repositorio.unifesp.br/oai/requestopendoar:34652023-06-05T22:08:12Repositório Institucional da UNIFESP - Universidade Federal de São Paulo (UNIFESP)false |
dc.title.en.fl_str_mv |
Illuminant-Based Transformed Spaces for Image Forensics |
title |
Illuminant-Based Transformed Spaces for Image Forensics |
spellingShingle |
Illuminant-Based Transformed Spaces for Image Forensics Carvalho, Tiago Digital forensics splicing detection illuminant maps image descriptors machine learning diversity measures |
title_short |
Illuminant-Based Transformed Spaces for Image Forensics |
title_full |
Illuminant-Based Transformed Spaces for Image Forensics |
title_fullStr |
Illuminant-Based Transformed Spaces for Image Forensics |
title_full_unstemmed |
Illuminant-Based Transformed Spaces for Image Forensics |
title_sort |
Illuminant-Based Transformed Spaces for Image Forensics |
author |
Carvalho, Tiago |
author_facet |
Carvalho, Tiago Faria, Fabio A. [UNIFESP] Pedrini, Helio Torres, Ricardo da S. Rocha, Anderson |
author_role |
author |
author2 |
Faria, Fabio A. [UNIFESP] Pedrini, Helio Torres, Ricardo da S. Rocha, Anderson |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Carvalho, Tiago Faria, Fabio A. [UNIFESP] Pedrini, Helio Torres, Ricardo da S. Rocha, Anderson |
dc.subject.eng.fl_str_mv |
Digital forensics splicing detection illuminant maps image descriptors machine learning diversity measures |
topic |
Digital forensics splicing detection illuminant maps image descriptors machine learning diversity measures |
description |
In 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. |
publishDate |
2016 |
dc.date.issued.fl_str_mv |
2016 |
dc.date.accessioned.fl_str_mv |
2020-08-21T16:59:46Z |
dc.date.available.fl_str_mv |
2020-08-21T16:59:46Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
Ieee Transactions On Information Forensics And Security. Piscataway, v. 11, n. 4, p. 720-733, 2016. |
dc.identifier.uri.fl_str_mv |
https://repositorio.unifesp.br/handle/11600/57761 http://dx.doi.org/10.1109/TIFS.2015.2506548 |
dc.identifier.issn.none.fl_str_mv |
1556-6013 |
dc.identifier.file.none.fl_str_mv |
WOS000370734700005.pdf |
dc.identifier.doi.none.fl_str_mv |
10.1109/TIFS.2015.2506548 |
dc.identifier.wos.none.fl_str_mv |
WOS:000370734700005 |
identifier_str_mv |
Ieee Transactions On Information Forensics And Security. Piscataway, v. 11, n. 4, p. 720-733, 2016. 1556-6013 WOS000370734700005.pdf 10.1109/TIFS.2015.2506548 WOS:000370734700005 |
url |
https://repositorio.unifesp.br/handle/11600/57761 http://dx.doi.org/10.1109/TIFS.2015.2506548 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.none.fl_str_mv |
Ieee Transactions On Information Forensics And Security |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
720-733 |
dc.coverage.none.fl_str_mv |
Piscataway |
dc.publisher.none.fl_str_mv |
Ieee-Inst Electrical Electronics Engineers Inc |
publisher.none.fl_str_mv |
Ieee-Inst Electrical Electronics Engineers Inc |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UNIFESP instname:Universidade Federal de São Paulo (UNIFESP) instacron:UNIFESP |
instname_str |
Universidade Federal de São Paulo (UNIFESP) |
instacron_str |
UNIFESP |
institution |
UNIFESP |
reponame_str |
Repositório Institucional da UNIFESP |
collection |
Repositório Institucional da UNIFESP |
bitstream.url.fl_str_mv |
${dspace.ui.url}/bitstream/11600/57761/1/WOS000370734700005.pdf ${dspace.ui.url}/bitstream/11600/57761/8/WOS000370734700005.pdf.txt ${dspace.ui.url}/bitstream/11600/57761/10/WOS000370734700005.pdf.jpg |
bitstream.checksum.fl_str_mv |
bc6b19ef75faef5ef75f7958e7b42a5f 7d85dccd73d9223d535da06070396bce 8add40b6d6ddf92b59299849531f7c67 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UNIFESP - Universidade Federal de São Paulo (UNIFESP) |
repository.mail.fl_str_mv |
|
_version_ |
1802764215970168832 |