End-to-end double JPEG detection with a 3D convolutional network in the DCT domain

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 196
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorahn, wonhyukko
dc.contributor.authorNam, Seung-hunko
dc.contributor.authorSon, Minseokko
dc.contributor.authorLee, Heung-Kyuko
dc.contributor.authorChoi, Sungheeko
dc.date.accessioned2020-02-11T06:20:21Z-
dc.date.available2020-02-11T06:20:21Z-
dc.date.created2020-02-10-
dc.date.issued2020-01-
dc.identifier.citationELECTRONICS LETTERS, v.56, no.2, pp.82 - 85-
dc.identifier.issn0013-5194-
dc.identifier.urihttp://hdl.handle.net/10203/272245-
dc.description.abstractDetection of double JPEG compression is essential in the field of digital image forensics. Although double JPEG compression detection methods have greatly improved with the development of convolutional neural networks (CNNs), they rely on handcrafted features such as discrete cosine transform (DCT) histograms. In this Letter, the authors propose an end-to-end trainable 3D CNN in the DCT domain for double JPEG compression detection. Moreover, they also propose a new type of module, called feature rescaling, to insert the quantisation table into the network suitably. The experiments show that the proposed method outperforms state-of-the-art methods.-
dc.languageEnglish-
dc.publisherINST ENGINEERING TECHNOLOGY-IET-
dc.titleEnd-to-end double JPEG detection with a 3D convolutional network in the DCT domain-
dc.typeArticle-
dc.identifier.wosid000507916900011-
dc.identifier.scopusid2-s2.0-85078102960-
dc.type.rimsART-
dc.citation.volume56-
dc.citation.issue2-
dc.citation.beginningpage82-
dc.citation.endingpage85-
dc.citation.publicationnameELECTRONICS LETTERS-
dc.identifier.doi10.1049/el.2019.2719-
dc.contributor.localauthorLee, Heung-Kyu-
dc.contributor.localauthorChoi, Sunghee-
dc.contributor.nonIdAuthorSon, Minseok-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorconvolution-
dc.subject.keywordAuthorquantisation (signal)-
dc.subject.keywordAuthorimage coding-
dc.subject.keywordAuthordiscrete cosine transforms-
dc.subject.keywordAuthorneural nets-
dc.subject.keywordAuthordata compression-
dc.subject.keywordAuthorDCT domain-
dc.subject.keywordAuthordigital image forensics-
dc.subject.keywordAuthordouble JPEG compression detection methods-
dc.subject.keywordAuthorconvolutional neural networks-
dc.subject.keywordAuthorhandcrafted features-
dc.subject.keywordAuthorend-to-end trainable 3D CNN-
dc.subject.keywordAuthorto-end double JPEG detection-
dc.subject.keywordAuthor3D convolutional network-
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0