Spatio-temporal rich model-based video steganalysis on cross sections of motion vector planes.

Hdl Handle:
http://hdl.handle.net/10545/622425
Title:
Spatio-temporal rich model-based video steganalysis on cross sections of motion vector planes.
Authors:
Tasdemir, Kasim ( 0000-0003-4542-2728 ) ; Kurugollu, Fatih; Sezer, Sakir
Abstract:
A rich model-based motion vector (MV) steganalysis benefiting from both temporal and spatial correlations of MVs is proposed in this paper. The proposed steganalysis method has a substantially superior detection accuracy than the previous methods, even the targeted ones. The improvement in detection accuracy lies in several novel approaches introduced in this paper. First, it is shown that there is a strong correlation, not only spatially but also temporally, among neighbouring MVs for longer distances. Therefore, temporal MV dependency alongside the spatial dependency is utilized for rigorous MV steganalysis. Second, unlike the filters previously used, which were heuristically designed against a specific MV steganography, a diverse set of many filters, which can capture aberrations introduced by various MV steganography methods is used. The variety and also the number of the filter kernels are substantially more than that of used in the previous ones. Besides that, filters up to fifth order are employed whereas the previous methods use at most second order filters. As a result of these, the proposed system captures various decorrelations in a wide spatio-temporal range and provides a better cover model. The proposed method is tested against the most prominent MV steganalysis and steganography methods. To the best knowledge of the authors, the experiments section has the most comprehensive tests in MV steganalysis field, including five stego and seven steganalysis methods. Test results show that the proposed method yields around 20% detection accuracy increase in low payloads and 5% in higher payloads.
Affiliation:
Abdullah Gül University; Queen's University Belfast
Citation:
Tasdemir, K. et al (2016) 'Spatio-Temporal Rich Model-Based Video Steganalysis on Cross Sections of Motion Vector Planes', IEEE Transactions on Image Processing, 25 (7):3316 .
Publisher:
Institute of Electrical and Electronic Engineers
Journal:
IEEE Transactions on Image Processing
Issue Date:
11-May-2016
URI:
http://hdl.handle.net/10545/622425
DOI:
10.1109/TIP.2016.2567073
Additional Links:
http://ieeexplore.ieee.org/document/7468453/
Type:
Article
Language:
en
ISSN:
10577149
EISSN:
19410042
Sponsors:
Engineering and Physical Sciences Research Council through the CSIT 2 Project under Grant EP/N508664/1.
Appears in Collections:
Department of Electronics, Computing & Maths

Full metadata record

DC FieldValue Language
dc.contributor.authorTasdemir, Kasimen
dc.contributor.authorKurugollu, Fatihen
dc.contributor.authorSezer, Sakiren
dc.date.accessioned2018-03-21T16:16:54Z-
dc.date.available2018-03-21T16:16:54Z-
dc.date.issued2016-05-11-
dc.identifier.citationTasdemir, K. et al (2016) 'Spatio-Temporal Rich Model-Based Video Steganalysis on Cross Sections of Motion Vector Planes', IEEE Transactions on Image Processing, 25 (7):3316 .en
dc.identifier.issn10577149-
dc.identifier.doi10.1109/TIP.2016.2567073-
dc.identifier.urihttp://hdl.handle.net/10545/622425-
dc.description.abstractA rich model-based motion vector (MV) steganalysis benefiting from both temporal and spatial correlations of MVs is proposed in this paper. The proposed steganalysis method has a substantially superior detection accuracy than the previous methods, even the targeted ones. The improvement in detection accuracy lies in several novel approaches introduced in this paper. First, it is shown that there is a strong correlation, not only spatially but also temporally, among neighbouring MVs for longer distances. Therefore, temporal MV dependency alongside the spatial dependency is utilized for rigorous MV steganalysis. Second, unlike the filters previously used, which were heuristically designed against a specific MV steganography, a diverse set of many filters, which can capture aberrations introduced by various MV steganography methods is used. The variety and also the number of the filter kernels are substantially more than that of used in the previous ones. Besides that, filters up to fifth order are employed whereas the previous methods use at most second order filters. As a result of these, the proposed system captures various decorrelations in a wide spatio-temporal range and provides a better cover model. The proposed method is tested against the most prominent MV steganalysis and steganography methods. To the best knowledge of the authors, the experiments section has the most comprehensive tests in MV steganalysis field, including five stego and seven steganalysis methods. Test results show that the proposed method yields around 20% detection accuracy increase in low payloads and 5% in higher payloads.en
dc.description.sponsorshipEngineering and Physical Sciences Research Council through the CSIT 2 Project under Grant EP/N508664/1.en
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronic Engineersen
dc.relation.urlhttp://ieeexplore.ieee.org/document/7468453/en
dc.rightsArchived with thanks to IEEE Transactions on Image Processingen
dc.subjectAdaptation modelsen
dc.subjectCorrelationen
dc.subjectAlgorithm design and analysisen
dc.subjectImage codingen
dc.subjectVideo signal processingen
dc.subjectSteganalysisen
dc.titleSpatio-temporal rich model-based video steganalysis on cross sections of motion vector planes.en
dc.typeArticleen
dc.identifier.eissn19410042-
dc.contributor.departmentAbdullah Gül Universityen
dc.contributor.departmentQueen's University Belfasten
dc.identifier.journalIEEE Transactions on Image Processingen
All Items in UDORA are protected by copyright, with all rights reserved, unless otherwise indicated.