JPEG Compression Model in Copy-move Forgery Detection

0482763 - ÚTIA 2018 RIV CA eng C - Konferenční příspěvek (zahraniční konf.)
Novozámský, Adam - Šorel, Michal
JPEG Compression Model in Copy-move Forgery Detection.
Proceedings of the Seventh International Conference on Image Processing Theory, Tools and Applications. Montreal: IEEE, 2017, č. článku 65. ISBN 978-1-5386-1843-1.
[International Conference on Image Processing Theory, Tools and Applications (IPTA 2017) /7./. Montreal (CA), 28.11.2017-01.12.2017]
Grant CEP: GA ČR(CZ) GA16-13830S; GA ČR(CZ) GA15-16928S
Institucionální podpora: RVO:67985556
Klíčová slova: Image forensics * Copy-move forgery detection * Image tampering * JPEG * Quantization constraint set
Obor OECD: Automation and control systems
http://library.utia.cas.cz/separaty/2017/ZOI/novozamsky-0482763.pdf

The integrity of visual data is important for the credibility of news media and especially when used as an evidence in court or during criminal investigation. The common way to manipulate image content is copying an object and pasting in another location of the same image. In this paper, we describe a new idea for the detection of this type of forgery in JPEG images, where the compression significantly degrades detection by popular algorithms. We derive a JPEG-based constraint that any pair of patches must satisfy to be considered a valid candidate for tampered area. We propose also efficient algorithm to verify the constraint that can be integrated into most existing methods. Experiments show significant improvement of detection, especially for difficult cases, such as small objects, objects covered by textureless areas and repeated patterns.
Trvalý link: http://hdl.handle.net/11104/0278140