Digital Image Forgery Detection by Local Statistical Models

0348592 - ÚTIA 2011 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Grim, Jiří - Somol, Petr - Pudil, Pavel
Digital Image Forgery Detection by Local Statistical Models.
2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Los Alamitos, California: IEEE computer society, 2010 - (Echizen, I.; Pan, J.; Fellner, D.; Nouak, A.; Kuijper, A.; Jain, L.), s. 579-582. ISBN 978-0-7695-4222-5.
[6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP 2010). Darmstadt (DE), 15.10.2010-17.10.2010]
Grant CEP: GA MŠMT 1M0572; GA ČR GA102/08/0593; GA ČR GA102/07/1594
Grant ostatní: GA MŠk(CZ) 2C06019
Výzkumný záměr: CEZ:AV0Z10750506
Klíčová slova: forgery detection * local statistical models * distribution mixtures * EM algorithm
Kód oboru RIV: IN - Informatika
http://library.utia.cas.cz/separaty/2010/RO/grim-digital image forgery detection by local statistical models.pdf

We propose an application of local statistical models in the form of a locally estimated Gaussian mixture to image forgery detection. The estimated mixture is used to compute the so called log-likelihood transformation of the original image. We show that image manipulations of different type may be visible in a suitably designed log-likelihood image. Unlike other methods the forgery detection based on local statistical model is rather non-specific and suitable to emphasize various traces of possible image tampering without any prior information.
Trvalý link: http://hdl.handle.net/11104/0189094