RUS  ENG JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB
 General information Latest issue Archive Search papers Search references RSS Latest issue Current issues Archive issues What is RSS

 Computer Optics: Year: Volume: Issue: Page: Find

 Computer Optics, 2017, Volume 41, Issue 6, Pages 920–930 (Mi co466)

IMAGE PROCESSING, PATTERN RECOGNITION

Image splicing localization based on CFA-artifacts analysis

A. A. Varlamovaa, A. V. Kuznetsovab

a Samara National Research University, Samara, Russia
b Image Processing Systems Institute of the RAS - Branch of the FSRC "Crystallography and Photonics" RAS, Samara, Russia

Abstract: Image splicing is a widespread image forgery technique in which fragments from another image are pasted into the image under forgery. In this paper, a method of image splicing localization based on the analysis of CFA-artifacts that appear in the image during the capturing process is described. A feature characterizing the presence/absence of CFA artifacts for each image block is measured. The obtained values of the feature define the probability of each block to be embedded. Analysis of the accuracy of the splicing localization method and its robustness against different types of tampering, such as additive Gaussian noise, JPEG compression, and linear enhancement are presented in the experimental part of the paper. The results show that the suggested method reveals the embedded regions of different shape, size, and nature in images. The method is found to be stable to the additive Gaussian noise and linear enhancement, but not stable to JPEG compression. The advantage of the method is the ability to localize the spliced-in regions as small as a $2\times 2$ block.

Keywords: image forgery, color filter array, Bayer filter, interpolation, artifact, tampering probability map.

 Funding Agency Grant Number Russian Foundation for Basic Research 16-37-00056-ìîë_à The work was partially funded by the RFBR grant #16-37-00056.

DOI: https://doi.org/10.18287/2412-6179-2017-41-6-920-930

Full text: PDF file (608 kB)
Full text: http://www.computeroptics.smr.ru/.../410618.html
References: PDF file   HTML file

Accepted:27.11.2017

Citation: A. A. Varlamova, A. V. Kuznetsov, “Image splicing localization based on CFA-artifacts analysis”, Computer Optics, 41:6 (2017), 920–930

Citation in format AMSBIB
\Bibitem{VarKuz17} \by A.~A.~Varlamova, A.~V.~Kuznetsov \paper Image splicing localization based on CFA-artifacts analysis \jour Computer Optics \yr 2017 \vol 41 \issue 6 \pages 920--930 \mathnet{http://mi.mathnet.ru/co466} \crossref{https://doi.org/10.18287/2412-6179-2017-41-6-920-930}