Abstract—We propose a novel technique in this paper to expose splicing forgery in digital images. The forged area spliced from other picture contains some features which may be inconsistent with the rest part of image. Noise pattern and level is a possible factor to reveal such inconsistency. To detect such noise discrepancies, the test picture is initially segmented into small pieces by SLIC superpixels algorithm. The noise pattern and level of each segment is then estimated by using various filters. The noise features constructed in this step are utilized in energy-based graph cut to expose forged area in the final step. Experimental results show that our method provides good illustration of regions with noise inconsistency in various scenarios.

Index Terms—Forgery detection, graphic cuts, noise estimation, SLIC, splicing forgery.

The authors are with the Department of Computer and Information Science, University of Macau, Macau, China (e-mail: liubo.macau@gmail.com, cmpun@umac.mo).

Cite:Bo Liu and Chi-Man Pun, "Splicing Forgery Exposure in Digital Image by Detecting Noise Discrepancies," International Journal of Computer and Communication Engineering vol. 4, no. 1, pp. 33-38, 2015.