As most of digital cameras and image capture devices do not have modules for embedding watermark or signature, passive forgery detection which aims to detect the traces of tamping without embedded information has become the major focus of recent research for JPEG compressed image. However, our investigation shows that current approaches for detection and localization of tampered areas are very sensitive to image contents, and suffer from high false detection rates for localization of tampered areas for images with intensive edges and textures. In this paper, we present an effective approach which overcomes above problem, using reliable estimation and analysis of block sizes from the block artifacts resulting in JPEG compression process. We first propose an enhanced cross difference filter to strengthen block artifacts and reduce interference from edges and textures, and then integrate techniques from random sampling, voting and maximum likelihood method to improve the accuracy of block size estimation. We develop two different random sampling strategies for block size estimation: one for estimation of the primary JPEG block size, and the other for consistency analysis of local block sizes. Local blocks whose JPEG block sizes are different from the primary block size are classified as tampered blocks. We finally perform a refinement process to eliminate false detections and fill in undetected tampered blocks. Experiment over various tampering methods such as copy-and-paste, image completion and composite tampering, shows that our approach can effectively detect and localize tampered areas, and is not sensitive to image contents such as edges and textures.
Relation:
Applied Mathematics & Information Sciences 9(2), p.1015–1028
