LAUSR

Copy-move forgery (CMF), which copies a part of an image and pastes it into another region, is one of the most common methods for digital image tampering. For CMF detection (CMFD), we propose a fast and robust approach that can handle several geometric transformations including rotation, scaling, sheering, and reflection. In the proposed CMFD design, keypoints and their descriptors are extracted from the image based on the Scale Invariant Feature Transform (SIFT). Then, an improved matching operation that can handle multiple copy-move forgeries is performed to detect matched pairs located in duplicated regions. Next, the geometric transformation between duplicated regions is estimated using a subset of reliable matched pairs which are obtained using the SIFT scale space representation. In our simulation, we present comparative results between the proposed algorithm and state-of-the-art ones with proven performance guarantees.