LAUSR

With the maturity of image editing software, image content has been forged frequently, posing potential threats to many critical fields. To detect forgery images effectively, this paper proposes an image copy-move forgery detection (CMFD) method based on speeded-up robust feature (SURF) and polar complex exponential transform (PCET). Firstly, image is divided into non-overlapping irregular image blocks by superpixel segmentation. Then, these image blocks are separated into two categories: smooth regions and texture regions. Secondly, after finding the keypoints by SURF, the PCET coefficients are extracted and utilized for searching similar features by feature matching algorithm. Thirdly, a strategy is used to eliminate false matched points and find the regions with dense matched points. It combines the random sample consensus (RANSAC) algorithm and a filtering scheme. Finally, mathematical morphology and an iterative strategy are adopted to refine the tampered regions. Compared with other CMFD methods, the proposed method can detect the forgery which occurs in high-brightness smooth regions or forgery images involving similar but genuine regions. Experimental results also indicate the proposed method can resist different distortions by various attacks, including rotation, scaling, blurring, joint photographic expert group (JPEG) compression, and noise addition.