Copy-move forgery detection in digital images using affine-SIFT

Copy-move is a simple and effective operation for creating digital image forgeries, where an area of an image is copied and pasted to a different location in that image. Generally, a forger uses some affine transformations to make the changes visually intact. Most existing copy-move detection methods are not effective when copied regions are under geometrical distortions. In this paper, a new copy-move detection method based on affine scale invariant feature transform (ASIFT) is proposed, which is fully affine invariant and robust to transformations and deformation of copy-move regions. Our method starts by finding matched ASIFT keypoints and then estimates all pixels within the duplicated regions by using superpixel segmentation and morphological operations. Our experimental results demonstrate that the proposed method is efficient and powerful to detect copy-move regions, even when the copied region has undergone severe transformations and common post-processings like adding noise and blurring.