Copy-Paste Detection Based on a SIFT Marked Graph Feature Vector

To detect copy-paste tampering, an improved SIFT (Scale invariant feature transform)-based algorithm was proposed. Maximum angle is defined and a maximum angle-based marked graph is constructed. The marked graph feature vector is provided to each SIFT key point via discrete polar coordinate transformation. Key points are matched to detect the copy-paste tampering regions. The experimental results show that the proposed algorithm can effectively identify and detect the rotated or scaled copy-paste regions, and in comparison with the methods reported previously, it is resistant to post-processing, such as blurring, Gaussian white noise and JPEG recompression. The proposed algorithm performs better than the existing algorithm to dealing with scaling transformation.