An Effective Feature Extracting and Matching Scheme for Copy-Move Forgery Detection

Nowadays, face the abuse of digital technique, it is much necessary to detect whether a digital image is an original one or artificial modification. In this paper, we proposed an effective image feature extracting and matching scheme for Copy-move forgery detection. First, after pre-processing, the overlapped block is slid one pixel each time to detect the host image. Discrete analytical Fourier-Mellin transform is presented to extract the features in each block. Then, locality sensitive hashing is proposed for distinguishing the identical or similar block features in matching step to get the inlier matches. Finally, the geometric operations are presented to better indicate the detected regions. A series of experimental results indicated that the proposed scheme can identify the forgery images and outperforms the state-of-the-art techniques.