A scheme for copy-move forgery detection in digital images based on 2D-DWT

Abstract

In this paper, a copy-move image forgery detection scheme is developed based on a block matching algorithm. Instead of considering spatial blocks, 2D-DWT is performed on the forged image and then DWT domain blocks are considered, where only approximate DWT coefficients are utilized. In order to reduce the computational burden, unlike conventional approaches, instead of performing block matching operation among all blocks, some candidate blocks are first selected from the non-overlapping blocks based on a similarity measure. In the next stage, all overlapping blocks are compared with the candidate blocks. A similarity criterion is introduced to finally detect the forged blocks. Extensive simulation is carried out on several forged images and it is found that proposed algorithm can efficiently detect copy-move forgery.