Detection of copy-move forgery in digital images based on DCT

With rapid advances in digital information processing systems, and more specifically in digital image processing software, there is a widespread development of advanced tools and techniques for digital image forgery. One of the techniques most commonly used is the Copy-move forgery which proceeds by copying a part of an image and pasting it into the same image, in order to maliciously hide an object or a region. In this paper, we propose a method to detect this specific kind of counterfeit. Firstly, the color image is converted from RGB color space to YCbCr color space and then the R, G, B and Y-component are splitted into fixed-size overlapping blocks and, features are extracted from the R, G and B-components image blocks on one hand and on the other, from the DCT representation of the R, G, B and Ycomponent image block. The feature vectors obtained are then lexicographically sorted to make similar image blocks neighbors and duplicated image blocks are identified using Euclidean distance as similarity criterion. Experimental results showed that the proposed method can detect the duplicated regions when there is more than one copy move forged area in the image and even in case of slight rotations, JPEG compression, shift, scale, blur and noise addition.