An Image Copy Move Forgery Detection Method Using QDCT

With a rapid evolution of computer science, digital image manipulation becomes much more easily. One of the most commonly tampering with a digital image is copy-move forgery, in which a part of image is copied and used to cover another part in a different location in the same image. In this paper, we present an efficient and robust quaternion discrete cosine transform (QDCT) based method to detect this artifact. First, the R,G,B component of a tampered image is divided into overlapping fixed-size blocks, and a quaternion is constructed by using each R,G,B component block. Secondly, QDCT is applied to each quaternion block and using Zig-zag scanning extract finite QDCT coefficients, thus, the feature vectors are extracted from finite QDCT coefficients of overlapping blocks, and reduced features are generated. Finally, feature vectors are sorted lexicographically. The duplicated image blocks will be matched by a preset threshold value. Experiment results show that our proposed scheme can efficiently detect the copy-move forgery.