Increase the efficiency of DCT method for detection of copy-move forgery in complex and smooth images

Digital images are easy to manipulate and edit due to advances in computers and image editing software. Copy-move forgery is one of the most popular tampering artifacts in digital images that used by image forgers. In this paper, a DCT-based method is developed to detect image forgery considering the complexity of input image. To detect duplicate region, images are divided into two categories: smooth and complex. To extract features discrete cosine transform (DCT) is applied to each block. Experimental results show that our proposed method is able to precisely detect duplicated regions even when the image was undergone several image manipulations like lossy JPEG compression, Gaussian blur filtering and Gaussian white noise contamination.