Abstract
In this era of technology, digital images turn out to be ubiquitous in a contemporary society and they can be generated and manipulated by a wide variety of hardware and software technologies. Copy-move forgery is considered as an image tampering technique that aims to generate manipulated tampered images by concealing unwanted objects or reproducing desirable objects within the same image. Therefore, image content authentication has become an essential demand. In this paper, an innovative design for automatic detection of copy-move forgery based on deep learning approaches is proposed. A Convolutional Neural Network (CNN) is specifically designed for Copy-Move Forgery Detection (CMFD). The CNN is exploited to learn hierarchical feature representations from input images, which are used for detecting the tampered and original images. The extensive experiments demonstrate that the proposed deep CMFD algorithm outperforms the traditional CMFD systems by a considerable margin on the three publicly accessible datasets: MICC-F220, MICC-F2000, and MICC-F600. Furthermore, the three datasets are incorporated and joined to the SATs-130 dataset to form new combinations of datasets. An accuracy of 100% has been achieved for the four datasets. This proves the robustness of the proposed algorithm against a diversity of known attacks. For better evaluation, comparative results are included.