Một lược đồ mới phát hiện ảnh giả mạo dựa trên luật Benford

Digital image tampering is becoming popular and might cause serious consequences on different areas. Thus, detection of image forgeries is an urgent need. There are various forgery types, which can be exposed by different forensic techniques. In this paper, we propose a new method based on Benford law, also known as the first-digit law, and the SVM classification in order to identify double JPEG compressed images and Gaussian noise added images. Experiments on large-scale image data sets show that the proposed scheme is reliable and it can achieve a high forgery detection capability, with a detection rate is about 90% or higher.