This project is concerned with the detection of digital image forgery. The area has an unexplored character and there is alot to do. Authentication of digital images play an important role in forensic investigation, criminal investigation,insurance processing, surveillance systems, intelligence services and journalism.The project is supposed to be carried out in five stages . The first four stages correspond to major theoretical goals of the project, the last one is related to real-life applications. a) blind method for resampling detection b) blind method for duplicated regions detection c) automatic method for detection of double JPEG compresion d) detection of inconsistent noise patterns e) system integration and testing Our attention will be paid to robustness and sensitivity of novel methods to noise, luminance transformations and to lossy compresssion schemes.