The traditional forgery methods are not able to detect forgery images due to latest development in software to edit original images. A highly sophisticated technique to be developed to detect image forgery of new images which is edited with high end modern editing tools. At present, image forgery detection is a one of the challenging task to detect whether an image is from authorized or unauthorized. In some criminal cases images are the major evidence to prove criminal by forensic departments. Forensic departments are to use new methods to detect image forgery which will be useful to investigate criminal cases further. In this paper, we proposed discrete wallet transform and CNN method to detect image forgery. First input images are preprocessed then apply CNN method to identify image forgery into either slicing or copy move. The performance of proposed method is compared with existing algorithm and our method shown better results.