Forensic Technique for Detection of Image Forgery

Todays digital image plays an important role in all areas such as baking, communication, business etc. Due to the availability of manipulation software it is very easy to manipulate the original image. The contents in an original image can be copy-paste to hide some information or to create tampering. The new area introduces to detect the forgery is an image forensic. In this paper proposes the new image forensic technique to detect the presence of forgery in the compressed images and in other format images. The proposed method is based on the no subsampled contoured transform (NSCT). The proposed method is made up of three parts as preprocessing, nsct transform and forgery detection. The proposed forensic method is flexible, multiscale, multidirectional, and image decomposition is shift invariant that can be efficiently implemented via the à trous algorithm. The proposed a design framework based on the mapping approach. This method allows for a fast implementation based on a lifting or ladder structure. The proposed method ensures that the frame elements are regular, symmetric, and the frame is close to a tight one. The NSCT compares with and dct method in this paper.