An integrated method of copy-move and splicing for image forgery detection

Splicing and copy-move are two well known methods of passive image forgery. In this paper, splicing and copy-move forgery detection are performed simultaneously on the same database CASIA v1.0 and CASIA v2.0. Initially, a suspicious image is taken and features are extracted through BDCT and enhanced threshold method. The proposed technique decides whether the given image is manipulated or not. If it is manipulated then support vector machine (SVM) classify that the given image is gone through splicing forgery or copy-move forgery. For copy-move detection, ZM-polar (Zernike Moment) is used to locate the duplicated regions in image. Experimental results depict the performance of the proposed method.