Detection of regional copy/move forgery in MPEG videos using optical flow

With rapid proliferation of affordable video capturing devices and state-of-the-art video editing software tools, it is now easier than ever to manipulate video contents. In this paper a passive method for copy/move video forgery detection in MPEG videos is proposed. The method first divides each video frame into suspicious and apparently innocent parts. Subsequently, an optical flow coefficient is computed from each part. Forgeries are located when an unusual trend in the optical flow coefficient of the suspicious object is detected. Experiments on a set of forged and original sequences validate the justifications made by the proposed method.