A Robust Region Duplication Detection Scheme for Digital Video

Abstract

This paper addresses the intra frame forgery detection problem in digital video. In the intra frame forgery, a part of the region or an object from the frame is copied and pasted at other location in the same frame or group of frames from the same video. This work proposes hybrid algorithm developed using Scale Invariant Transform (SIFT) and Random Sample Consensus (RANSAC) to address the issue. While performing the experimentation, it is assumed that a small object is copied from the frame pasted in same as well as across the consecutive frames in the video sequence. Also, various image processing operations such as rotation, scaling, compression, flipping are applied on the forged region before pasting at other position to check the robustness of the algorithm. The experimental results show that the proposed method outperforms with respect to detection accuracy and simulation time. The observed average detection accuracy is 99.56% and the simulation time is 0.0921 sec. which is better than other methods reported in the literature.