Publication

Abstract : The videos produced as evidences in courts, science and business are exceedingly confidential and even a simple amendment done in these videos will have a greater impact on our civilization. To ensure the genuineness of such videos, better methods are needed. In this paper we propose a technique to find inter-frame duplications (a video is tampered by adding frames from different videos) which includes two phases. Phase1 extract the key frames from the given input video and thus reduces the computation time compared to frame by frame comparisons, followed by phase2 which uses spatial Correlation and optical flow algorithm to detect the forgery from the key frames. The experimental results show our algorithm detects forgery efficiently beneath the following circumstances such as: Inserting Duplicate frames at random positions, Inserting duplicate frames throughout the video except the first frame and Inserting only one duplicate frame in the entire video.