GOP Based Automatic Detection of Object-based Forgery in Advanced Video

Abstract— Passive multimedia forensics has become an active topic in recent years. However, the research on video forensics, and especially on automatic detection of object-based video forgery is still in its infancy. In this paper, we develop an approach for automatic identification of object-based forged video encoded with advanced frameworks based on its GOP (Group Of Pictures) structure. The proposed approach contains two specific frame manipulation detectors for three categories of frames. GOP structures are used in the proposed approach to determine the sampling interval when extracting I frames or P/B frames in the training and testing procedure. In the construction of the frame manipulation detector, motion residuals are generated from the target video frame sequence. We regard the object-based forgery in video frames as image tampering in the motion residuals, and employ the feature extractors which are originally built for frequency domain image steg analysis to extract forensic features from the motion residuals. The experiments show that the proposed approach achieves excellent results. With the wide availability of powerful media editing tools, it becomes much easier to tamper digital media without leaving any perceptible traces. This leads to an increasing concern about the trustworthiness of digital media contents and there is a pressing need to develop effective forensic techniques to verify the authenticity, originality, and integrity of media contents < final year projects >