Exposing Digital Video Forgery By Ghost Shadow Artifact

With the wide-spread availability of sophisticated and low-cost digital video cameras and the prevalence of video sharing websites, digital videos are playing a more important role in our daily life. But the fact that all kinds of videos are easily tampered has seriously reduced the public confidence in videos. So it is importmant to ensure the integrity and authenticity of the digital videos both for important academic significance and practical values.The thesis focuses and studies on digital video forensics, which is a new technology used to judge the videos whether they are inpainted or not according to the video data. The present situation of digital video forensics is discussed and tampered methods and tools are introduced, and then a novel approach is proposed for detecting video forgery based on exposing ghost shadow artifact. When tampering video by removing the moving object, it is necessary to complete the forged region by video inpainting. But video inpainting usually cannot ensure the consistence and continuity of the motion trace. Thus the ghost shadow artifact is introduced in the forged video. In our approach, the track of moving foreground is obtained by accumulative differences and the moving foreground mosaic is built by block matching. If the moving track and the foreground mosaic are inconsistent, the input video is judged as forged video with ghost shadow artifact. Otherwise, it is judged as authentic video. Experiments show that our approach can accurately detect the forgery in the video, and it's robust to the lossy compression.Digital video forensics is a challenging question, and it's significant in theories and applications. In this thesis, data analysis, theory deduction and computer simulation methods are utilized for studying. The simulation tools include matlab 7.6.0, VC++, and so on.