A Novel Video Inter-frame Forgery Model Detection Scheme Based on Optical Flow Consistency

In this paper, a novel video inter-frame forgery detection scheme based on optical flow consistency is proposed. It is based on the finding that inter-frame forgery will disturb the optical flow consistency. This paper noticed the subtle difference between frame insertion and deletion, and proposed different detection schemes for them. A window based rough detection method and binary searching scheme are proposed to detect frame insertion forgery. Frame-to-frame optical flows and double adaptive thresholds are applied to detect frame deletion forgery. This paper not only detects video forgery, but also identifies the forgery model. Experiments show that our scheme achieves a good performance in identifying frame insertion and deletion model.

[1]  Hany Farid,et al.  Exposing Digital Forgeries in Complex Lighting Environments , 2007, IEEE Transactions on Information Forensics and Security.

[2]  Jian Li,et al.  Double H.264/AVC compression detection using quantized nonzero AC coefficients , 2011, Electronic Imaging.

[3]  Takahiro Okabe,et al.  Detecting Video Forgeries Based on Noise Characteristics , 2009, PSIVT.

[4]  Luis Rueda,et al.  Advances in Image and Video Technology, Second Pacific Rim Symposium, PSIVT 2007, Santiago, Chile, December 17-19, 2007, Proceedings , 2007, PSIVT.

[5]  Tang Xiang-hong,et al.  Integrity authentication scheme of color video based on the fragile watermarking , 2011, 2011 International Conference on Electronics, Communications and Control (ICECC).

[6]  Weihong Wang,et al.  Exposing Digital Forgeries in Interlaced and Deinterlaced Video , 2007, IEEE Transactions on Information Forensics and Security.

[7]  Min Wu,et al.  Digital image forensics via intrinsic fingerprints , 2008, IEEE Transactions on Information Forensics and Security.

[8]  Anderson Rocha,et al.  Vision of the unseen: Current trends and challenges in digital image and video forensics , 2011, CSUR.