Video inter-frame forgery identification based on the consistency of quotient of MSSIM

Inter-frame forgery is a common type of video forgery in digital videos. In this paper, a method based on the consistency of quotient of mean structural similarity QoMSSIM is proposed. For original videos, the QoMSSIM are consistent, but in forgeries the consistency will be destroyed. First, the mean structural similarity MSSIM between every two adjacent frames is extracted, and then the quotients between every two sequential MSSIM are calculated. Finally, the quotient of mean SSIM after post-processing, normalization and quantization is used as distinguishing feature to identify inter-frame forgeries. Experiments are conducted on a large database and support vector machine SVM is used to distinguish original videos and inter-frame forgeries. Experimental results show that the proposed method is efficient in differentiating original videos and forgeries. For differentiating frame deletion and insertion forgeries, the proposed method performs also pretty well. Compared with the other method, the proposed method has higher classification accuracy, lower computational complexity and robustness against recompression and white Gaussian noise. Copyright © 2016 John Wiley & Sons, Ltd.