Detection of deleted frames on videos using a 3D Convolutional Neural Network

Digital video forgery or manipulation is a modification of the digital video for fabrication, which includes frame sequence manipulations such as deleting, insertion and swapping. In this paper, we focus on the detection problem of deleted frames in videos. Frame dropping is a type of video manipulation where consecutive frames are deleted to skip content from the original video. The automatic detection of deleted frames is a challenging task in digital video forensics. This paper describes an approach using the spatial-temporal procedure based on the statistical analysis and the convolutional neural network. We calculate the set of different statistical rules for all frames as confidence scores. Also, the convolutional neural network used to obtain the output scores. The position of deleted frames determines based on the two score curves for per frame clip. Experimental results demonstrate the effectiveness of the proposed approach on a test video database.