A Forgery Video Detection Algorithm for Resolution Promotion Manipulations Using Frequency Spectrum Analysis

Resolution is one of the important factors for video visual quality. With the development of the video editing software, one video sequence can be easily enlarged and inserted into another video sequence to generate a forgery video. The detection of video resolution modifications has become an important issue for digital video authentication. In this paper, we propose a passive detection algorithm based on the zero-crossings of the high-frequency component of the key frames in frequency domain. Firstly, the key frames of video are extracted before the second-order differential is executed. Then, the zero crossings of differential are calculated to generate a one-dimensional binary sequence. Finally, the frequency analysis is applied to expose the original resolution of the video for detection. Based on this method, we also develop a forgery detection method for sequence inserting. The experimental results demonstrate that the proposed method can accurately estimate the video original resolution, as well as detect the forgery traces of synthetic videos with maliciously inserted irrelevant video sequences.