鉴定视频的真实性和完整性是信息安全领域的重要内容之一,针对视频帧间篡改操作,提出一种基于非负张量分解的视频篡改检测方法。首先,对视频帧进行快速特征提取,利用主要压缩特征创建三维张量描述视频;然后,使用Tucker分解方法对张量进行非负分解,提取时间维因子矩阵进行相关性计算;最后,利用切比雪夫不等式自适应地定位篡改位置。实验证明,该方法能快速顽健地检测出视频帧间篡改操作。
The authenticity and integrity of video authentication is one of the important contents in information security field. A video tampering detection method based on non-negative tensor decomposition was proposed for video inter-frame tampering. First of all, spectral feature of video frame was extracted quickly. The video was described by a three-dimensional tensor which created by the main compression feature. The tensor was factorized by Tucker non-negative decomposition method and then the time dimension matrix was extracted to calculate correlation. Finally, the tampering position was determined by using the Chebyshev's inequality. Experiments show that this method can detect the video inter-frame tampering quickly and robustly.