Digital Video Inpainting Detection Using Correlation Of Hessian Matrix

Abstract

The use of digital video during forensic investigation helps in providing evidence related to crime scene. However, due to freely available user friendly video editing tools, the forgery of acquired digital videos that are used as evidence in a law suit is now simpler and faster. As a result, it has become easier for manipulators to alter the contents of digital evidence. For instance, inpainting technique is used to remove an object from a video without leaving any artefact of illegal tampering. Therefore, this paper presents a technique for detecting and locating inpainting forgery in a video sequence with static camera motion. Our technique exploits statistical correlation of Hessian matrix (SCHM) to detect and locate tampered regions within a video sequence. The results of our experiments prove that the technique effectively detect and locate areas which are tampered using both texture and structure based inpainting with an average precision rate of 99.79% and an average false positive rate of 0.29%.