Detecting tampered region in video using LSTM and U‐Net
Kunihiko Taya, Nobutaka Kuroki, Naoto Takeda, Tetsuya Hirose, Masahiro Numa · Electronics and Communications in Japan · 2020
Abstract In the world today, we can always shoot digital videos with smartphones and share them with family or friends after editing them. It is necessary to check whether these videos have been tampered with to use them as forensic evidence in criminal investigations. This paper proposes a method for detecting tampered regions in a video where a specific subject is removed from a scene. In the proposed method, we use LSTM for the time domain analysis and UNet for the space domain analysis. The detection accuracy achieved 0.98 in terms of F‐measure, even though tampered the region was deformed or moved in the video. The experimental results show superior performance in the detection of tampered regions in digital videos.