A Convolutional Neural Network Ensemble for Video Source Camera Forensics

The advancement of Internet of Things technologies has influenced a substantial increase in the use of multimedia devices. Consequently, forensic specialists have begun to experience a vast load of video and image data during investigative procedures. This has triggered a need to ensure the integrity of multimedia data and verify its source origin for digital forensics processes. In this article, we address the problem of identifying the video source camera of the video data acquired by investigators. We develop a novel convolutional neural network (CNN) ensemble framework to identify the video source camera. In our method, we analyze the video data using patches extracted from intracoded frame (I-frame) quadrants (i.e., nonoverlapping squares) using independent CNNs for each quadrant to achieve location awareness. Experimental results demonstrate that our framework is robust for the same device-type classification and outperforms existing deep learning-based techniques.