A NOVEL APPROACH FOR USIND MACHINE LEARNING FORENSIC SCANNER IDENTIFICATION

Abstract

In this paper, we review recent work in media forensics for digital images, video, audio, and documents. The proposed system uses deep-learning to automatically learn the intrinsic features from various scanned images. Our experimental results show that high accuracy can be achieved for source scanner identification. The proposed system can also generate a reliability map that indicates the manipulated regions in an scanned image. This study is the first to extract brightness variations as a unique characteristic of each scanner model and recognize the potential of brightness variations in source identification and manipulation detection