Coarse-to-Fine Copy-Move Forgery Detection for Video Forensics

Video copy-move forgery detection is one of the hot topics in multimedia forensics to protect digital videos from malicious use. Several approaches have been presented through analyzing the side effect caused by copy-move operation. However, based on multiple similarity calculations or unstable image features, a few can well balance the detection efficiency, robustness, and applicability. In this paper, we propose a novel approach to detect frame copy-move forgeries in consideration of the three requirements. A coarse-to-fine detection strategy based on optical flow (OF) and stable parameters is designed. Specifically, coarse detection analyzes OF sum consistency to find suspected tampered points. Fine detection is then conducted for precise location of forgery, including duplicated frame pairs matching based on OF correlation and validation checks to further reduce the false detections. Experimental evaluation on three public video data sets shows that the proposed approach is effective and efficient in detecting both unsmooth manipulation and common smooth forgery and also with high robustness to regular attacks, including additive noise, filtering, and compression.