COPY MOVE FORGERY DETECTION IN VIDEO FORENSICS USING OPTICAL FLOW FOR COARSE TO FINE DETECTION

Video copy-move forgery detection is used in multimedia forensics to protect digital videos from malicious use. Based on multiple similarity calculations and unstable image features the detection efficiency, robustness and applicability can be balanced. A novel approach has been proposed to detect frame copy-move forgeries. A coarse-to-fine detection strategy based on optical flow and stable parameters is designed. Coarse detection analyzes OF sum consistency to find suspected tampered points. Fine detection is then conducted for precise location of forgery, including duplicated frames pair matching based on OF correlation and validation checks to further reduce the false detections. The proposed approach is effective and efficient in detecting both unsmooth and common smooth forgery. Also it has high robustness. Keywords—Copy-move forgery, optical flow, coarse–to-fine detection, video passive forensics.