Passive copy-move forgery detection in videos

Due to evolution of prevalent sophisticated digital video editing software it has become easier to forge any video. Copy-Move forgery is a special kind of video forgery technique, in which copy-move of the frame region is performed in intra frame or inter frames. This copy-move introduces a special kind of relationship between the original frame segment and the pasted one, which provides clue for copy-move forgery detection (CMFD). In this paper a passive forensic scheme has been considered for CMFD in spatial and temporal domain of video. For detecting copy-move forgery in spatial domain, Scale Invariant Features Transform (SIFT) is proposed. Noise residue and Correlation technique have been proposed for temporal copy-move forgery detection. Copy-Move forgery detection using SIFT features show robust result in comparison to other features because SIFT features are immune to various type of transformation like scaling, translation, rotation etc. Experimental results show that our technique successfully detect spatial and temporal copy-move forgery in the video.