Detection of Copy-Paste Forgery in CCTV Footages

Abstract: Video forgery detection aims at checking the authenticity of videos by recovering information about their history. Copy-paste forgery is done by replacing a region from a video with another region from the same video. By copying a part from the same video , its important properties, such as noise, colour palette and texture, will be fit with the rest of the video and thus will be more difficult to distinguish and detect these parts. In this paper DWT (Discrete Wavelet Transform) is used to compress the frame and optical flow technique is used to detect the flow of the moving objects and the forgery object. But the SIFT (Smart Information Flow Technology) is used to detect the key features of the original frame and the forgery frame. OpenCV is used for image processing.

Keywords: Copy Paste forgery Detection in videos, Optical flow, ROI masking, DWT, SIFT.