LAUSR

Digital videos are an incredibly important source of information, and as evidence, they are highly inculpatory. Digital videos are also inherently prone to conscious semantic manipulations, such as copy–paste forgeries, which involve insertion or removal of objects into or from a set of frames. Such forgeries involve direct manipulation of the information presented by a video scene, thus having an immediate effect on the meaning conveyed by that scene. Given the highly influential nature of video data and the fact that they are easy to manipulate, it becomes important to devise measures that can help ascertain their integrity and authenticity, so that we can be certain of their ability to serve as reliable evidence. The challenge of detecting copy–paste forgeries in digital videos has been at the receiving end of much innovation over the last decade, and as a result, the available literature in this domain has grown to considerable proportions. However, thorough analysis of this literature appears to show that the task of detecting such forgeries necessitates the use of elaborate and operationally restrictive procedures, and somehow cannot be accomplished via a relatively simpler process, whose method of operation imposes little to no restrictions on its scope of applicability. With the aim of quashing this notion, in this paper, we present two simple forensic solutions that can enable an analyst to detect copy–paste forgeries quickly and effectively, without having to resort to any complicated analyses or relying on unrealistic presumptions. These solutions are based on optical flow inconsistency analysis and pattern noise abnormality analysis , and have been validated on a substantial set of realistically tampered test videos in a diverse experimental set-up, which is representative of a neutral testing platform and simulates a real-world heterogeneous forensic environment, where the analyst has no control over any of the variable parameters of the video creation or manipulation process. When tested in such an experimental set-up, the proposed solutions achieved an average accuracy rate of 98% and demonstrated attributes desired of an efficacious and practical forensic solution, all the while validating our initial hypothesis that not only can the task of copy–paste detection be accomplished in a fast and uncomplicated manner, but also that in an actual forgery scenario, the less onerous a forensic solution is, the more likely it is to succeed.