Authentication of Video Evidence for Forensic Investigation: A Case of Nigeria

Video shreds of evidence are usually admissible in the court of law all\r\nover the world. However, individuals manipulate these videos to either defame\r\nor incriminate innocent people. Others indulge in video tampering to falsely\r\nescape the wrath of the law against misconducts. One way impostors can forge\r\nthese videos is through inter-frame video forgery. Thus, the integrity of such\r\nvideos is under threat. This is because these digital forgeries seriously\r\ndebase the credibility of video contents as being definite records of events. This leads to an increasing concern about the\r\ntrustworthiness of video contents. Hence, it continues to affect the social and\r\nlegal system, forensic investigations, intelligence services, and security and\r\nsurveillance systems as the case may be. The problem of inter-frame video\r\nforgery is increasingly spontaneous as more video-editing software continues to\r\nemerge. These video editing tools can easily manipulate videos without leaving\r\nobvious traces and these tampered videos become viral. Alarmingly, even the\r\nbeginner users of these editing tools can alter the contents of digital videos\r\nin a manner that renders them practically indistinguishable from the original\r\ncontent by mere observations. This paper, however, leveraged on the concept of\r\ncorrelation coefficients to produce a more elaborate and reliable inter-frame\r\nvideo detection to aid forensic investigations, especially in Nigeria. The\r\nmodel employed the use of the idea of a threshold to efficiently distinguish\r\nforged videos from authentic videos. A benchmark and locally manipulated video\r\ndatasets were used to evaluate the proposed model. Experimentally, our approach\r\nperformed better than the existing methods. The overall accuracy for all the\r\nevaluation metrics such as accuracy, recall, precision and F1-score was 100%.\r\nThe proposed method implemented in the MATLAB programming language has proven\r\nto effectively detect inter-frame forgeries.