Temporal Copy-Move Forgery Detection and Localization Using Block Correlation Matrix

One of the drawbacks of the current revolution on media is that tampering with images and videos is an increasingly easy task which brings a situation where digital media cannot be trusted. Digital video forensics study the effects of attacks and tampering techniques on videos and has arisen as a solution to the problem of lack of trustworthiness on digital media. Copy-Move tampering is one of the most common attacks, with variants for delete and duplicate objects in videos, and has been studied in several video forensics works with different approaches. Despite that, there is not yet a simple method to determine multiple variants of Copy-Move attacks. This work proposes a simple yet effective method do detect Copy-Move for both subregion and full-frame duplication.