If you’ve seen the videos posted by terrorists, many of them tend to hide behind masks and cover themselves up pretty heavily in order to prevent themselves from being identified. Some, like Jihadi John, have become more identifiable through his accent and actions, but unless they frequently make an appearance on video, it might be hard to say who’s who.
However researchers have recently discovered a way that might help them identify terrorists in videos. This is thanks to Ahmad Hassanat at Mu’tah University in Jordan and his fellow researchers who are using machine learning to help identify terrorists based on the ‘V’ signs that they make in videos.
Apparently different people create ‘V’ signs differently, and the researchers claim that they are able to point out who is who based on finger size and the angle between fingers. While it won’t unmasks the terrorists, at least it will provide information as to whether or not the terrorist appears in videos frequently.
So far their technique has yielded 90% accuracy, but unfortunately their data set is pretty small so as to how effective it will be in the field remains to be seen. However the researchers claim, “There is a great potential for this approach to be used for the purpose of identifying terrorists, if the victory sign were the only identifying evidence.”
Filed in AI (Artificial Intelligence).. Read more about