Researchers looking to identify terrorists based on hand geometry
Researchers at Mu’tah University in Jordan are using an artificial intelligence algorithm and biometrics to identify a person using hand geometry and more specifically, the “V” signs terrorists sometimes make when posing for photos or videos.
In an MIT Technology Review report, researcher Ahmad Hassanat and his team said: “Identifying a person using a small part of the hand is a challenging task, and has, to the best of our knowledge, never been investigated.”
According to the study’s abstract: “Sometimes the only evidence to identify a person is their hand geometry, and not the whole hand — only two fingers (the index and the middle fingers) while showing the victory sign, as seen in many terrorists videos.”
The researchers had 50 men and women of varying ages make a V sign with their right hand and photographed it several times against a black background with an eight-megapixel camera phone, producing a database of 500 images. The AI algorithm focused on an analysis of different points of the hands: the endpoints of the two fingers, the lowest point of the valley in between them and then two points in the palm. They reported the method had an accuracy of over 90 percent in some cases.
The data set is small, for now, and hand geometry is only one piece of someone’s identity, but Hassanat told MIT that they are hoping to add even more metrics, such as finger width and length, to help bolster the method’s accuracy.