Researchers Develop Software That Identifies Terrorists Through 'V' Hand Gestures

Terrorists with masks have been seen to gesture the "V" sign with their hands, discovered Ahmad Hassanat and his team at Mu'tah University in Jordan. Experts have identified the sign using an artificial intelligence (AI) algorithm, along with biometrics.

new technique method discovers the "V" signs used by terrorists who pose for photographs.

"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 terrorist videos," the researchers wrote.

Biometrics employ human characteristics, used in multiple technologies, that include voice recognition, fingerprint scanning and facial recognition on the social media. The research currently looked at the "geometry of the human" and how they can show the identities of people.

Scientists used a sample of 50 men and women, shooting each person's hand a number of times and using 500 images to create a database.

An AI algorithm then analyzed each hand, examining the endpoints of both fingers that flashed the "V". It also studied the valley between the fingers and two points on the palm.

The information in the study is not too much, and using the methods in this with other data, the team could achieve an accuracy of more than 90 percent, which could be improved with more research and metrics.

However, the task of recognizing people using just a section of their hands was much harder. "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," say Ahmad Hassanat at Mu'tah University in Jordan.

The findings were released on Feb. 26, 2016 on the airXiv server.