Biometric recognition has become more prevalent in recent years. Facial recognition technology is used everywhere, from check-in lines at airports to police departments and even nightclubs, while iris, fingerprint and voice recognition are used in a variety of sectors to security purposes.
But researchers at the University of New South Wales, Australia, say that some biometric methods have “well-known weaknesses”.
Fingerprints can be collected from a surface that someone has touched and duplicated to create a simulated impression, facial recognition technology can be bypassed using images collected on social networks, and contact lenses can be used to confuse iris-based mechanisms, Syed Shah, a researcher at the School of Computer Science and Engineering at the University of New South Wales, told CNN.
“The vein patterns are under the skin, therefore, they do not leave any marks, unlike fingerprints, they are not available on social networks, unlike facial photos, and cannot be obtained clandestinely, unlike irises,” he said Shah to CNN via email. “Therefore, we believe that a vein-based approach will be much more difficult to get around.”
Using a shelf-depth camera – an Intel RealSense D415 depth camera – the researchers took about 17,500 images from 35 people, where participants clenched their fists and set the patterns in the veins in the hand.
Using artificial intelligence, the researchers extracted “discriminatory characteristics” from these patterns – these, they say, could then be used to identify an individual with more than 99% accuracy in a group of 35 participants.
“Especially, the requirement to make (a) fist for vein extraction makes it difficult for an opponent to sneak vein patterns,” explained Shah.
Shah told CNN that while the idea of using veins to identify people is not new, it usually requires specialized technology – but his team’s research uses ready-made 3D cameras.