Biometric recognition has become more common in recent years. Face 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 for security purposes in various sectors.
But researchers at the Australian University of New South Wales say some biometric methods have ‘known weaknesses’.
Fingerprints can be collected from a surface that someone has touched and duplicated to create a dummy print. Face recognition technology can be bypassed using images from social media, and contact lenses can be used to confuse iris-based mechanisms, Syed Shah, a researcher at The University of New South Wales’ School of Computer Science and Engineering, told CNN said.
“Venous patterns lie under the skin and therefore leave no imprint, unlike fingerprints, it is not available on social media, other than facial photographs, and can not be obtained in secret unlike irises,” Shah said in ‘ an email to CNN said. “That is why we believe that an air-based approach can be bypassed much more difficult.”
Using a shelf depth camera – an Intel RealSense D415 depth camera – researchers took approximately 17,500 images of 35 people, where participants fisted and determined the vein patterns by hand.
Using artificial intelligence, researchers extracted ‘discriminatory characteristics’ from these patterns – according to them, they could be used to identify an individual with more than 99% accuracy from a group of 35 participants.
“Specifically, the requirement to make a fist for vein extraction makes it difficult for an adversary to obtain vein patterns quickly,” Shah explained.
Shah told CNN that while the idea of using veins to identify people is not new, it usually requires specialist technology – but his team’s research uses off-the-shelf 3D cameras.