A preliminary study by the U.S. National Institute of Standards and Technology shows 89 facial recognition algorithms had some degree of inaccuracy while identifying people wearing face masks. Research showed the algorithms were anywhere between 5% and 50% inaccurate in matching digitally applied face masks with photos of the same person without a mask. "With respect to accuracy with face masks, we expect the technology to continue to improve," NIST Computer Scientist Mei Ngan said, adding that users should know any algorithm "thoroughly" before deployment.
Full Story