How face masks are fooling facial recognition technologies
Wearing a mask increased error rates by 5 to 50 percent among the facial recognition algorithms as per a recent study by U.S. National Institute of Standards and Technology amidst COVID penademic.
The study tested 89 commercial facial recognition algorithms which could identify people who had masks on. Researchers tested a specific method of facial recognition called “one-to-one” matching, where the software compares a photo of a person to a different photo of the same person. The algorithm works by measuring the exact distance between a person’s facial features. This is the same technique used to unlock smartphone and verify passports.
Algorithms tested about 6 million photos. The results showed that masks effectively confused the software, causing a 5 to 50 percent spike in error rate in the algorithms. Black masks led to higher error rates than blue masks. Researchers said they weren’t able to completely explore how color affected the software. Error rates were also higher when people wore wide masks
Category: Featured