Masks complicating facial recognition algorithms

Masks are making facial recognition algorithms more problematic, says a study issued by the National Institute of Standards and Technology on Monday.

The best of 89 commercial facial recognition algorithms tested had error rates between 5% and 50% in matching digitally applied face masks with photos of the same person without a mask, according to an interagency report issued by Gaithersburg, Maryland-based NIST, Ongoing Face Recognition Vendor Test (FRV) Part 6A; Face Recognition Accuracy with Face Masks Using Pre-COVID-19 Algorithms.

Mei Ngan, a NIST computer scientist and an author of the report, said in a statement, “We have begun by focusing on how an algorithm developed before the pandemic might be affected by subjects wearing face masks. Later this summer, we plan to test the accuracy of algorithms that were intentionally developed with masked faces in mind.”

The work was conducted in collaboration with Dept. of Homeland Security’s Science and Test Science and Technology Directorate, Office of Biometric Identity Management, and Customs and Border Protection, NIST said.

In May, the American Civil Liberties Union and other organizations filed suit in state court in Illinois charging a company that collects biometric data for law enforcement with violating the Illinois Biometric Privacy Act.