DHS conducts tests that show facial recognition technologies could work with masks

Tests conducted by the Department of Homeland Security (DHS) Science and Technology Directorate (S&T) showed promising results that facial recognition technologies can accurately identify individuals wearing protective face masks.

The tests were conducted as part of S&T’s 2020 Biometric Technology Rally, held this fall at the Maryland Test Facility. The findings could reduce the need for people to remove masks at airports or ports of entry.

The tests were done on 582 diverse volunteers from 60 countries using 60 facial recognition configurations. Several different technologies and systems were tested, with performance varying greatly between systems. But overall, the results showed that without masks, median system performance demonstrated a 93 percent identification rate, with the best-performing system correctly identifying people 100 percent of the time.

With masks, the median system performance demonstrated a 77 percent identification rate, with the best-performing system correctly identifying people 96 percent of the time.

“This isn’t a perfect 100% solution,” Arun Vemury, director of S&T’s Biometric and Identity Technology Center, said. “But it may reduce risks for many travelers, as well as the frontline staff working in airports, who no longer have to ask all travelers to remove masks.”

The final test results from the 2020 Biometric Technology Rally are anticipated in the coming weeks.