While wearing a mask can protect users from COVID-19, promising new research shows it doesn't prevent you from being recognized.

In a grand display of growing technological capabilities, the Department of Homeland Security’s Biometric and Identity Technology Center unveiled new data on the effectiveness of facial recognition software in identifying people wearing masks and other facial coverings. These developments are poised to change the way facial recognition functions in society.

“Through careful selection of camera systems and matching systems, it appears possible to verify the identity of most people without requiring them to remove their masks,” Arun Vemury, director of the Biometric and Identity Technology Center, said in a press release. “This is not a 100% perfect solution, but it could reduce risks for many travelers, as well as for the frontline staff working in airports who no longer need to ask travelers to remove their masks.”

At its best, the new technology was able to identify 96% of masked airline users, with a median accuracy of 77%. By comparison, maskless users were correctly identified 100% of the time, with a median of 94%. Both sets evaluated 60 combinations in DHS’s test lab, using a variety of camera angles and 10 matching algorithms. The test included a diverse group of 582 people from 60 countries, in hopes of ensuring that the technology could identify underrepresented ethnic and racial populations.