Preliminary test results of the third Biometric Technology Rally held by the Department of Homeland Security’s (DHS) science and technology (S&T) directorate in the fall of 2020 showed that biometric acquisition tools and matching algorithms were up to 96 percent accurate in identifying individuals with protective face masks.
The S&T directorate tested 60 facial recognition systems with 582 test volunteers during the 10-day testing period to evaluate the technologies’ ability to capture images of people with or without wearing masks, volunteer satisfaction and processing time.
Matching algorithms and biometric acquisition systems showed an identification rate of 77 percent as their median system performance for recognizing individuals who are wearing masks.
“This isn’t a perfect 100% solution 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,” said Arun Vemury, director of S&T directorate’s Biometric and Identity Technology Center.
The directorate said it expects to release the 2020 Biometric Technology Rally’s final test results in the next few weeks.
