20 busiest airports in the U.S. must use facial recognition technology this year
The U.S. Department of Homeland Security (DHS) recently tested facial recognition technology, which can ostensibly identify people wearing masks with high accuracy, reducing the need for people to take off masks at airports or ports of entry, thereby protecting the public and the frontline during the epidemic staff member. According to the White House, in 2021, the 20 busiest airports in the United States must use facial recognition technology to provide protection for international passengers entering and leaving the United States.
According to a press release issued this week, the US Department of Homeland Security's Science and Technology Council (S&T) conducted a pilot at a facility in Maryland as part of its third annual biometric technology rally.
Although many companies claim to have developed technologies that can identify mask wearers, such as cloth masks designed to minimize the spread of the virus, the Department of Homeland Security recommends applying it to the screening process at airports and other ports of entry. For example, the United States Customs and Border Protection (CBP) Simplified Arrival program (Simplified Arrival program) recently extended to Las Vegas, San Francisco and Los Angeles airports, the program uses facial recognition to verify the identity of air passengers arriving in the United States.
According to the press release, the live event included 10 days of human testing, including 60 facial recognition configurations, 6 camera-based face and iris recording systems, 10 matching algorithms, and 582 "different" people from 60 countries Test volunteers. The basis for evaluating each system is that it can reliably take pictures of each volunteer with and without masks and minimize the processing time.
For masks, the Department of Homeland Security stated that the median accuracy rate of all systems is 77%, and the accuracy rate of the best performing system is 96%. This is roughly in line with a report from the U.S. National Institute for Standardsand Technology last December. The report found that among more than 150 commercial facial recognition algorithms, the false match rate of the best-
