New Facial Recognition Technology To Identify Travelers Wearing Masks
A test for new facial recognition technology by the U.S. Department of Homeland Security (DHS) Science and Technology Directorate (S&T) has shown promising results in recognizing individuals wearing protective face masks. The technology highlights application in screening individuals at airports without the need to uncover their mouth or nose. The tests were conducted as part of S&T’s 2020 biometric technology Rally held at the Maryland Test facility. Since 2018, every year, the rally has been a host for diverse technology experts and vendors to display top biometric system systems and to staying ahead of the challenges in the use of facial recognition technology.
The test included 10 days of human testing with 60 facial recognition configurations and up to 600 diverse test volunteers from 60 countries. According to the press release published by DHS, the results were:
- Without masks, median system performance demonstrated a ~93% identification rate, with the best-performing system correctly identifying individuals ~100% of the time.
- With masks, median system performance demonstrated a ~77% identification rate, with the best-performing system correctly identifying individuals ~96% of the time.
- Performance can vary greatly between systems.
Earlier in July 2020, DHS was initially concerned that the use of a face mask might interfere with facial recognition technology.
Recommended AI News: RedSwan CRE Opens First $300 Million Tranche of Commercial Real Estate to Investors
“This isn’t a perfect 100% solution,” said Arun Vemury, director of S&T’s Biometric and Identity Technology Center, “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.” Based on these results, organizations that need to perform photo ID checks could potentially allow individuals to keep their masks on.
At present, U.S. Customs and Border Protection (CBP) uses Simplified Arrival program which uses facial recognition to verify the identity of the traveler in the U.S. It was recently expanded to airports in Las Vegas, San Francisco, and Los Angeles. Travelers can enter and exit airports with AI-based image verification, rather than presenting a travel document. The technology compares the pictures with the gallery of images provided by travelers through passport and visa photos. They can opt-out of the AI-based recognition but then have to go through the standard document inspection conducted by the CBP officials.
DHS awaits final test results from the 2020 Biometric Technology Rally in the coming weeks.
Recommended AI News: SentinelOne Releases Free SUNBURST Attack Identification Assessment Tool