Screening Masked Faces At Airports: 96 Percent Accuracy

Courtesy/National Institute of Standards and Technology (NIST)

HSNW News:

A controlled scenario test by the DHS S&T shows promising results for facial recognition technologies to accurately identify individuals wearing protective face masks.

A controlled scenario test by the Department of Homeland Security (DHS) Science and Technology Directorate (S&T) shows promising results for facial recognition technologies to 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, and could reduce the need for people to remove masks at airports or ports of entry.

The third annual rally evaluated the ability of biometric acquisition systems and matching algorithms to reliably collect and match images of individuals wearing a diverse array of face masks.

Previous rallies show biometric systems can excel at rapidly processing high volumes of travelers using face recognition. This year’s focused on using such systems to detect and recognize travelers without asking them to remove their masks, thereby protecting both the public and frontline workers during the COVID-19 era.

The in-person event included 10 days of human testing with 60 facial recognition configurations (using six face and/or iris acquisition systems and 10 matching algorithms) and 582 diverse test volunteers representing 60 countries. Acquisition systems were evaluated based on their ability to reliably take images of each volunteer with and without masks, volunteer processing time, and overall volunteer satisfaction.

Early results, released today on the Biometric Rally website, indicate:

  • 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.

Based on these results, organizations that need to perform photo ID checks could potentially allow individuals to keep their masks on, thereby reducing the risk of COVID-19 infection.

“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.”

Final test results from the 2020 Biometric Technology Rally are anticipated in the coming weeks. To learn more about S&T’s research into facial recognition, you may read our feature article, Identity Verification During the Age of COVID-19.

Source: Homeland Security News Wire

CSTsiteisloaded