Face Masks Are Breaking Facial Recognition Algorithms, Says New Government Study
By News
Published 4 years ago on
July 30, 2020
Share
[aggregation-styles]
The Verge
Face masks are one of the best defenses against the spread of COVID-19, but their growing adoption is having a second, unintended effect: breaking facial recognition algorithms.
Wearing face masks that adequately cover the mouth and nose causes the error rate of some of the most widely used facial recognition algorithms to spike to between 5 percent and 50 percent, a study by the US National Institute of Standards and Technology (NIST) has found. Black masks were more likely to cause errors than blue masks, and the more of the nose covered by the mask, the harder the algorithms found it to identify the face.
“With the arrival of the pandemic, we need to understand how face recognition technology deals with masked faces,” said Mei Ngan, an author of the report and NIST computer scientist. “We have begun by focusing on how an algorithm developed before the pandemic might be affected by subjects wearing face masks. Later this summer, we plan to test the accuracy of algorithms that were intentionally developed with masked faces in mind.”
Read More →
The Verge
Face masks are one of the best defenses against the spread of COVID-19, but their growing adoption is having a second, unintended effect: breaking facial recognition algorithms.
Wearing face masks that adequately cover the mouth and nose causes the error rate of some of the most widely used facial recognition algorithms to spike to between 5 percent and 50 percent, a study by the US National Institute of Standards and Technology (NIST) has found. Black masks were more likely to cause errors than blue masks, and the more of the nose covered by the mask, the harder the algorithms found it to identify the face.
“With the arrival of the pandemic, we need to understand how face recognition technology deals with masked faces,” said Mei Ngan, an author of the report and NIST computer scientist. “We have begun by focusing on how an algorithm developed before the pandemic might be affected by subjects wearing face masks. Later this summer, we plan to test the accuracy of algorithms that were intentionally developed with masked faces in mind.”
Read More →
By James Vincent | 28 July 2020
RELATED TOPICS:
California Leaders Take Sides in Monumental Supreme Court Case on Homelessness
Housing /
52 mins ago
Man Sets Himself on Fire Outside Trump Hush Money Trial Court
U.S. /
13 hours ago
Real Estate Experts Talk Fresno’s Economic Future. Are Tough Times Ahead?
Economy /
14 hours ago
Unlocking the Secrets to Fresno State’s Superb Baseball Season
Sports /
15 hours ago
Get a 3D First Look at Merced’s High-Speed Rail Station Design
Events /
17 hours ago
California Court to Decide on Transgender Ballot Measure Wording
Politics /
17 hours ago
Rare House Vote Sees Ukraine, Israel Aid Advance as Democrats Join Republicans
Politics /
18 hours ago
The Pickle Flavor Frenzy and Its Rise in Food Trends
You might have noticed that the tangy taste of pickles has taken over more than just the condiment aisle. From pickle-flavored popcorn to pi...
Food /
22 mins ago
Categories
Latest
Videos
Food /
22 mins ago
The Pickle Flavor Frenzy and Its Rise in Food Trends
Housing /
52 mins ago
California Leaders Take Sides in Monumental Supreme Court Case on Homelessness
U.S. /
13 hours ago
Man Sets Himself on Fire Outside Trump Hush Money Trial Court
Economy /
14 hours ago
Real Estate Experts Talk Fresno’s Economic Future. Are Tough Times Ahead?
Sports /
15 hours ago
Unlocking the Secrets to Fresno State’s Superb Baseball Season
Economy /
2 days ago