London Daily

Focus on the big picture.
Tuesday, Oct 21, 2025

Face masks are screwing up facial recognition software

Face masks are screwing up facial recognition software

Face masks are already known to stop the spread of coronavirus. Apparently, they can also make it much harder for facial-recognition software to identify you, too.
This is the key finding of a new report released Monday from federal researchers at the National Institute of Standards and Technology, or NIST, which is a branch of the US Commerce Department whose functions include measuring the accuracy of facial-recognition algorithms that companies and researchers submit to the lab.

When tasked with matching a picture of a person wearing a digitally added face mask to a different photo of the person without one, the most accurate facial-recognition algorithms failed to make a correct match between 5% and 50% of the time, according to the report. Generally speaking, most of the algorithms tested had failure rates of between 20% and 50%, Mei Ngan, a computer scientist at NIST and an author of the report, told CNN Business.

The identification issues make sense, as facial-recognition systems typically work by comparing measurements between different facial features in one image to those in another. Blocking off part of the face means there is less information for the software to use to make a match.

It highlights a unique challenge the tech industry is already working to confront as the pandemic continues. While the technology is controversial, with a number of companies recently rethinking providing this technology to law enforcement, it's used in a range of products and services, from using your face to unlock your smartphone to passing through a security checkpoint.

For their report, the researchers created nine different black and light blue mask shapes to account for the ways mask shapes vary in the real world and used them to hide part of a person's face in a photo. They then compared a digitally masked photo of each person with another, unmasked photo of the same person. They also conducted a test of the algorithms on both sets of photos with no virtual masks.

In all, they tested 89 algorithms on more than 6 million photos featuring a million different people. The photos came from two sources: applications for US immigration benefits, which were used as the unmasked images, and photos of travelers crossing a border to enter the US, which were given a digital mask.

NIST found that the best of these algorithms -— which were submitted to the lab before mid-March — failed just 0.3% of the time when tested on these same sets of photos without the digital masks. With the digital masks on, however, error rates climbed to 5% among these same algorithms.

An obvious shortcoming of the report is that NIST didn't test the algorithms on images of people who were actually wearing masks — Ngan said the digital approximations of masks were used due to time and resource constraints. On the plus side, it allowed researchers to quickly get a sense of the effect of masks on the algorithms, but real masks fit differently on different people. It's still unknown how texture or patterns might affect accuracy of facial recognition software.

"That's something we want to look at," Ngan said.

Some companies have said their facial-recognition technology can work with masks, and Ngan said she's heard from developers who are working on algorithms meant to make this possible — perhaps by training an algorithm with lots of images of people wearing actual masks, or by targeting the region of the face above the middle of the nose.

That's a focus for Marios Savvides, a professor at Carnegie Mellon University who studies biometric identification. He said a person who's wearing a mask can be essentially invisible to a facial-recognition system, as it doesn't even detect a face in the first place. He thinks the region of the face that includes the eyes and eyebrows tends to change the least over time, which makes it a good part of the face to use when trying to identify a person whose mouth and nose are hidden.

The NIST report is the first of several that the lab plans to issue about how facial-recognition algorithms identify masked faces. In the fall, Ngan said, NIST expects to release a report on the accuracy of algorithms that were specifically created with the intention of spotting people in masks.
Newsletter

Related Articles

0:00
0:00
Close
This Is How the 'Heist of the Century' Was Carried Out at the Louvre in Seven Minutes: France Humiliated as Crown with 2,000 Diamonds Vanishes
China Warns UK of ‘Consequences’ After Delay to London Embassy Approval
France’s Wealthy Shift Billions to Luxembourg and Switzerland Amid Tax and Political Turmoil
"Sniper Position": Observation Post Targeting 'Air Force One' Found Before Trump’s Arrival in Florida
Shouting Match at the White House: 'Trump Cursed, Threw Maps, and Told Zelensky – "Putin Will Destroy You"'
Windows’ Own ‘Siri’ Has Arrived: You Can Now Talk to Your Computer
Thailand and Singapore Investigate Cambodian-Based Prince Group as U.S. and U.K. Sanctions Unfold
‘No Kings’ Protests Inflate Numbers — But History Shows Nations Collapse Without Strong Executive Power
Chinese Tech Giants Halt Stablecoin Launches After Beijing’s Regulatory Intervention
Manhattan Jury Holds BNP Paribas Liable for Enabling Sudanese Government Abuses
Trump Orders Immediate Release of Former Congressman George Santos After Commuting Prison Sentence
S&P Downgrades France’s Credit Rating, Citing Soaring Debt and Political Instability
Ofcom Rules BBC’s Gaza Documentary ‘Materially Misleading’ Over Narrator’s Hamas Ties
Diane Keaton’s Cause of Death Revealed as Pneumonia, Family Confirms
Former Lostprophets Frontman Ian Watkins Stabbed to Death in British Prison
"The Tsunami Is Coming, and It’s Massive": The World’s Richest Man Unveils a New AI Vision
Outsider, Heroine, Trailblazer: Diane Keaton Was Always a Little Strange — and Forever One of a Kind
Dramatic Development in the Death of 'Mango' Founder: Billionaire's Son Suspected of Murder
Two Years of Darkness: The Harrowing Testimonies of Israeli Hostages Emerging From Gaza Captivity
EU Moves to Use Frozen Russian Assets to Buy U.S. Weapons for Ukraine
Europe Emerges as the Biggest Casualty in U.S.-China Rare Earth Rivalry
HSBC Confronts Strategic Crossroads as NAB Seeks Only Retail Arm in Australia Exit
U.S. Chamber Sues Trump Over $100,000 H-1B Visa Fee
Shenzhen Expo Spotlights China’s Quantum Step in Semiconductor Self-Reliance
China Accelerates to the Forefront in Global Nuclear Fusion Race
Yachts, Private Jets, and a Picasso Painting: Exposed as 'One of the Largest Frauds in History'
Australia’s Wedgetail Spies Aid NATO Response as Russian MiGs Breach Estonian Airspace
McGowan Urges Chalmers to Cut Spending Over Tax Hike to Close $20 Billion Budget Gap
Victoria Orders Review of Transgender Prison Placement Amid Safety Concerns for Female Inmates
U.S. Treasury Mobilises New $20 Billion Debt Facility to Stabilise Argentina
French Business Leaders Decry Budget as Macron’s Pro-Enterprise Promise Undermined
Trump Claims Modi Pledged India Would End Russian Oil Imports Amid U.S. Tariff Pressure
Surging AI Startup Valuations Fuel Bubble Concerns Among Top Investors
Australian Punter Archie Wilson Tears Up During Nebraska Press Conference, Sparking Conversation on Male Vulnerability
Australia Confirms U.S. Access to Upgraded Submarine Shipyard Under AUKUS Deal
“Firepower” Promised for Ukraine as NATO Ministers Meet — But U.S. Tomahawks Remain Undecided
Brands Confront New Dilemma as Extremists Adopt Fashion Labels
The Sydney Sweeney and Jeans Storm: “The Outcome Surpassed Our Wildest Dreams”
Erika Kirk Delivers Moving Tribute at White House as Trump Awards Charlie Presidential Medal of Freedom
British Food Influencer ‘Big John’ Detained in Australia After Visa Dispute
ScamBodia: The Chinese Fraud Empire Shielded by Cambodia’s Ruling Elite
French PM Suspends Macron’s Pension Reform Until After 2027 in Bid to Stabilize Government
Orange, Bouygues and Free Make €17 Billion Bid for Drahi’s Altice France Telecom Assets
Dutch Government Seizes Chipmaker After U.S. Presses for Removal of Chinese CEO
Bessent Accuses China of Dragging Down Global Economy Amid New Trade Curbs
U.S. Revokes Visas of Foreign Nationals Who ‘Celebrated’ Charlie Kirk’s Assassination
AI and Cybersecurity at Forefront as GITEX Global 2025 Kicks Off in Dubai
DJI Loses Appeal to Remove Pentagon’s ‘Chinese Military Company’ Label
EU Deploys New Biometric Entry/Exit System: What Non-EU Travelers Must Know
Australian Prime Minister’s Private Number Exposed Through AI Contact Scraper
×