How Facial Recognition Is Learning to Read Masked Faces

Key Takeaways

  • Facial recognition algorithms are getting better at reading faces with masks on.
  • A new study showcases limitations to how an algorithm can read a face mask, such as the mask’s color and shape.
  • Experts say the facial recognition industry is actively working to include face masks in their algorithms.

reklamlar / Getty Images

Many industries have needed to adjust to the pandemic, including the facial recognition industry. Experts say the technology is slowly getting better at recognizing people wearing face masks.

A new report published by the National Institute of Standards and Technology (NIST) shows the results of 65 new facial recognition algorithms created after the start of the COVID-19 pandemic, as well as 87 algorithms submitted pre-pandemic. The report revealed that software developers are getting better at developing algorithms that recognize masked faces, even getting as accurate as regular facial recognition algorithms. 

“While a few pre-pandemic algorithms still remain within the most accurate on masked photos, some developers have submitted algorithms after the pandemic showing significantly improved accuracy and are now among the most accurate in our test,” the report reads.

What the Study Found

The study was the second of its kind conducted by NIST with the same dataset meant to test facial recognition algorithms and their accuracy in the presence of face masks. The report’s authors used 6.2 million photos and applied simulations of various digital mask combinations to these images. 

Mei Ngan, a co-author of the report and computer scientist at NIST, told Lifewire in a phone interview that the presence of face masks has essentially taken facial recognition technology back about two to three years.

“Error rates are anywhere between 2.5% and 5%—comparable to where the state-of-the-art technology was in 2017,” she said.

A previous report from NIST published in July looked at the performance of facial recognition algorithms submitted before March 2020, prior to the World Health Organization declaring a global pandemic. This first study found the error rate of these pre-pandemic algorithms to be between 5% and 50%.

LeoPatrizi / Getty Images

Even if these algorithms are getting better at reading masked faces, the more recent study found that some factors affect the error rate, such as mask color (darker masks like red or black have higher error rates) and how the mask is shaped (rounder mask shapes have lower error rates). 

Ngan said the algorithms use the visible part of someone’s face, such as the region around the eyes and the forehead, to recognize facial features rather than read through the mask itself. 

The Future of Facial Recognition and Face Masks

Ngan said it’s obvious developers have made significant improvements with their facial recognition algorithms when it comes to face masks. 

“There is clearly a need for facial recognition systems to operate under the constraints of wearing face masks,” she said. “Given the stuff we’ve been doing and the outcomes from our recent study, we are seeing the facial recognition industry is actively working to include face masks in their algorithms.” 

Since the technology is improving, that means it’ll be easier to do things like unlock our phones while wearing a face mask, but there are other implications when it comes to facial recognition advancing in this way. 

Morsa Images / Getty Images

Numerous studies show that facial recognition is widely reported to misidentify the wrong person and have racial biases. A 2019 study by the NIST found that facial recognition technology misidentifies Black and Asian people up to 100 times more often than white people.

Even if the technology is getting better at reading face masks, the error percentage—no matter how small—could still be a concern for misidentifying a person wearing a face mask.

While the most recent NIST report shows that algorithms are getting better at handling the face mask task, Ngan said only time will tell if this really is where the future of facial recognition is going during pandemic times.

“Maybe we can expect further error reductions, or maybe developers might find limitations to the amount of unique information in the unmasked region,” Ngan said.

Leave a Reply

Your email address will not be published. Required fields are marked *



What’s Next for the Mac in 2021?

Key Takeaways Apple plans to switch all its Macs to Apple Silicon chips within two years. The current iMac is due for an update—its design dates back to 2008. This year’s Pro Macs may get a hot-rodded version of the M1 chip. Apple With new chips, a new iMac, and new laptops, 2021 might be […]

Read More

Will CES 2021 Be the Battleground for New Computer Chips?

Key Takeaways Apple’s successful introduction of its custom, in-house Apple Silicon will challenge the fragmented PC market. The battle between Intel and AMD is intensifying, with AMD Ryzen processors coming to many mainstream laptops. Consumers buying a Windows laptop in 2021 will have the most choice in over two decades. Jeremy Laukkonen / Lifewire Apple […]

Read More

Dell’s New Monitors Are Made for Remote Work

Key Takeaways Dell’s new monitors have a button just to launch Microsoft Teams. They also feature a built-in camera, speakers, and microphone, and blue-light reduction. In the future, office tech might be more home-office friendly. Dell Dell’s just to launch Microsoft Teams, along with built-in microphones and pop-up webcams. In short, they’re the perfect monitors […]

Read More