Masks cause "great difficulty" for pre-pandemic facial recognition algorithms

A study by the US National Institute of Standards and Technology (NIST) has found that facial recognition algorithms developed before the emergence of the COVID-19 pandemic have "great difficulty" in accurately identifying people.


According to NIST: "Even the best of the 89 commercial facial recognition algorithms tested had error rates between 5% and 50% in matching digitally applied face masks with photos of the same person without a mask."

The study was based on one-to-one verification, whereby an image captured of a person's face is compared with another photo of the same person. This is the method used to unlock smartphones or verify someone's passport. The photos were not of people actually wearing masks, but had masks digitally added to them.

Later this year, NIST plans to test algorithms developed specifically to identify people wearing masks, an area where there have been swift technological developments in response to the pandemic.

See: NIST Launches Investigation of Face Masks’ Effect on Face Recognition Software (NIST, link)

Full study: Ongoing Face Recognition Vendor Test (FRVT) Part 6A: Face recognition accuracy with masks using pre-COVID-19 algorithms (pdf)

More information: FRVT Face Mask Effects (NIST, link)

See also: Wearing a mask won’t stop facial recognition anymore (Abacus, link):

"New forms of facial recognition can now recognize not just people wearing masks over their mouths, but also people in scarves and even with fake beards. And the technology is already rolling out in China because of one unexpected event: The coronavirus outbreak."

 

 

Spotted an error? If you've spotted a problem with this page, just click once to let us know.

Report error