Many industries have had to adapt 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) details the results of 65 new facial recognition algorithms created after the COVID-19 pandemic began, as well as 87 algorithms submitted before the pandemic. The report found that software developers are getting better at developing algorithms that recognize masked faces, even becoming as accurate as regular facial recognition algorithms.

“While some pre-pandemic algorithms are still the most accurate for masked photos, some developers submitted algorithms after the pandemic that showed significantly improved accuracy and are now among the most accurate in our test,” the report said.

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