skip to Main Content

Covid-19, face masks deceive the facial recognition algorithms

Covid-19, Face Masks Deceive The Facial Recognition Algorithms

A NIST research: The anti-Covid-19 face masks deceive also the most advanced facial recognition algorithms. Error rates varied from 5% to 50%, depending on their capabilities. Blacks one double rates than light-blue

Anti Covid-19 face masks could be a nightmare for the security. It has been discovered by the NIST cyber security researchers. According a study, if they are worn, even the most advanced facial recognition algorithms make mistakes in identifying the target. Error rates varied from 5% to 50%, depending on their capabilities. Moreover, most algorithms have higher error rates in black masks than light-blue. The NIST team explored how well each of the algorithms was able to perform “one-to-one” matching, where a photo is compared with a different photo of the same person. The function is commonly used for verification such as unlocking a smartphone or checking a passport. The team tested the algorithms on a set of about 6 million photos used in previous FRVT studies.

How the cyber security experts made the test

The cyber security research team digitally applied mask shapes to the original photos and tested the algorithms’ performance. Because real-world masks differ, the team came up with nine mask variants, which included differences in shape, color and nose coverage. The digital masks were black or a light blue that is approximately the same color as a blue surgical mask. The shapes included round masks that cover the nose and mouth and a larger type as wide as the wearer’s face. These wider masks had high, medium and low variants that covered the nose to different degrees. The team then compared the results to the performance of the algorithms on unmasked faces.

However, none of these algorithms were designed to handle face masks, and the masks we used are digital creations, not the real thing. But cyber security experts are studying new ones that takes in consideration the pandemic elements

With the arrival of the Covid-19, “we need to understand how face recognition technology deals with masked faces,” said Mei Ngan, a NIST computer scientist and an author of the report. “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.” “We can draw a few broad conclusions from the results, but there are caveats,” Ngan said. “None of these algorithms were designed to handle face masks, and the masks we used are digital creations, not the real thing.” However, this discovery made the intelligence-law enforcement forces antennas stand up. Especially for its implication in security and crime-fight. Not surprisingly, the cyber security experts are studying and testing new algorithms that takes this element in consideration.

Photo Credits: B. Hayes/NIST

Back To Top