Facial recognition systems have indeed advanced over the years, improving in both accuracy and efficiency. Facial recognition systems, like the ones made by Los Angeles startup TrueFace, are used to speed security checks over at the base entrances at the US Air Force. But because of the world changing drastically in only a few months’ time, not only are we heavily affected by this sudden change, but our systems as well.
… CEO Shaun Moore says he’s facing a new question: How good is TrueFace’s technology when people are wearing face masks?
“It’s something we don’t know yet because it’s not been deployed in that environment,” Moore says. His engineers are testing their technology on masked faces and are hurriedly gathering images of masked faces to tune their machine-learning algorithms for pandemic times.
In other words, some facial recognition systems are struggling to cope with the current times. Others, however, like those in Russia and China (because of their lighter privacy rules), as well as Japan (because they have a flu season, a time when people wear face masks), cope a bit better.
So how well are our facial recognition systems in scanning faces with face masks? Good, but far from perfect.
Check out Ars Technica for more details about this subject.
(Image Credit: teguhjatipras/ Pixabay)