Having a tough time recognizing your neighbors behind their pandemic masks? Computers are struggling too.
A preliminary study published by a U.S. agency found that even the best commercial facial recognition systems have error rates as high as 50% when trying to identify masked faces.
The mask issue is why Apple this year made it easier for iPhone owners to unlock their phones without Face ID.
The National Institute of Standards and Technology is launching an investigation to better understand how facial recognition performs on covered faces. Its preliminary study examined only those algorithms created before the pandemic, but the next step is to look at how accuracy could improve as commercial providers adapt their technology for the pandemic era.
Under ideal conditions, NIST says the failure rate for the best facial recognition systems is only about 0.3%, though research has found significant disparities across race, gender and age. When confronted with masks, the agency says, “many otherwise competent algorithms failed between 20% to 50% of the time.”