
The accuracy of face recognition algorithms used on photos of people that have been altered with a digitally created mask declines even with the best commercial algorithms used in one-to-one matches, the National Institute of Standards and Technology (NIST) says in a new study. The algorithms tested by NIST were mostly developed before COVID-19 hit and not with masked faces in mind. A later evaluation will assess software developed for masked faces. NIST says that the best of the 89…