WPF Issue Brief

Face Recognition and Face Masks:  Accuracy of face recognition plummets when applied to mask-wearers; NIST report 

NIST has published its first report regarding face recognition algorithms and the wearing of face masks. The report quantifies how one-to-one face recognition systems perform when they are utilized on images of diverse people wearing a variety of mask types and colors. The study found that pre-COVID-19 FR algorithms have substantial error rates, some reaching as high as 50 percent for false non-match rates.