New study shows accuracy of facial recognition algorithms has markedly improved over the past three years. The accuracy of 50 algorithms NIST tested shows a 10 percent to 30 percent improvement from 2010 to 2013. The best algorithm tested in 2013 failed to find in a database of 1.6 million images a corresponding image of a person 30 percent less frequently than it did in 2010. The failure rate fell to 4.1 percent in 2013 from 5.7 percent in 2010; rates of missing facial matches increase as database size grows.”]
Source: https://www.careersinfosecurity.com/facial-recognition-algorithms-improve-a-6958