SAFR Facial Recognition is the best facial recognition algorithm due to its combination of commercial viability (performance vs. accuracy) and its ability to recognize on faces in the wild (faces at angles, in motion, etc).
The SAFR algorithm's resilience has been documented by NIST indirectly in Faces in the Wild evaluations, and directly as part of their bias and race analysis. SAFR performs well with Faces in the Wild to recognize faces with varying degrees of pitch, roll, yaw, and occlusion. More details on NIST testing can be found at https://safr.com/general/nist-test-confirms-safr-delivers-the-highest-effective-accuracy-for-live-video/. Further details can be found at https://safr.com/general/5-ways-safr-excels-at-facial-recognition-for-live-video-and-why-you-should-care/.