Google claims its ‘FaceNet’ system has almost perfected recognising human faces – and is accurate 99.96% of the time

Facebook and Google have been involved in an algorithm war to come up with the perfect facial detection system.

Now Google has claimed the latest victory, saying its new FaceNet system is practically perfect – getting the right person 99.96% of the time.

Google researchers call their system the most-accurate technology available for recognizing human faces.
In the paper, titled ‘FaceNet: A Unified Embedding for Face Recognition and Clustering’, Google claims the system achieved nearly 100-percent accuracy rate on the facial recognition dataset Labeled Faces in the Wild….

Translate »