Facebook's Facial Recognition 'Approaching Human-Level Performance'

H

HardOCP News

[H] News
Joined
Dec 31, 1969
Messages
0
This whole facial recognition "approaching human-level performance" is cool and all but your nine-layer deep neural network is starting to creep me out a bit there Facebook. :eek:

The learned representations coupling the accurate model-based alignment with the large facial database generalize remarkably well to faces in unconstrained environments, even with a simple classifier. Our method reaches an accuracy of 97.25% on the Labeled Faces in the Wild (LFW) dataset, reducing the error of the current state of the art by more than 25%, closely approaching human-level performance.
Click to expand...
 
Ducman69 said:
When it can tell apart South Korean band members, I'll be impressed.
Click to expand...

I had to look around first, then I laughed. :)

I wonder if facial recognition could tell the difference between identical twins. They usually have a few minor differences to put them apart, but they are still very similar. That would be the true test.
 
You must log in or register to reply here.
Back
Top