MIT Technology Review - Asked whether two unfamiliar photos of faces show the same person, a human being will get it right 97.53 percent of the time. New software developed by researchers at Facebook can score 97.25 percent on the same challenge, regardless of variations in lighting or whether the person in the picture is directly facing the camera.
"Some of today’s artificial neural networks can train themselves to recognize complex patterns."
isn't that the whole point of neural networks?
So, hopefully they finally stop recognizing my dog as a person. lol.
The most uncanny thing about this whole project is that it used what the traditional user considers their own private information. Still Facebook's droves of data and some creative research could one day help to advance medical technology as we know it. Starting out, maybe DeepFace could identify a few faces that are not at the forefront of the image.