Project DeepFace: Facebook is working on perfecting human facial verification
Facial identification is one of the most complex fields in science and is a task that has been left for computers to process. According to Facebook’s blog , the company says it’s developed a technology for verifying whether two people in side-by-side photos are the same that comes pretty close to replicating human abilities. Project DeepFace, is according to Facebook 97.25 percent accurate, which is less than the 97.5 percent humans have scored in the same standardized test. Facebook’s technology maps out 3D facial features, out puts a flat model that’s filtered by color to characterize specific facial elements. The social giant has also tapped into a pool of 4.4 million labeled faces from 4,030 different people on its network in order to help the system learn.
In late-2010, Facebook introduced facial recognition — that is, the actual capability to figure out who a person is in a photo —a feature which was initially available only to US users before the company made it worldwide in 2011. Facebook, which gets more than 350 million photos uploaded by users each day could use project deepface as the next level tagging tool.