notes.husk.org/likes images.

DeepFace: Facebook’s new face verification software - Via MIT

Facebook researchers have achieved a 97.25% success rate at identifying a face due to advances in performing face verification with Deep Learning, plus the clever trick of correcting the orientation of the face first. The example provided is rather amusing as Sylvester Stallone’s face could be considered a low-hanging fruit for face recognition. 

DeepFace processes images of faces in two steps. First it corrects the angle of a face so that the person in the picture faces forward, using a 3-D model of an “average” forward-looking face. Then the deep learning comes in as a simulated neural network works out a numerical description of the reoriented face. If DeepFace comes up with similar enough descriptions from two different images, it decides they must show the same face.