The algorithm, called DeepFace, is capable of identifying faces at about the same accuracy rate as a person. The software works by building 3-D models from 2-D photographs, analyzing the 3-D models, and then matching that model against other models to find a match.
“So far,” TechCrunch reported, “this project is being put forward as mostly an academic pursuit […] and the research team behind it will present its findings at the Computer Vision and Pattern Recognition conference in Columbus, Ohio in June.”