The ability of a new facial recognition algorithm to recognise partially obscured and tilted faces is being been hailed as a potentially game-changing breakthrough for the technology.Developed by Sachin Farfade and Mohammad Saberian at Yahoo Labs in California and Li-Jia Li at Stanford University, the so-called “Deep Dense Face Detector” algorithm aims to identify faces at a wide range of angles, even when partially covered.Farfade and Saberian used a database of 200,000 images that included faces at various angles and orientations and a further 20 million images without faces. They then trained a machine learning method known as “Deep Convolutional Neural Networks” by processing batches of 128 images over 50,000 iterations.The algorithm is built on one developed by computer scientists Paul Viola and Michael Jones in 2001 that looks for a light vertical line (the nose) on faces crossed by a dark horizontal line (the eyes) in a “detection cascade.”Because it can pick out faces in an image in real time and be easily incorporated in devices, the Viola and Jones algorithm has been widely adopted. However, it is limited to full view frontal upright faces.The Deep Face tool used by Facebook also uses a neural network technique to help recognise users in photos. Its algorithm identifies faces 'as accurately as a human' and uses a 3D model to virtually rotate faces so they are facing the camera.