Nokia N900 does real-time face tracking for verification (video)

video of your face contains useful information such as who you are, where you are looking and how you are feeling. If we can extract this information from the video, it potentially paves the way for automatic face verification (i.e. determining whether you are who you claim to be), augmented reality and robots that can recognize emotions.

To get this information from the video we track landmarks on the face (e.g. around the eyes, nose, mouth and jawline) using a technique known as the Active Appearance Model that was pioneered by the University of Manchester. The positions of these landmarks relative to each other define the shape of your face and indicate where you are looking, your expression and (to a small degree) who you are. Your identity, however, is more strongly indicated by the texture of the face which we can extract by cutting out just the bits of the image that lie within the boundary defined by the landmarks on your eyebrows and jawline.

This Experiment achieved by the University of Manchester (UK). Using an N900, the research team developed a prototype that quickly locks and tracks 22 facial features in real time (even when upside down) using the Nokia's front-facing camera. The Active Appearance modeling technique was developed for the EU-funded Mobile Biometrics (MoBio) project as a means of using face verification to authenticate smartphone access to social media sites. Unfortunately, there's no mention of how long Manchester's face-verified login actually takes.