No need for passwords - when mobile phones recognise faces

Software for mobile phones that can track facial features in real time has been developed by scientists in the United Kingdom. Potentially, it could allow for greater security across many platforms.

Eventually, the software would mean goodbye to passwords because it would be able to tell who the user is, where they are looking and even how they are feeling, say researchers at the University of Manchester.

The biometric technology method is believed to be unrivalled for speed and accuracy. It could lead to facial recognition replacing passwords and personal identification numbers to log into internet sites from a mobile phone.

“The idea is to recognise you as the user, and it does that by first taking a video of you, so it has your voice and lots of images for comparison,” said Dr Phil Tresadern, lead researcher on the project.

“Existing mobile face trackers give only an approximate position and scale of the face. Our model runs in real time and accurately tracks a number of landmarks on and around the face such as the eyes, nose, mouth and jaw line.

“A mobile phone with a camera on the front captures a video of your face and tracks 22 facial features. This can make face recognition more accurate and has great potential for novel ways of interacting with your phone,” he added.

Originally intended as part of a face and voice-verification system for access to mobile internet applications such as email, social networking and online banking, alternative uses for the device could include fun applications that, for instance, attach virtual objects to the user’s face as they move around.

“At this stage, we are particularly interested in demonstrating uses for the face-tracking part of the technology, which is the area that the University of Manchester is involved in,” added Dr Tresadern who is based in Manchester’s School of Cancer & Enabling Sciences. “It is very fast and I can’t find anything that can rival it on a mobile phone.

“To register with a face verification system, you first record a video of your face. To log in to the system, you then record a new video and the system compares the new video with the original one to see if they match.

“If, however, you are facing in a slightly different direction or have a different expression in the two videos, your appearance on the screen is very different which may confuse the verification system.

“To avoid this problem, we use the tracked landmarks to rotate, scale and stretch the image of your face so that it seems more like you are looking straight at the camera and have a neutral expression. This way, most of the remaining differences are down to who you are which ensures that the verification process is more accurate and secure. Ideally, using a biometric such as your face will eventually replace passwords and PINs that are difficult to remember and are easily forgotten or stolen,” said Dr Tresadern.

Face verification is already used in laptops, webcams and the Xbox 360 Kinect, but this is the first time the technology is being used with such sophistication in mobile devices such as smartphones.

The new software, built on 20 years of research at the university, has been demonstrated on a Nokia N900 for the Mobile Biometrics project funded by the European Union.

And in London the Metropolitan Police Service hopes to capitalise on the advances in facial recognition software, vehicle number plate recognition and DNA detection in a bid to reduce crime rates, said Commissioner Bernard Hogan-Howe.

He said that facial recognition technology is growing rapidly and wants to see that technology adapted to CCTV. During his time as chief constable at Merseyside Police, Hogan-Howe used advanced technology such as helicopters fitted with cameras to tackle crime.