Scientists develop quick, accurate, real time facial recognition for mobile

Scientists at the Univeristy of Manchester have developed facial recognition software which could eventually tell how you are feeling, opening up new avenues for the technology of the future and scare the pants off Luddites.

Facial recognition software is not exactly new, but the Manchester scientists say that their method is “unrivalled for speed and accuracy” and believe it could be used to replace passwords and PIN numbers for logging into websites and mobile phones. 

“Existing mobile face trackers give only an approximate position and scale of the face,” said Dr. Phil Tresadern, lead researcher on the project. “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.”

This accuracy is vital if the technology is to replace passwords, to ensure that only the individual in question is recognised as the appropriate user. However, the software would also need to allow for different hairstyles, facial hair, accessories or a balaclava.

“A mobile phone with a camera on the front captures a video of your face and tracks twenty-two facial features. This can make face recognition more accurate, and has great potential for novel ways of interacting with your phone,” Tresadern continued. “It is very fast and I can’t find anything that can rival it on a mobile phone.”

Along with being used to replace passwords, the technology will eventually be able to tell where you are looking and even how you are feeling. The possible ramifications of software that is aware of your emotions, based on the different expressions we make, could open doors for new types of games or mobile applications which employ the human face as the main input controller.

The software could even be linked with augmented reality developments to attach virtual objects to the user’s face as they move around, showcasing how these two technologies, which make use of the camera features that are present on every modern mobile phone, can merge together to provide a news and unique interactive experience.

The software is based on 20 years of research at the University and has been demonstrated on a Nokia N900 smartphone. It is EU-funded under the Mobile Biometrics project.