Ear recognition

A University of Southampton scientist says that the features of the human ear could be used as a potential biometric signature but the fact that they can be concealed by hair means further research is needed into the subject.

According to Professor Mark Nixon of the School of Electronics and Computer Science (ECS) at the University of Southampton, ears have certain advantages over the more established biometrics as they have a rich and stable structure that is preserved from birth to old age and instead of aging they just get bigger.

The ear also does not suffer from changes in facial expression and it is firmly fixed in the middle of the side of the head against a predictable background, unlike face recognition which usually requires the face to be captured against a controlled background.

Taking into account all of these properties, Professor Nixon and his team decided to assess the ear as a potential biometric.

To do so, they developed a new linear transform that transforms an ear image, with very powerful smoothing and without loss of information, into a smooth dome shaped surface whose special shape enabled them to perform a new form of feature extraction that extracts the essential ear signature.

They applied this technique to a small database of ears and initial results showed promising results.

Professor Nixon comments: 'This research proves that ears work as a biometric. However, there are drawbacks and one of them is that ears can be concealed by hair. We need devices that can integrate multiple biometrics. We are working on some of these at the moment and will be reporting on them soon.'

Professor Nixon has written a learned paper on the subject that can be downloaded here:

http://eprints.ecs.soton.ac.uk/10242/01/hurley_cviu.pdf