Innovations in biometric identification

From immigration controls to crime-solving, the use of biometric identification - the identification of people by unique physical traits - is becoming increasingly common. Innovative gait recognition technology developed by our researchers has broken new ground in this burgeoning field.

We all have a signature walking style that can be identified much like a fingerprint. Building on previous pioneering work relating to facial recognition, researchers in Electronics and Computer Science have used computer modelling to capture information about a person's walk that is unique and recognisable with over 90 per cent accuracy.

The technique has potential in a range of fields, including the fight against global terrorism and domestic crime. It has already been used by the Metropolitan Police to identify a violent mugger who had otherwise been able to obscure his identity.

Professor Mark Nixon, who is leading the research, explains: "There are several benefits of gait recognition over other identification techniques. It's easy to avoid being identified by covering your face or wearing gloves to hide fingerprints, but much harder to disguise your gait. Gait recognition is also non-invasive and can be used at a distance when it's not possible to deploy other techniques."

The research used a biometrics tunnel - the first of its kind in the world - to combine and process data from 12 cameras to produce individual gait 'signatures'.

The concept has created considerable international interest; the research database, which contains information for use in the design and testing of gait recognition systems, has been downloaded by 30 different countries. Commercial development of the technology is currently underway.