Nose scanner identity verification developed
By Paul Ridden
March 17, 2010
As identity theft continues to rise, authorities are on the lookout for ways to use a person's physical characteristics to distinguish between an imposter and the genuine article. Whereas eyes change shape according to facial expression and ears can be hidden away, researchers from the University of Bath have discovered that the shape of a person's nose is rarely affected by such things and have developed a technique which shows distinct promise for biometric identify verification.
The research team led by Dr Adrian Evans utilized a 3D photographic system developed by the University of the West of England in Bristol and Imperial College London called Photoface. Volunteers had four flash photographs taken from different angles, the resulting images were then processed by software which analyzes all the shadows, colors, surface orientation and depth of each point on a face to produce a composite image of unparalleled detail.
Instead of using data from the whole of the face, the team concentrated on the characteristics of the ridge profile, the nose tip and the naison (section between the eyes and the top of the nose). Examination of the curvature of the ridge, combined with the measurements of the tip and naison allowed the researchers to divide the results into six main nose groups - Roman, Greek, Nubian, Hawk, Snub and Turn-up. Furthermore, the technique revealed a high rate of accuracy in identifying individuals from the 36 volunteers scanned and showed good potential for use as a biometric.
Commenting on the research, Dr Evans said: "There’s no one magic biometric – irises are a powerful biometric, but can be difficult to capture accurately and can easily be obscured by eyelids or glasses. Noses, however, are much easier to photograph and are harder to conceal, so a system that recognizes noses would work better with an uncooperative subject or for covert surveillance. We've only tried this on a small sample of people, but the technique certainly shows potential, perhaps to be used in combination with other identification techniques."
The team hopes to build on the database to test and refine the process, with tests planned to see if the technique can distinguish between family members.
Just enter your friends and your email address into the form below
For multiple addresses, separate each with a comma