A new biometric technique developed by computer scientists at the University of Southampton can automatically identify people by their ears. The technique uses light rays to highlight circular and tubular structures, such as the curved rim at the ear, known as the helix. The elliptical shape of the helix can be extracted and used as the basis of a method for discovering, localizing, and normalizing an image for ear biometrics.
Southampton professor Mark Nixon notes that ears have a rich and stable structure that gets bigger as people age, and remains fixed in the middle of the side of the head against a predictable background. The researchers say the new technique had a 99.6 percent rate of success in identifying ears from more than 250 images, even with hair concealment and possible confusion with spectacles.
"The Image Ray Transform technique may also be appropriate for use in gait biometrics, as legs act as tubular features that the transform is adept at extracting," Nixon says. "The transform could also be extended to work upon [three-dimensional] images, both spatial and spatio-temporal, for 3-D biometrics or object tracking."
From University of Southampton
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA
No entries found