Biometrics, as anyone who reads tech news, has been a hot topic for years and a component of spy movie plots for even longer. In the near future, however, you may see movies with dialog like this:
Suspect: You can't prove I was there!
Cop: Well, that's where you're wrong, you no-good thug.
Suspect: But I wore gloves! Covered my face and retinas! Left no DNA samples! Disguised my voice!
Cop: Yes, but your ears gave you away. Lock him up, Sergeant.
According to research published by the University of Southampton School of Electronics and Computer Science in the UK, scientists have discovered a way to identify people by their ears with 99.6 percent accuracy. According to the researchers, Professor Mark Nixon, Dr. John Carter and Alastair Cummings, a technology called image ray transform can highlight tubular structures of people's ears, which are unique to individuals, making it possible to identify them with a high rate of accuracy. According to Professor Nixon, ears have certain advantages over more established biometrics: they have a rich and stable structure that is preserved from birth to old age (ears get bigger with age, but they retain their unique shape). The ear also does not suffer from changes in facial expression and is fixed in the middle of the side of the head against a predictable background, unlike facial recognition which usually requires the face to be captured against a controlled background. Using the technology, ear images could be extracted from photos of individuals' heads and processed for identification purposes by matching the ear against an established database of ears.
The researchers have also theorized that the image ray transform could capture the way people walk (each person has a unique gait) and turn that into a biometric science as well. Professor Nixon said, “The 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. The transform could also be extended to work on 3D images, both spatial and spatio-temporal, for 3D biometrics or object tracking. As a general pre-processing technique for feature extraction in computer images the technology is now pervading manufacturing, surveillance and medical applications.”
The research, which was published in a paper entitled “A Novel Ray Analogy for Enrollment of Ear Biometrics,” was presented at the recent IEEE (News - Alert) Fourth International Conference on Biometrics: Theory, Applications and Systems, held in Washington DC.
Tracey Schelmetic is a contributing editor for TMCnet. To read more of Tracey's articles, please visit her columnist page.
Edited by Jaclyn Allard