Biometric Identification: Identifying Who's Who in a Post 9-11 World
A biometric is a stable and distinctive physical or behavioral feature of a person that can be measured and used to identify that individual. Ideally, this feature would be stable in the sense that it doesn’t change over time or with a person’s health, mood or other factors. It also should be distinctive so that no two people could exhibit the same features. Just as important, it should be something that can be quickly and easily measured, cataloged, and referenced. The fingerprint is probably the most familiar example of biometric identification. In the late 1890s, the odds of finding identical fingerprints were calculated at 1 in approximately 64 billion. In modern times, we have seen high-profile fingerprint recognition errors, such as in the Brandon Mayfield case. It is now acknowledged that a fingerprint is not the ultimate biometric, nor can it be used to accurately identify all individuals. The fingers of bricklayers, rock climbing enthusiasts, senior citizens, and toddlers, for example, may have ridges that are so difficult to image that they can’t be reliably identified. Fortunately, other physical markers can be used — an iris, an ear, or the face itself.
Notre Dame’s Kevin W. Bowyer, the Schubmehl-Prein Professor and Chair of the Department of Computer Science and Engineering, is a pioneer in biometrics. Since 2001 Bowyer, fellow faculty, and students have been studying image-based biometrics and multi-biometrics. They have collected the largest database of multi-modal biometrics in the world, including first-of-their-kind comparisons of facial photographs, facial thermograms, 3-D facial images, iris images, ear and hand shapes, and videos of human gait.
These types of biometrics are vital to any number of corporate and national security issues today. In fact, federal agencies have frequently used the group’s expertise and findings to objectively analyze commercial biometrics technologies. The group’s findings have also led to changes in the ISO standard for iris template data and image capture criteria, and improved our basic understanding of the effects of contact lenses, dilation, and aging on iris recognition.
Bowyer’s research interests range broadly over computer vision and pattern recognition, including biometrics, data mining, object recognition, and medical image analysis. He is a recipient of the Institute of Electrical and Electronics Engineers (IEEE) Computer Society’s Technical Achievement Award, a Fellow of the IEEE, and a Fellow of the International Association for Pattern Recognition.
Click here for more information on Bowyer and his group’s work.