Quantification and Correction of Iris Color

A system has been developed that automatically extracts the iris region from photographs, computes the iris color in CIE u ́v ́ diagram color space, and corrects the color based on a standard calibration target. This system has advantages over previous manual methods in that it (1) is much less time-consuming because it is fully automatic, (2) corrects for the variability inherent in a film-based photographic process, (3) allows for greater objectivity and reproducibility, and (4) uses a mathematical foundation that enables quantification and statistical analysis. Preliminary experimental results show that color correction significantly improves grading accuracy. We would like to thank Dennis Hafford and Jane Armstrong for providing assistance and the iris images. The support of the National Eye Institute of the National Institutes of Health under Grant No. N01-EY-02130 is gratefully acknowledged. University of Wisconsin-Madison Department of Computer Sciences TR# 1495