Date of Graduation


Document Type


Degree Type



Statler College of Engineering and Mineral Resources


Lane Department of Computer Science and Electrical Engineering


In this thesis, the accuracy of iris segmentation algorithms will be compared using quality measures based on both homogeneity and heterogeneity of the resulting image regions. After calculation of the quality measures, Principal Component Analysis (PCA) is performed. The resulting pairwise distances between the genuine pairs are compared to the hamming distance scores of the iris templates. The relationship between the two samples will be examined, and curve fitting by least squares regression is shown to be an adequate method of prediction for genuine Hamming distance score. The work proposes a segmentation quality metric that is highly correlated with the distance score.;By determining the relationship between the segmentation quality values and hamming distances, it is possible to apply the same quality measures for future segmented iris images to determine the approximate genuine Hamming distance score without having to first encode the iris template and then calculate the actual hamming distance. This would be of the most practical use in a verification biometric system, where the hamming distance score is used to confirm the identity of a user. The raw data obtained from the user can be examined and determined whether it should be used for verification after segmentation, without needing to have the hamming score calculated.