Date of Graduation


Document Type


Degree Type



Statler College of Engineering and Mineral Resources


Lane Department of Computer Science and Electrical Engineering

Committee Chair

Arun Abraham Ross.


Of all the physiological traits of the human body that help in personal identification, the iris is probably the most robust and accurate. Although numerous iris recognition algorithms have been proposed, the underlying processes that define the texture of irises have not been extensively studied. In this thesis, multiple pair-wise pixel interactions have been used to describe the textural content of the iris image thereby resulting in a Markov Random Field (MRF) model for the iris image. This information is expected to be useful for the development of user-specific models for iris images, i.e. the matcher could be tuned to accommodate the characteristics of each user's iris image in order to improve matching performance. We also use MRF modeling to construct synthetic irises based on iris primitive extracted from real iris images. The synthesis procedure is deterministic and avoids the sampling of a probability distribution making it computationally simple. We demonstrate that iris textures in general are significantly different from other irregular textural patterns. Clustering experiments indicate that the synthetic irises generated using the proposed technique are similar in textural content to real iris images.