Due to renewed interest in security, iris images have become a popular biometric alternative to fingerprints for human identification. However, there exist very few databases on which researchers can test iris recognition technology. We present a novel method to augment existing databases through iris image synthesis. A multiresolution technique known as reverse subdivision is used to capture the necessary characteristics from existing irises, which are then combined to form a new iris image. In order to improve the results, a set of heuristics to classify iris images is proposed. We analyze the performance of these heuristics and provide preliminary results of the iris synthesis method.


This paper was originally published as a short paper in the Graphite 2005 Conference Proceedings. More details on the publication are available at the ACM Portal.

Iris Synthesis: a MultiResolution Approach

Additionally, the subject is covered in more detail in my thesis. Although Chapter 5 is dedicated to Iris Synthesis the entire thesis revolves around multiresolution and synthesis.

Synthesizing Techniques Based on Multiresolution


I have posted the result of the synthesis on a separate page. It requires a recent browser with Javascript.

View the slideshow