Abstract
Biometric systems have gradually become an accepted mean for person identification and verification. Recently, person identification using iris features has received a lot of attention in both research and industry communities. This is mainly due to the unique characteristics and texture found in iris images. Most proposed iris recognition techniques are based on gray-level representations. The aim of this paper is to develop a novel method for the automatic recognition and matching of color iris images based on hypercomplex (Quaternion) Gabor wavelets. The performance of Quaternion image representation is compared with that of other representations, and a study of the results is conducted. The well-known IrisCode algorithm, developed by John Daugman, is extended to the color domain.