Global Texture Analysis of Iris Images for Ethnic Classification

Iris pattern is commonly regarded as a kind of phenotypic feature without relation to the genes. In this paper, we propose a novel ethnic classification method based on the global texture information of iris images. So we would argue that iris texture is race related, and its genetic information is illustrated in coarse scale texture features, rather than preserved in the minute local features of state-of-the-art iris recognition algorithms. In our scheme, a bank of multichannel 2D Gabor filters is used to capture the global texture information and AdaBoost is used to learn a discriminant classification principle from the pool of the candidate feature set. Finally iris images are grouped into two race categories, Asian and non-Asian. Based on the proposed method, we get an encouraging correct classification rate (CCR) of 85.95% on a mixed database containing 3982 iris samples in our experiments.