Ethnic Classification Based on Iris Images

Iris texture is commonly thought to be highly discriminative between eyes and stable over individual lifetime, which makes iris particularly suitable for personal identification. However, iris texture also contains more information related to genes, which has been demonstrated by successful use of ethnic and gender classification based on iris. In this paper, we propose a novel ethnic classification method based on supervised codebook optimizing and Locality-constrained Linear Coding (LLC). The optimized codebook is composed of codes which are distinctive or mutual. Iris images from Asian and non-Asian are classified into two classes in experiments. Extensive experimental results show that the proposed method achieves encouraging classification rate and largely improves the ethnic classification performance comparing to existing algorithms.