Iris recognition based on local orientation features
Bin Li · Journal of Circuits and Systems · 2008
Feature extraction and matching are very important to iris recognition. A new algorithm for iris feature extraction and matching is proposed in this paper. In this approach, a bank of multi-orientation odd symmetric 2-D Gabor wavelets are used to capture local orientation information of iris texture, and the method of iris matching is similar to a method computing the adopted Euclidean distance (ED). Moreover according to the eyelid, eyelash and reflection's distribution of every iris image, a matching template is used to reduce their disturbance to minimum. The experimental results show that the proposed algorithm achieves an encouraging recognition performance.