A robust feature extraction method based on monogenic filter for iris recognition system

摘要

Iris recognition system is an attractive technology for identity authentication. This technology takes advantages of random variations in the features of the iris. Usually, each iris recognition system has four modules: segmentation, normalization, encoding and matching. Iris texture analysis or and matching are two essential processes in iris recognition. First, in this paper we propose to use a combined of monogenic filter and 1D log gabor filter to extract the iris signature. Second, two types of distances measures are chosen as a metric for recognition. Experimental results on CASIA iris database V3.0 demonstrates that the proposed method provides the high performance in speed and accuracy compared to the state of the art.