An Approach of Iris Recognition Based on Partical Swarm Optimization

Iris recognition is a kind of novel biometric feature recognition approach which was developed from 1990s and it has attracted more and more attention because of its high accuracy. In this paper, based on researching the existing iris authentication methods, a novel iris feature selection approach based on practical swarm optimization is proposed. We use the improved wavelet modulus maximum to locate iris image to extract ROI first. Then we use multi-scale Gabor filter to extract feature, which can retain features completely and reduce the computation. At last, GA and PSO are used respectively to select features. After feature selection, each user will possess specific feature parameters and classifiers. For proving the effectiveness and feasibility, we has carried out an experiment in CASIA database to verify iris authentication based on feature selection methods valid which this paper has proposed. The experimental results show the proposed approach can achieve lower error rates in iris authentication.