Abstract: In order to improve recognition rate of the iris recognition system, the Gabor filter is studied, and the weighted Hamming distance based on analytic hierarchy process is proposed. First of all, the feature image was generated through different scales and directions of the odd symmetric Gabor filter; then, the recognition correct rate and equal error rate were acquired by Hamming distance matching; the appropriate scales and directions were selectded to the weighted Hamming distance calculating, the weight was calculated by AHP; then, use new distance to recognition. The equal error rate of CASIA2.0 and MMU1 were decreased by 0.64% and 0.66%. The experimental results show that: this method has better recognition performance and robustness.

Key words: iris recognition, Gabor Filter, Hamming distance, analytic hierarchy process