Iris recognition method using Log-Gabor filter and multi-resolution analysis

A new method is proposed to improve the performance of iris recognition, which is named iris recognition based on global texture (IRBGT). The method based on global information of iris texture, is realized through obtaining iris texture image with different resolutions by the down-sample algorithm. 2D Log-Gabor filters with different orientations are used to extract the global features of iris texture. The minimum weighted Hamming distance is used to test the similarity of two iris feature codes. The proposed method has lower equal error rate and lower false rejection rate at the same false acceptance rate than the traditional Gabor filter method has. Experiment results on the CASIA and UBIRIS iris database show that when the false acceptance rates are at 0.01% and 0.1%, the false rejection rates of IRBGT are decreased by 0.54%±0.2% and 0.35%±0.15% respectively, and the equal error rate is decreased by about 0.2%.