Algorithm for iris recognition based on texture distribution and Gabor filters

An algorithm based on the character of texture distribution in the iris image is presented in this paper. In the algorithm, iris is divided into a number of bands and every band is filtered by the Gabor filters and encoded with the phase of the result of filtering. A new weight Hamming distance of the bands is proposed to match two iris codes. Compared with the common algorithm, the new algorithm can make the Hamming distance between the same irises and the different irises further, which is helpful to reduce the false accept rate(FAR) and false reject rate(FRR).The result of experiments shows that this algorithm is effective and available.