Iris Identification Based on Fusion of Multiple Methods
Abstract— Iris recognition occupied an important rank in the biometric types as a result of the accuracy and efficiency which they have. The aim of this paper is suggesting a developed system for iris identification based fusion of scale invariant features transformation also local binary pattern of features extraction. Several steps have been applied. Firstly, convert any image type to a gray type. Secondly, localization the iris using circular Hough transform. Thirdly, step was the normalization to convert polar value to Cartesian using daugman rubber sheet models, after that using the histogram equalization to enhancing iris region. Finally, are the feature extractions utilize the scale invariant feature transformation and local binary pattern. Some sigma and threshold values were used to feature extraction, which achieved the highest rate of recognition. The programming implement by (MATLAB 2013).Performing the matching by the city block distance, build iris recognition system with the use of iris images for 30 individuals in CASIA v4. 0 database, every individual has 20 captures for left and right, and a total is 600 pictures, the main finding of recognition rates in the proposed system are 98.67% for left eyes and 96.66% for right eyes of thirty persons.