A Novel Algorithm to Classify Iris Image Based on Differential of Fractal Dimension by Using Neural Network

A novel algorithm to classify iris images automatically is announced by this paper, which apply differential of fractal dimension (DFD) by determined fractal dimension of image with box counting method, and using neural network. First iris image is separated from other part of captured eye image then normalized. After that normalized iris images partition to sixteen boxes that size of each box is (32 times 32) then calculate FDs of each boxes then determined DFDs between two neighbors blocks, therefore we have fourteen DFDs of per image, then use neural network to categorize iris images. This classification method has been tested and evaluated on 716 iris images. Consequent of this method iris images classify to five classes with accuracy of classification is 95.67%.