Iris Recognition Method Based on Independent Component Analysis and Support Vector Machine

In order to improve the performance of iris recognition, a novel iris recognition method is presented. In this method the independent component analysis is used to obtain iris high order statistic information and mapped the input mode space into the corresponding independent component space. Then the maximal hyperplane is constructed in the independent component space using the generalization of the support vector machine. Numerical simulation based on the CASIA iris database shows that the proposed method can reduce the dimension of the feature space and has higher correct classification rate. Especially, though using Gauss kernel, the rate of correct recognition reaches 98.61% which is increased 6.48% and 4.54% respectively comparing with dissimilarity functions and the nearest feature line method, while improving robustness and flexibility of iris recognition.