Improving feature vectors for iris recognition through design and implementation of new filter bank and locally compound using of PCA and ICA

With a growing emphasis on human identification, iris recognition as a biometric identification has recently received increasing attention. Feature vectors are extracted from iris templates and are used for classification purpose. But efficiency of classification operation depends on exclusivity of feature vectors. We have improved features of iris templates by using new filter bank and applying locally of Principle and Independent component analysis on extracted features. Simulation results show improvement of iris recognition by decreasing false match rate in matching level.