Analysis of Iris Identification System by Using Hybrid Based PSO Classifier

Abstract

In the present days, Iris recognition as a physiological attribute of biometric is an important biometric process. Human eye iris acts as a significant task in vast identification of a human being. In this research work, the block sum and Haar transform algorithms i.e. hybrid algorithms are presented as a feature extraction method. After extracted features, hybrid based PSO classifier is used for classification. Hybrid based PSO classifier contains the combination of weighted DAG multi-class SVM and SNN i.e. spiking neural network. Internally weighted DAG multi class SVM is used for classification and SNN is used for optimization of PSO. For performing an experiment, we have taken 280 images of eye from 28 individuals and every person has 10 images of eye from CASIA version VI iris database. Experimental result shows that the hybrid PSO based classifier gives superior result in evaluation with other methods i.e. SVM and ANN. By using this method the average classification accuracy is 99.99%. The entire simulation is done on MATLAB R2013@ environment with tested images and accuracy as a parameter.