Improving the Accuracy of Iris Recognition System using Neural Network and Particle Swarm Optimization

Iris recognition is the process of recognizing a person by analyzing the apparent pattern of his or her iris. Many techniques have been developed for iris recognition so far. Here, we propose a new iris recognition system with the help of local histogram and then optimized with FFBNN-PSO. In the proposed system, first the input eye images are preprocessed using adaptive median filter to remove the salt and pepper noise. Then, the features, which are extracted from the preprocessed image are given to FFBNN for training. In order to get accurate results, the FFBNN parameters are optimized using PSO. General Terms Soft Computing, Biometric.