Use of Improved Particle Swarm Optimization for Identity Recognition Based on Iris

For many researchers, a process that automatically identifies people based on biometric behavior seriously been considered. Iris recognition has appeared as one of the most promising methodologies to provide reliable human identification. The process of iris recognition is divided many major steps. Image enhancement using Retinex algorithm, locate internal and external borders of the iris, iris segmentation, normalization, feature extraction and matching. In this paper, a new method is proposed to feature extraction from the iris images that uses a sliding window and then the feature vectors are optimized using the improved particle swarm optimization. Experiments conducted on data collection CASIA, show that the proposed method, greatly reduced storage space requirements and performance by taking advantage of various criteria including false acceptance rate (FAR), false rejection rate (FRR), the algorithm detection rate of 98.93%, equal error rate and index decidable shown that this method can operate with better accuracy and fewer errors. Also, identity recognition accurate is increased compare to the other methods using the improved particle swarm optimization.