Iris Feature Detection using Split Block and PSO for Iris Identification System

Abstract

The past decade has seen the rapid development of iris identification in many approaches to identify unique iris features such as crypts. However, it is noted that, unique iris features change due to iris aging, diet or human health conditions. The changing of iris features creates the mismatch in comparison phase to determine either genuine or not genuine. Therefore, to determine genuinely, this study proposes a new model of iris recognition using combinational approach of a split block and particle swarm optimization (PSO) in selecting the best crypt among unique iris features template. The split block has been used in this study to separate the image with the part that very important in the iris template meanwhile, the particles in PSO searches the most optimal crypt features in the iris. The results indicate an improvement of PSNR rates, which is 23.886 dB and visually improved quality of crypts for iris identification. The significance of this study contributes to a new method of feature extraction using bio-inspired, which enhanced the ability of detection in iris identification.