High Performance Iris Recognition Based on 1-D Circular Feature Extraction.pdfVIP

High Performance Iris Recognition Based on 1-D Circular Feature Extraction Chia Te CHU and Ching-Han CHEN Institute of Electrical Engineering,I-Shou University,1, Section 1, Hsueh-Cheng Rd., Ta-Hsu Hsiang, Kaohsiung County, Taiwan, 840, R.O.C. Email: cld123@.tw, pierre@.tw ABSTRACT In this paper, a novel and simple iris feature extraction technique is proposed for iris recognition of high performance. We use one dimensional circular ring to represent iris features. The reduced and significant features afterward are extracted by Sobel operator and 1- D wavelet transform. So as to improve the accuracy, this paper combines Probabilistic Neural Network (PNN) and Particle Swarm Optimization (PSO) for an optimized PNN model. A comparative experiment of existing methods for iris recognition is evaluated on CASIA iris image databases. The experimental results reveal the proposed algorithm provides superior performance in iris recognition. Keywords : iris recognition; wavelet transform; probabilistic neural network; particle swarm optimization 1. INTRODUCTION Among all the biometric indicators, iris has one of highest levels of reliability. The human iris, an annular part between the pupil and the white sclera as shown Fig. 1(a), has an extraordinary structure and provides many interlacing minute characteristics such as freckles, coronas, stripes, etc. These visible characteristics, which are generally called the texture of the iris, are unique to individuals. Even identical twins having similar DNA, are believed to have different iris. Iris recognition [1-13] is the process of automatically differentiating people on the basis of individuality information from their iris images. The technique can be used to verify the identity of a person when accessing a system. Due to its reliability and high precision, it is beneficial for biometric authentication system. A typical iris recognition system can be decomposed into three mod