High performance iris recognition based on 1-D circular feature extraction and PSO-PNN classifier

被引：34

作者：

Chen, Ching-Han ^{[1
]}

Chu, Chia-Te ^{[1
]}

机构：

[1] Natl Cent Univ, Dept Comp Sci & Informat Engn, Jhongli 32001, Taoyuan County, Taiwan

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2009年 / 36卷 / 07期

关键词：

Iris recognition; Wavelet transform; Probabilistic neural network; Particle swarm optimization;

D O I：

10.1016/j.eswa.2009.01.033

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, a novel iris feature extraction technique with intelligent classifier is proposed for high performance iris recognition. We use one dimensional circular profile 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 classifier 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. (C) 2009 Published by Elsevier Ltd.

引用

页码：10351 / 10356

页数：6

共 11 条

[1]

[Anonymous], 1998, INTRO WAVELETS WAVEL

[2]

CHEN CH, 2005, 2005 DESIGN AUTOMATI

[3]

*CHIN AC SCI I AUT, CASIA IR DAT

[4]

CHU CT, 2005, J INTERNET TECHNOL, V6, P419

[5] HIGH CONFIDENCE VISUAL RECOGNITION OF PERSONS BY A TEST OF STATISTICAL INDEPENDENCE [J].

DAUGMAN, JG .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (11) :1148-1161

[6]

Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968

[7]

Ma L, 2002, INT C PATT RECOG, P414, DOI 10.1109/ICPR.2002.1048327

[8]

SANCHEZAVILA C, 2002, P IEEE 35 INT CARN C, P272

[9]

Specht D.F., 1988, IEEE International Conference on Neural Networks, V1, P525, DOI DOI 10.1109/ICNN.1988.23820

[10]

TISSE CL, 2002, P 15 INT C VIS INT

← 1 2 →