基于实数形式Gabor变换的虹膜识别方法

吉林大学学报(工学版) ›› 2004, Vol. ›› Issue (1): 46-51.

基于实数形式Gabor变换的虹膜识别方法

徐涛¹, 刘畅², 明星³, 胡朝晖⁴

1. 吉林大学, 机械科学与工程学院, 吉林, 长春, 130025;
2. 解放军军需大学, 装备部, 吉林, 长春, 130062;
3. 吉林大学, 计算机科学与技术学院, 吉林, 长春, 130025;
4. 广西工学院, 信息与计算科学系, 广西, 柳州, 545006

收稿日期:2003-05-11 出版日期:2004-01-01
基金资助:
长春市新星创业计划资助项目(20010103003023).

Using real Gabor transform in iris identification

XU Tao¹, LIU Chang², MING Xing³, HU Zhao-hui⁴

1. College of Mechanical Science and Engineering, Jilin University, Changchun 130025, China;
2. Department of Equipment, Quartermaster University of the PLA, Changchun 130062, China;
3. College of Computer Science and Technology, Jilin University, Changchun 130025, China;
4. Department of Information and Computing Science, Guangxi University of Technology, Liuzhou 545006, China

Received:2003-05-11 Online:2004-01-01

摘要/Abstract

摘要： 提出基于实数形式Gabor变换(RGT)的虹膜识别算法。首先计算 Gaussian 函数的对偶窗函数;然后将对偶窗函数的 RGT 对规范化后的虹膜纹理进行分解,利用得到的实数 Gabor变换系数求取局部均值与方差作为虹膜纹理特征。在算法上实现完全实数运算,大大降低了算法的复杂性。实验结果及数据分析表明了此方法的合理性及有效性。

关键词: 虹膜识别, 实Gabor变换, 对偶窗, 加权欧氏距离

Abstract: An approach of iris identification based on real Gabor transform (RGT) was proposed. The localization property in time-frequency domain of RGT was suitable for extracting features of iris texture. Based on the theory of linear algebra the dual window function of Gaussian function was computed. The RGT of the dual window function is employed to analysis the normalized iris texture. The mean and variance were computed and formed in array to represent the features of iris texture. This algorithm was completed by real computation. A significant computation effort of RGT can be saved. The experiment results and data analysis are given to illnstrate the effectiveness of the prent mothod.

Key words: Iris inentification, real Gabor transform, dual window, weighted Euclidean distance

中图分类号:

TP391

徐涛, 刘畅, 明星, 胡朝晖. 基于实数形式Gabor变换的虹膜识别方法[J]. 吉林大学学报(工学版), 2004, (1): 46-51.

XU Tao, LIU Chang, MING Xing, HU Zhao-hui. Using real Gabor transform in iris identification[J]. 吉林大学学报(工学版), 2004, (1): 46-51.

参考文献

[1] DAUGMAN J. High confidence visual recognition of persons by a test of statistical independence［J］.IEEE Trans Pattern Anal Machine Intelligence,1993,15 (11):1148-1161.
[2] LIANG Tao, KWAN H K. 2-D real Gabor transform［Z］.Proceedings of the 1999 IEEE Canadian Conference on Electrical and Computer Engineering, Edmonton, Alberta, Canada, 1999.
[3] 陶亮,张德龙,KWAN H K.离散信号和图象的实数形式Gabor变换［J］.中国图像图形学报,2000,10,5(A):840-845.
[4] 陶亮,庄镇泉.2D实值离散Gabor变换及其在图像变换编码中的应用［J］.电讯技术,2000(6):50-54.
[5] BRACEWELL R M. The discrete hartley transform［J］.J Opt Soc Am, 1983, 73(12):1832-1835.
[6] 余品能.第Ⅱ类二维离散Hartley变换(DHT-Ⅱ)的一种快速算法［J］.解放军理工大学学报,2000,1(1):1-5.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed