Journal of Jilin University(Engineering and Technology Edition) ›› 2021, Vol. 51 ›› Issue (2): 650-658.doi: 10.13229/j.cnki.jdxbgxb20191176

Previous Articles    

Iris recognition based on multi⁃direction local binary pattern and stable feature

Xiao-dong ZHU1,2(),Qi-xian ZHANG1,3,Yuan-ning LIU1,2(), WU-di1,2,Zu-kang WU1,2,Chao-qun WANG1,3,Xin-long LI1,3   

  1. 1.Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,Jilin University,Changchun 130012,China
    2.College of Computer Science and Technology,Jilin University,Changchun 130012,China
    3.College of Software,Jilin University,Changchun 130012,China
  • Received:2019-12-23 Online:2021-03-01 Published:2021-02-09
  • Contact: Yuan-ning LIU E-mail:zhuxd@jlu.edu.cn;lyn@jlu.edu.cn

Abstract:

To improve the iris recognition rate by suppressing the noise and extracting the feature of local texture effectively in iris image, an iris recognition algorithm based on multi-direction local binary mode and stable feature is proposed. First, applying a variety of filtering processing algorithms, sufficient iris internal features are extracted from the iris image in unstable state with illumination and noise interference, which are as effective iris information to form a stable iris feature image. Then, based on the local binary pattern, a multi-directional local binary pattern is proposed to extract the feature vectors. This method not only can describe the overall spatial information of the iris image, but also reduce the dimension of the feature image. Finally, the Hamming distance is used for iris recognition. This method is used to identify CASIA, JLU-6.0 database, and the results show that this method not only can guarantee the effectiveness of the stable feature, but also extract the local texture feature effectively with higher recognition rate and robustness.

Key words: local texture, iris recognition, local binary pattern, robustness

CLC Number: 

  • TP391.41

Fig.1

Quality qualified and location image"

Fig.2

Normalized and recognition area image"

Fig.3

Four different feature difference images"

Fig.4

Stable feature recognition area"

Fig.5

MD-LBP operator"

Fig.6

Weighted grayscale values in eight different directions"

Fig.7

MD-LBP encoding process"

Fig.8

Calculate eigenvector of iris"

Table 1

Number of matches of iris library"

虹膜库

虹膜

类别

单类

数量

虹膜

总数

类内比较次数类外比较次数总匹配次数
JLU-6.0160203200315156398790

Table 2

CRR and EER of four methods"

稳定特征处理算法CRR/%EER/%
不做处理95.213.23
高斯滤波97.721.74
高斯拉普拉斯滤波和中值滤波99.040.85
本文算法99.420.53

Fig.9

ROC curve of experimental results"

Table 3

Experimental results of JLU-6.0"

虹膜库项目4×816×832×832×1664×16

JLU-6.0

(T4)

识别率/%93.493.289.784.580.1
时间/s9.55.24.43.22.6

JLU-6.0

(T6)

识别率/%95.194.990.786.483.6
时间/s11.67.35.44.83.3

JLU-6.0

(T8)

识别率/%96.896.292.487.785.3
时间/s12.78.27.56.24.9

JLU-6.0

(T10)

识别率/%98.297.695.391.687.3
时间/s15.510.89.28.46.9

Table 4

Experimental results of CASIA-Interval"

虹膜库项目4×816×832×832×1664×16

CASIA-

Interval(T4)

识别率/%87.885.784.682.380.4
时间/s6.64.23.52.71.4

CASIA-

Interval(T6)

识别率/%89.886.485.682.981.1
时间/s7.54.94.63.82.1

CASIA-

Interval(T8)

识别率/%90.687.285.983.782.5
时间/s7.95.35.04.23.4

CASIA-

Interval(T10)

识别率/%92.290.387.885.483.6
时间/s9.26.65.75.04.1

Fig.10

Recognition rate and calculation time of different block sizes"

Table 5

Matching number of different databases"

虹膜库

虹膜

类别

单类

数量

虹膜

总数

类内比较次数类外比较次数总匹配 次数
JLU-6.0160203 2003 40016 70020 100
Interval12056001 8008 50010 300
Lamp8075601 3507 8409 190

Table 6

CRR and EER of each iris library"

识别算法JLU-6.0CASIA-Iris- IntervalCASIA-Iris-Lamp
CRREERCRREERCRREER
LBP94.522.3296.122.1791.343.94
MB-LBP94.272.5997.982.1494.932.25
CS-LBP96.671.6698.171.5395.252.45
SCCS-LBP97.530.9698.951.1696.430.98
MD-LBP99.280.4390.422.4898.260.67

Fig.11

ROC curve of experimental results"

1 王蕰红, 朱勇, 谭铁牛. 基于虹膜识别的身份鉴别[J]. 自动化学报, 2002, 28(1): 1-10.
Wang Wen-hong, Zhu Yong, Tan Tie-niu. Identification based on iris recognition[J]. Journal of Automation, 2002, 28(1): 1-10.
2 李星光, 孙哲南, 谭铁牛. 虹膜图像质量评价综述[J]. 中国图象图形学报, 2014, 19(6): 813-824.
Li Xing-guang, Sun Zhe-nan, Tan Tie-niu. Overview of iris image quality-assessment[J]. Journal of Image and Graphics, 2014, 19(6): 813-824.
3 Daugman J. High confidence visual recognition of persons by a test of statistical independence[J]. IEEE Transactions, 1993, 15(11): 1148-1161.
4 Wildes R P, Asmuth J C, Green G L, et al. A machine-vision system for iris recognition[J]. Machine Vision & Application, 1996, 9(1): 1-8.
5 孙哲南. 虹膜图像特征表达方法研究[D]. 北京: 中国科学院自动化研究所研究生院, 2006.
Sun Zhe-nan. A study on iris feature representation[D]. Beijing: Graduate School, Institute of Automation, Chinese Academy of Sciences, 2006.
6 Liu J, Sun Z N, Tan T N. Distance metric learning for recognizing low-resolution iris images[J]. Neurocomputing, 2014, 144: 484-492.
7 Yang D T, Fan P C. Effective scale-invariant feature transform based iris matching technology for identity identification[C]∥In Proceedings of the IEEE International Conference on Consumer Electronics-Taiwan(ICCE-TW), Taichung, 2018: 19-21.
8 Redman A, Zainal N, Suandi S A. Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut[J]. Digital Signal Processing, 2017, 64: 60-70.
9 Han C Y, Kwon S H, Choi H I, et al. Seeded Ising model and the statistical nature of human iris templates[J]. Physical Review E, 2018, 98: 1-7.
10 Ojala T, Pietikainen M, Maenpaa T. Multi-resolution gray scale and rotation invariant texture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987.
11 Zhang L, Chu R, Xiang S, et al. Face detection based on multi-block lbp representation[C]∥International Conference on Biometrics. Berlin: Springer, 2007: 11-18.
12 Heikkila M, Pietikainen M, Schmid C. Description of interest regions with local binary patterns[J]. Pattern Recognition, 2009, 42(3): 425-436.
13 李欢利, 郭立红, 李小明, 等. 基于统计特征中心对称局部二值模式的虹膜识别[J]. 光学精密工程, 2013, 21(8): 2129-2136.
Li Huan-li, Guo Li-hong, Li Xiao-ming, et al. Iris recognition based on SCCS-LBP[J]. Optics and Precision Engineering, 2013, 21(8): 2129-2136.
14 刘帅. 基于粒子群优化改进的虹膜特征提取与识别算法的研究[D]. 长春: 吉林大学软件学院, 2019.
Liu Shuai. Research on iris feature extraction and recognition algorithm based on improved particle swarm optimization[D]. Changchun: College of Software, Jilin University, 2019.
15 Daugman J G. How iris recognition works[J]. IEEE Transactions on Gircuits and System for Video Technology, 2004, 14(1): 21-30.
16 Liu S, Liu Y N, Zhu X D, et al. Iris double recognition based on modified evolutionary neural network[J].Journal of Electronic Imaging, 2017, 26(6): 1-11.
17 Zhang Q X, Zhu X D, Liu Y N, et al. Iris recognition based on adaptive optimization log-gabor filter and rbf neural network[C]∥14th Chinese Conference on Biometric Recognition. Cham: Springer, 2019: 312-320.
18 毛星云, 冷雪飞. OpenCV3编程入门[M]. 1版, 北京: 电子工业出版社, 2017.
19 de Souza J M, Gonzaga A. Human iris feature extraction under pupil size variation using local texture descriptors[J]. Multimedia Tools and Applications, 2019, 78(15): 20557-20584.
20 吉林大学生物识别与信息安全技术实验室. 虹膜库[EB/OL]. [2019-10-25].
21 中国科学院自动化研究所. 共享虹膜库[EB/OL]. [2019-10-25]. .
22 刘元宁, 刘帅, 朱晓冬, 等. 基于决策粒子群优化与稳定纹理的虹膜二次识别[J]. 吉林大学学报: 工学版, 2019, 49(4): 1329-1338.
Liu Yuan-ning, Liu Shuai, Zhu Xiao-dong, et al. Iris secondary recognition based on decision particle swarm optimization and stable texture[J]. Journal of Jilin University (Engineering and Technology Edition), 2019, 49(4): 1329-1338.
23 Liu S, Liu Y N, Zhu X D, et al. Unsteady state lightweight iris certification based on multi-algorithm parallel integration[J]. Algorithms, 2019, 12(9): 1-24.
[1] LIU Yuan-ning, LIU Shuai, ZHU Xiao-dong, CHEN Yi-hao, ZHENG Shao-ge, SHEN Chun-zhuang. LOG operator and adaptive optimization Gabor filtering for iris recognition [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1606-1613.
[2] HU Yun-feng, GU Wan-li, LIANG Yu, DU Le, YU Shu-you, CHEN Hong. Start-stop control of hybrid vehicle based on nonlinear method [J]. 吉林大学学报(工学版), 2017, 47(4): 1207-1216.
[3] GU Wan-li, ZHANG Sen, HU Yun-feng, CHEN Hong. Nonlinear controller design of brushed DC motor [J]. 吉林大学学报(工学版), 2017, 47(3): 900-907.
[4] MA Bei, ZHANG Hai-lin, ZHANG Zhao-wei, ZHONG Ming. Imperfect channel state information based D2D power allocation algorithm [J]. 吉林大学学报(工学版), 2016, 46(4): 1320-1324.
[5] WANG Yu, SHEN Xuan-jing, CHEN Hai-peng, TAN Ying. Video-based face texture representation and recognition with fusion features from multi-view [J]. 吉林大学学报(工学版), 2015, 45(6): 1954-1960.
[6] QIU Chun-ling, TAO Qiang, FAN Run-long, WANG Pei-zhi. Zircon image matching method based on description of SIFT feature by LBP [J]. 吉林大学学报(工学版), 2014, 44(6): 1793-1798.
[7] LI Gen,LI Wen-hui. Face occlusion recognition based on MEBML [J]. 吉林大学学报(工学版), 2014, 44(5): 1410-1416.
[8] LI Yi-bing,CHANG Guo-bin,YE Fang. Exponential entropy-based spectrum sensing algorithm in cognitive radio [J]. 吉林大学学报(工学版), 2014, 44(5): 1506-1511.
[9] WANG You-wei, LIU Yuan-ning, ZHU Xiao-dong. Novel robust watermarking algorithm for regional attacks of digital images [J]. 吉林大学学报(工学版), 2014, 44(4): 1151-1158.
[10] LIU Fu, HOU Tao, LIU Yun, ZHANG Xiao. A variable trade-off parameter support vector domain description [J]. 吉林大学学报(工学版), 2014, 44(2): 440-445.
[11] LI Huan-li, GUO LI-hong, WANG Xin-zui, LI Xiao-ming, DONG Yue-fang, FANG Yan-chao. Iris recognition based on weighted Gabor filter [J]. 吉林大学学报(工学版), 2014, 44(01): 196-202.
[12] ZHANG Yuan-yuan, LI Jing, JIANG Shu-ming, YANG Zi-jiang, ZHANG Jiang-zhou. Local features of gait energy image through the method of texture analysis [J]. 吉林大学学报(工学版), 2013, 43(增刊1): 193-198.
[13] CHEN Chen, DANG Jing-min, HUANG Jian-qiang, WANG Yi-ding. DFB laser temperature control system with high stability and strong robustness [J]. 吉林大学学报(工学版), 2013, 43(04): 1004-1010.
[14] LIU Shu-cheng, PAN Xin, WEI Wei, YAN Qing-dong, LAI Yu-yang. Complexity-based robustness analysis of turbulence model in torque converter flow field simulation [J]. 吉林大学学报(工学版), 2013, 43(03): 613-618.
[15] DAI Jin-bo, XIAO Xiao, ZHAO Hong-wei. Human face recognition based on low resolution local binary pattern [J]. 吉林大学学报(工学版), 2013, 43(02): 435-438.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!