基于决策粒子群优化与稳定纹理的虹膜二次识别

doi:10.13229/j.cnki.jdxbgxb20180487

吉林大学学报(工学版) ›› 2019, Vol. 49 ›› Issue (4): 1329-1338.doi: 10.13229/j.cnki.jdxbgxb20180487

• • 上一篇

基于决策粒子群优化与稳定纹理的虹膜二次识别

刘元宁^1,²(),刘帅^1,³,朱晓冬^1,²(),霍光⁴,丁通^1,³,张阔^1,²,姜雪^1,³,郭书君^1,²,张齐贤^1,³

1. 吉林大学符号计算与知识工程教育部重点实验室, 长春 130012
2. 吉林大学计算机科学与技术学院, 长春 130012
3. 吉林大学软件学院, 长春 130012
4. 东北电力大学计算机学院, 吉林省吉林市 132012

收稿日期:2018-05-22 出版日期:2019-07-01 发布日期:2019-07-16
通讯作者: 朱晓冬 E-mail:lyn@jlu.edu.cn;zhuxd@jlu.edu.cn
作者简介:刘元宁（1962-），男，教授，博士生导师. 研究方向：虹膜识别. E-mail:lyn@jlu.edu.cn
基金资助:
国家自然科学基金项目(61471181);吉林省自然科学基金项目(20140101194JC,20150101056JC);吉林省产业创新专项资金项目(2019C053-2);吉林省教育厅科技项目(JJKH20180448KJ)

Iris secondary recognition based on decision particle swarm optimization and stable texture

Yuan-ning LIU^1,²(),Shuai LIU^1,³,Xiao-dong ZHU^1,²(),Guang HUO⁴,Tong DING^1,³,Kuo ZHANG^1,²,Xue JIANG^1,³,Shu-jun GUO^1,²,Qi-xian ZHANG^1,³

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
4. College of Computer Science, Northeast Electric Power University, Jilin 132012, China

Received:2018-05-22 Online:2019-07-01 Published:2019-07-16
Contact: Xiao-dong ZHU E-mail:lyn@jlu.edu.cn;zhuxd@jlu.edu.cn

摘要/Abstract

摘要：

不同时刻虹膜图像的采集状态不同，因此单一识别算法在多类别虹膜识别中的准确率可能较差。本文提出了基于决策粒子群优化与稳定纹理的虹膜二次识别算法。首先，使用6种图像处理算法提取稳定纹理特征。由Gabor滤波与Hamming距离组成首次识别，Haar小波与BP神经网络组成第二次识别，以顺序结构完成多类别虹膜的二次识别。根据马尔可夫决策过程与不同的虹膜库，自适应优化Gabor滤波和神经网络。结果表明，该算法可以有效提高虹膜识别的准确率。

关键词: 计算机应用, 虹膜二次识别, 稳定纹理, 马尔可夫决策过程, 决策粒子群优化

Abstract:

The collection statuses of the iris image are different at different times, so the accuracy of single recognition algorithm in the multi-category iris recognition may be poor.This paper proposes an iris secondary recognition algorithm based on decision particle swarm optimization and stable texture. Use six image processing algorithms to extract stable texture features.The Gabor filtering and Hamming distance constitute the first recognition, and the Haar wavelet and BP neural network constitute the second recognition, complete secondary recognition of multi-category irises by sequence structure.Gabor filtering and neural network are adaptively optimized according to the Markov decision process and different iris libraries.The results show that the proposed algorithm can effectively improve accuracy of iris recognition.

Key words: computer application, iris secondary recognition, stable texture, Markov decision process, decision particle swarm optimization

中图分类号:

TP391.41

刘元宁,刘帅,朱晓冬,霍光,丁通,张阔,姜雪,郭书君,张齐贤. 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.

Yuan-ning LIU,Shuai LIU,Xiao-dong ZHU,Guang HUO,Tong DING,Kuo ZHANG,Xue JIANG,Shu-jun GUO,Qi-xian ZHANG. 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.

图/表 14

图1

图2

图3

图4

图5

图6

图7

表1

表2

表3

表4

图8

表5

图9

参考文献 35

1	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.
	LiXing-guang,SunZhe-nan,TanTie-niu.overview of iris image quality-assessment[J]. Journal of Image and Graphics, 2014, 19(6):813-824.
2	刘元宁,刘帅,朱晓冬,等.基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J].吉林大学学报：工学版, 2018, 48(5):1606-1613.
	LiuYuan-ning,LiuShuai, ZhuXiao-dong,et al.Log operator and adaptive optimization Gabor filtering for iris recognition[J].Journal of Jilin University (Engineering and Technology Edition), 2018, 48(5):1606-1613.
3	刘元宁,刘帅,朱晓冬,等. 基于特征加权融合的虹膜识别算法[J].吉林大学学报:工学版, 2019, 49(1):221-229.
	LiuYuan-ning,LiuShuai, ZhuXiao-dong,et al.Iris recognition algorithm based on feature weighted fusion[J].Journal of Jilin University (Engineering and Technology Edition), 2019, 49(1):221-229.
4	M PankajPruthi.The minimum Hamming distances of the irreducible cyclic codes of length[J].Journal of Discrete Mathematical Sciences and Cryptography, 2016, 19(5/6): 965-995.
5	DengK, XiaoL, XuL,et al.Prediction model of sports performance based on grey BP neural network[J]. International Journal of U-and E-Service, Science and Technology, 2016,9(8):87-96.
6	史雪松,冯辉,杨涛,等.无线传感网络中的离散拉普拉斯算子及数据选择和恢复算法[J].小型微型计算机系统, 2016,37(1):65-71.
	ShiXue-song,FengHui,YangTao,et al.Data selection and recovery based on a customized discrete Laplace operator in wireless sensor networks[J].Journal of Chinese Computer Systems，2016,37(1):65-71.
7	赵海英,张小利,李雄飞,等.基于多尺度Meanshift图像去噪算法[J].吉林大学学报:工学版, 2014,44(5):1417-1422.
	ZhaoHai-ying,ZhangXiao-li,LiXiong-fei,et al.Image denoising algorithm based on multi-scale Meanshift[J]. Journal of Jilin University (Engineering and Technology Edition),2014,44(5):1417-1422.
8	王宏志,武伟,钟诚.基于非线性扩散与小波变换的混合图像去噪算法[J].吉林大学学报:工学版,2009,39(2): 525-529.
	WangHong-zhi,WuWei,ZhongCheng.Image denoising algorithm based on nonlinear diffusion and wavelet transform[J]. Journal of Jilin University (Engineering and Technology Edition),2009,39(2): 525-529.
9	HuoG, LiuY N, ZhuX D, et al.Secondary iris recognition method based on local energy-orientation feature[J].Journal of Electronic Imaging,2015,24(1): 013033.
10	LiuS,LiuY N, ZhuX D,et al.Iris double recognition based on modified evolutionary neural network[J].Journal of Electronic Imaging,2017,26(6):063023.
11	刘帅, 刘元宁, 朱晓冬, 等. 蚁群变异粒子群优化的2次虹膜识别[J].计算机辅助设计与图形学学报, 2018, 30(9):1604-1614.
	LiuShuai, LiuYuan-ning, ZhuXiao-dong,et al.Ant colony mutation particle swarm optimization for secondary iris recognition[J].Journal of Computer-Aided Design & Computer Graphics, 2018, 30(9):1604-1614.
12	DongH X,ZhuX D,LiuY N,et al.Iris recognition based on CPSO algorithm for optimizing multichannel gabor parameters[J].Journal of Computational Information Systems, 2015,11(1):333-340.
13	蔺想红,王向文,张宁,等.脉冲神经网络的监督学习算法研究综述[J].电子学报,2015,43(3):577-585.
	LinXiang-hong,WangXiang-wen,ZhangNing.Supervised learning algorithms for spiking neural networks:a review[J].Acta Electronica Sinica,2015,43(3):577-585.
14	刘帅, 刘元宁, 朱晓冬, 等.基于形态学与灰度分布的序列虹膜质量评价算法[J].吉林大学学报：理学版, 2018,56(5):1156-1162.
	LiuShuai, LiuYuanning, ZhuXiaodong,et al. Sequence Iris Quality Evaluation Algorithm Based on Morphology and Grayscale Distribution[J]. Journal of Jilin University (Science Edition),2018,56(5):1156-1162.
15	YuHan, ZhangXiu-jie,WangShuo,et al.Alternative framework of the Gaussian filter for non-linear systems with synchronously correlated noises[J].IET Science, Measurement and Technology, 2016,10(4): 306-315.
16	李振兴,刘进忙,李松,等.基于箱式粒子滤波的群目标跟踪算法[J].自动化学报,2015,41(4):785-798.
	LiZhen-xing,LiuJin-mang,LiSong,et al.Group targets tracking algorithm based on box particle filter[J].Acta Automatica Sinica,2015,41(4):785-798.
17	KhanS,LeeD H.An adaptive dynamically weighted median filter for impulse noise removal[J].Eurasip Journal on Advances in Signal Processing,2017(1):67.
18	LengXiang-guang,JiKe-feng,XingXiang-wei,et al. Hybrid bilateral filtering algorithm based on edge detection[J].IET Image Processing,2016,10(11):809-816.
19	Nayak Deepak Ranjan, RatnakarDash , BanshidharMajhi .Discrete ripplet-II transform and modified PSO based improved evolutionary extreme learning machine for pathological brain detection[J]. Neurocomputing, 2018,282:232-247.
20	XuS P,HuL Y,YangX H .Quality-aware features-based noise level estimator for block matching and three-dimensional filtering algorithm[J].Journal of Electronic Imaging,2016,25(1):013029.
21	禹建丽,黄鸿琦,苗满香.基于主成分分析与神经网络的多响应参数优化[J].系统仿真学报, 2018,30(1): 176-183.
	YuJian-li,HuangHong-qi,MiaoMan-xiang. Multi- response parameters optimization based on PCA and neural network[J].Journal of System Simulation, 2018, 30(1): 176-183.
22	朱军,许倩,易辉跃,等.节点删除法的虚拟网络映射算法[J].安徽大学学报:自然科学版,2014,38(5):37-43.
	ZhuJun, XuQian,YiHui-yue,et al.Virtual network mapping algorithm of node deletion[J].Journal of Anhui University(Natural Sciences),2014,38(5):37-43.
23	ShaoX L, WangH L, LiuJ, et al. Sigmoid function based integral-derivative observer and application to autopilot design[J].Mechanical Systems and Signal Processing, 2017 ,84 , 113-127.
24	BarpandaS S, SaP K ,MarquesO, et al. Iris recognition with tunable filter bank based feature[J].Multimedia Tools and Applications, 2018, 77(6): 7637-7674.
25	周从华, 邢支虎, 刘志锋, 等. 马尔可夫决策过程的限界模型检测[J]. 计算机学报, 2013 36(12): 2587-2600.
	ZhouCong-hua, XingZhi-hu, LiuZhi-feng, et al. Bounded model checking for Markov decision processes[J]. Chinese Journal of Computers, 2013 36(12): 2587-2600.
26	吉林大学生物识别与信息安全技术实验室.虹膜库[EB/OL]. ，2018.
27	中科院自动化研究所.虹膜库[EB/OL]. .
28	董宏兴.基于自适应Gabor滤波的虹膜特征提取与识别方法研究[D].长春:吉林大学计算机科学与技术学院,2016.
	DongHong-xing.Research on iris feature extraction and recognition based on the adaptive Gabor filtering [D]. Changchun:School of Computer Science and Technology, Jilin University, 2016.
29	JohnD. High confidence visual recognition of persons by a test of statistical independence[J]. IEEE Transactions, 1993, PAMI-15(11):1148-1161.
30	姚鹏, 叶学义, 张文聪,等. 基于改进的Log-Gabor小波的虹膜识别算法[J]. 计算机辅助设计与图形学学报,2007, 19(5):563-567,574.
	YaoPeng, YeXue-yi, ZhangWen-cong,et al.Iris recognition using modified Log-Gabor wavelets[J]. Journal of Computer-Aided Design & Computer Graphics,2007, 19(5):563-567,574.
31	DonaldM M, SoumyadipR, ZhangD X. DCT-Based iris recognition[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29(4):586-595.
32	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.
	LiHuan-li, GuoLi-hong, LiXiao-ming, et al.Iris recognition based on SCCS-LBP[J].Optics and Precision Engineering,2013, 21(8): 2129-2136.
33	TanC W,KumarA.Accurate iris recognition at a distance using stabilized iris encoding and zernike moments phase features[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2014, 23(9): 3962-3974.
34	HeF,HanY,WangH,et al. Deep learning architecture for iris recognition based on optimal Gabor filters and deep belief network[J].Journal of Electronic Imaging, 2017, 26(2): 023005.
35	NallaP R，KumarA.Toward more accurate iris recognition using cross-spectral matching[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2016, 26 (1) :208.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

序号	D₁	D₂	M	F
1	增加	增加	增加	增加
2	增加	增加	增加	减小
3	增加	增加	减小	增加
4	增加	减小	增加	增加
5	减小	增加	增加	增加
6	减小	减小	增加	增加
7	减小	增加	减小	增加
8	减小	增加	增加	减小
9	增加	减小	减小	增加
10	增加	减小	增加	减小
11	增加	增加	减小	减小
12	增加	减小	减小	减小
13	减小	增加	减小	减小
14	减小	减小	增加	减小
15	减小	减小	减小	增加
16	减小	减小	减小	减小

虹膜库	类别数	单类别图像数	图像总数	匹配数
虹膜库	类别数	单类别图像数	图像总数	类间	类外	总数
JLU?4.0	150	200	30 000	60 000	150 000	210 000
Iris?Lamp	411	40	16 440	30 000	100 000	130 000

算法	JLU-4.0		CASIA-Iris-Lamp
算法	CRR/%	EER/%	CRR/%	EER/%
Daugman	93.48	3.84	94.26	3.27
Lim	94.59	3.48	94.13	3.16
Yao	98.75	1.24	98.23	1.79
Donald	98.13	1.92	98.53	1.51
Li	98.65	1.36	98.42	1.44
二次识别	99.47	0.73	99.16	0.94

虹膜库	类别数	单类别图像数	图像总数	匹配数
虹膜库	类别数	单类别图像数	图像总数	类间	类外	总数
JLU?5.0	100	100	10 000	16 000	51 300	67 300
Iris?Interval	200	15	3 000	8 565	25 462	34 027

算法	JLU?5.0		Iris?Interval
算法	CRR/%	EER/%	CRR/%	EER/%
决策优化+二次识别	97.13	2.95	98.62	1.47
稳定特征+二次识别	98.42	1.65	98.96	1.05
Zernike矩相位特征	98.78	1.36	97.83	2.63
深度学习架构	96.45	3.64	97.03	3.19
交叉光谱匹配	97.84	2.61	98.27	1.75
稳定特征+决策优化+二次识别	99.21	0.89	99.43	0.78

基于决策粒子群优化与稳定纹理的虹膜二次识别

Iris secondary recognition based on decision particle swarm optimization and stable texture

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 35

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	李雄飞,宋璐,张小利. 基于协同经验小波变换的遥感图像融合[J]. 吉林大学学报(工学版), 2019, 49(4): 1307-1319.
[2]	孙延君,申铉京,陈海鹏,赵永哲. 基于局部平面线性点的翻拍图像鉴别算法[J]. 吉林大学学报(工学版), 2019, 49(4): 1320-1328.
[3]	王楠,李金宝,刘勇,张玉杰,钟颖莉. TPR⁃TF:基于张量分解的时间敏感兴趣点推荐模型[J]. 吉林大学学报(工学版), 2019, 49(3): 920-933.
[4]	刘富,宗宇轩,康冰,张益萌,林彩霞,赵宏伟. 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报(工学版), 2018, 48(6): 1844-1850.
[5]	王利民,刘洋,孙铭会,李美慧. 基于Markov blanket的无约束型K阶贝叶斯集成分类模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1851-1858.
[6]	金顺福,王宝帅,郝闪闪,贾晓光,霍占强. 基于备用虚拟机同步休眠的云数据中心节能策略及性能[J]. 吉林大学学报(工学版), 2018, 48(6): 1859-1866.
[7]	赵东,孙明玉,朱金龙,于繁华,刘光洁,陈慧灵. 结合粒子群和单纯形的改进飞蛾优化算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1867-1872.
[8]	刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[9]	欧阳丹彤, 范琪. 子句级别语境感知的开放信息抽取方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1563-1570.
[10]	刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[11]	桂春, 黄旺星. 基于改进的标签传播算法的网络聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1600-1605.
[12]	刘元宁, 刘帅, 朱晓冬, 陈一浩, 郑少阁, 沈椿壮. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1606-1613.
[13]	车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[14]	赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[15]	黄辉, 冯西安, 魏燕, 许驰, 陈慧灵. 基于增强核极限学习机的专业选择智能系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.