计算机科学 ›› 2021, Vol. 48 ›› Issue (6A): 57-62.doi: 10.11896/jsjkx.200900218

• 图像处理&多媒体技术 • 上一篇    下一篇

基于小波包分析的虹膜识别研究

周俊1,2, 王帅3, 刘凡漪4   

  1. 1 中国人民解放军陆军勤务学院信息工程系 重庆401331
    2 重庆现代服务业研究中心 重庆401331
    3 中国人民解放军陆军勤务学院基础部基础实验中心 重庆401331
    4 重庆交通大学 重庆400074
  • 出版日期:2021-06-10 发布日期:2021-06-17
  • 通讯作者: 刘凡漪(470926161@qq.com)
  • 作者简介:hgzhou2008@163.com
  • 基金资助:
    重庆市教育委员会科学技术研究计划(KJZD-K202004401,KJZD-K201904401);重庆商务职业学院人工智能技术应用协同创新中心资助项目

Research on Iris Recognition Algorithm Based on Wavelet Packet Decomposition

ZHOU Jun1,2, WANG Shuai3, LIU Fan-yi4   

  1. 1 Department of Information Engineering,Army Service College,Chongqing 401331,China
    2 Chongqing Modern Service Industry Research Center,Chongqing 401331,China
    3 Basic Laboratory Center,Army Service College,Chongqing 401331,China
    4 Chongqing Jiaotong University,Chongqing 400074,China
  • Online:2021-06-10 Published:2021-06-17
  • About author:ZHOU Jun,born in 1981,doctoral candidate,senior engineer,is a member of China Computer Federation.His main research interests include signal processing and artificial intelligence.
  • Supported by:
    Science and Technology Research Program of Chongqing Municipal Education Commission(KJZD-K201904401,KJZD-K202004401) and Artificial Intelligence Application Collaborative Innovation Center of Chongqing Business Vocational College.

摘要: 虹膜特征提取是虹膜识别中的关键环节。小波方法在提取虹膜特征时未对分解后的高频空间进一步细化分解,而虹膜纹理特征较多地蕴含在高频空间中,因此提取的虹膜特征在表示特征能力上存在不足。针对此类问题,提出一种基于小波包多尺度分解的虹膜识别方法,利用阈值将小波包分解后第二层对角高频子带图调制为虹膜特征码,利用海明距离对特征进行识别。对108类人眼虹膜图像进行特征提取与匹配,分解小波采用sym2小波,共进行5 350次特征匹配,正确识别率达到98.5%,在识别性能上优于Boles的小波变换过零点法和Lim的二维Haar小波变换法,仅次于Daugman的二维Gabor方法。

关键词: 小波包, 分解, 对角高频, 阈值化, 虹膜特征

Abstract: Iris feature extraction is the key step in iris recognition.The wavelet method does not further decompose the high-frequency space when decomposing the iris image,but the iris features are more contained in the high-frequency space,and the extracted iris features are insufficient in the feature expression capabilities.Aiming at the above problems,an iris feature recognition method based on wavelet packet multi-scale decompositionis proposed in this paper,diagonal high-frequency subband map from the second layer based on wavelet packet de-composition is modulated into iris feature code,and the feature is recognized through hamming distance.In the experiment,sym2 wavelet is used as decomposition wavelet function,which carries out 5350 times of feature matching.The results show that the correct recognition rate is 98.5%,which is superior to the wavelet zero crossing method of boles and the two-dimensional Haar wavelet transform method of Lim,is second only to the two-dimensional Gabor method of Daugman.

Key words: Wavelet packet, Decomposition, Diagonal high-frequency, Threshold, Iris features

中图分类号: 

  • TP391.5
[1] TIAN Q C,ZHANG R S.Overview of biometric recog-nition technology [J].Computer Application Research,2010,26(12):4401-4410.
[2] DAUGMAN J.High confidence visual recognition of persons by a test of statistical independence[J],IEEE Transactions on Pattern Analysis Machine Intelligence,1993,15(11):1148-1161.
[3] WILDES R,ASMUTH J C.A system for automated iris recognition[C]//Proceedings of the 2nd IEEE Workshop on Applicant Computer Vision.Sarasota,FL USA,1994:121-128.
[4] HE F,HAN Y,WANG H,et al.Deep learning architecture for iris recognition based on optimal Gabor filters and belief network[J].Journal of Electronic Imaging,2017,26(2):023005.
[5] YANG X,ZHU X D,LIU Y N,et al.Iris recognition methodbased on block wavelet feature combined with BP neural network [J].Computer Engineering and Applications,2019,55(18):132-139.
[6] ZHENG Y P,LI G Y,LI Y.A review of research on the application of deep learning in image recognition[J].Computer Engineering and Applications,2019,55(12):20-36.
[7] LIMS S,LEE K,BYEON O,et al.Efficient iris recognitionthrough improvement of feature vector and classifier[J].ETRI Journal,2001,23(2):61-70.
[8] BOLES W W,BOASHASH B.A human identification techni-que using images of the iris and wavelet transform[J].IEEE Transactions on Signal Processing,1998,46(4):1185-1188.
[9] BAIY C.Research on iris recognition method of visible lightmobile terminal [D].Shenyang:Shenyang University of Technology,2019.
[10] KANG B J,PARK K R.A robust eyelash detection based on iris focus assessment [J].Pattern Recognition,2007,28(13):1630-1639.
[11] DAUGMAN J.Statistical richness of visual phase information:Update on recognizing persons by iris patterns[J].International Journal of Computer Vision,2001,45(1):25-38.
[12] MA L,TAN T,WANG Y,et al.Personal Recognition Based on Iris Texture Analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(12):1519-1533.
[13] MASEK L.Recognition of human iris patterns for biometricidentification[R].Technical Report,School of Computer Science and Software Engineering,University of Western Australia,2003.
[14] YANG J G.Wavelet analysis and its engineering application[M].Beijing:Mechanical Industry Press,2009.
[15] SUNG H,LIM J,PARK J.Iris Recognition Using CollaretteBoundary Localization[C]//Proceedings of the 17th International Conference on Pattern Recognition.Washington,DC,USA 2004:857-860.
[16] FU H Z,XU Y W,LIN S,et al.Angle-Closure Detection in Anterior Segment OCT Based on Multilevel DeepNetwork[J].IEEE Transactions on Cybernetics,2020,50(7).
[17] 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):063023.
[18] TIAN Q C.Principle and Algorithm of Iris Recognition [M].Beijing:National Defense Industry Press,2010.
[19] JIANG H,MENG D T.Iris recognition based on CS-LBPand adaptive neural network[J].Journal of Northeast Normal University (Natural Science Edition),2018,50(3):58-64.
[20] Institute of Automation,Chinese Academy of Sciences.CASIA iris image database [EB/OL].(2007-12-23).http://www.cbsr.ia.ac.cn/English/Irisdatabase.asp.
[1] 邵超, 宋淑米. 基于信任关系下用户兴趣偏好的协同过滤推荐算法[J]. 计算机科学, 2021, 48(6A): 240-245.
[2] 段菲, 王慧敏, 张超. 面向数据表示的Cauchy非负矩阵分解[J]. 计算机科学, 2021, 48(6): 96-102.
[3] 钟岳, 方虎生, 张国玉, 王钊, 朱经纬. 基于9轴姿态传感器的CNN旗语动作识别方法[J]. 计算机科学, 2021, 48(6): 153-158.
[4] 宋慧超, 刘晓楠, 王洪, 尹美娟, 江舵. 基于Grover搜索算法的整数分解[J]. 计算机科学, 2021, 48(4): 20-25.
[5] 郝志峰, 廖祥财, 温雯, 蔡瑞初. 基于多上下文信息的协同过滤推荐算法[J]. 计算机科学, 2021, 48(3): 168-173.
[6] 李雨蓉, 刘杰, 刘亚林, 龚春叶, 王勇. 面向语音分离的深层转导式非负矩阵分解并行算法[J]. 计算机科学, 2020, 47(8): 49-55.
[7] 杨德成, 李凤岐, 王祎, 王胜法, 殷慧殊. 智能3D打印路径规划算法[J]. 计算机科学, 2020, 47(8): 267-271.
[8] 刘君良, 李晓光. 个性化推荐系统技术进展[J]. 计算机科学, 2020, 47(7): 47-55.
[9] 李向利, 贾梦雪. 基于预处理的超图非负矩阵分解算法[J]. 计算机科学, 2020, 47(7): 71-77.
[10] 吴静, 周先春, 徐新菊, 黄金. 三维块匹配波域调和滤波图像去噪[J]. 计算机科学, 2020, 47(7): 130-134.
[11] 方梦琳, 唐文兵, 黄鸿云, 丁佐华. 基于模糊信息分解与控制规则的移动机器人沿墙导航[J]. 计算机科学, 2020, 47(6A): 79-83.
[12] 赵晓东, 苏公瑾, 李克利, 成杰, 徐江峰. 一种融合EMD分解和LSTM网络的频谱占用度预测模型[J]. 计算机科学, 2020, 47(6A): 294-298.
[13] 张德干, 范洪瑞, 龚倡乐, 高瑾馨, 张婷, 赵彭真, 陈晨. 一种基于张量的车辆交通数据缺失估计新方法[J]. 计算机科学, 2020, 47(6A): 505-511.
[14] 马海江. 基于卷积神经网络与约束概率矩阵分解的推荐算法[J]. 计算机科学, 2020, 47(6A): 540-545.
[15] 刘纪芹, 史开泉. 大数据分解-融合及其智能获取[J]. 计算机科学, 2020, 47(6): 66-73.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 方磊, 武泽慧, 魏强. 二进制代码相似性检测技术综述[J]. 计算机科学, 2021, 48(5): 1 -8 .
[2] 朱雨, 庞建民, 徐金龙, 陶小涵, 王军. 面向SW26010处理器的三维Stencil自适应分块参数算法[J]. 计算机科学, 2021, 48(6): 10 -18 .
[3] 冯芙蓉, 张兆功. 目标轮廓检测技术新进展[J]. 计算机科学, 2021, 48(6A): 1 -9 .
[4] 孙正, 张小雪. 生物光声成像中声反射伪影抑制方法的研究进展[J]. 计算机科学, 2021, 48(6A): 10 -14 .
[5] 周欣, 刘硕迪, 潘薇, 陈媛媛. 自然交通场景中的车辆颜色识别[J]. 计算机科学, 2021, 48(6A): 15 -20 .
[6] 黄雪冰, 魏佳艺, 沈文宇, 凌力. 基于自适应加权重复值滤波和同态滤波的MR图像增强[J]. 计算机科学, 2021, 48(6A): 21 -27 .
[7] 江妍, 马瑜, 梁远哲, 王原, 李光昊, 马鼎. 基于分数阶麻雀搜索优化OTSU肺组织分割算法[J]. 计算机科学, 2021, 48(6A): 28 -32 .
[8] 张子丞, 谭志苇, 张晨瑞, 王旋, 刘晓璇, 俞一彪. 基于高低频带对数能量谱比贝叶斯决策的语音端点检测[J]. 计算机科学, 2021, 48(6A): 33 -37 .
[9] 崔雯昊, 蒋慕蓉, 杨磊, 傅鹏铭, 朱凌霄. 结合MCycleGAN与RFCNN实现太阳斑点图高分辨重建[J]. 计算机科学, 2021, 48(6A): 38 -42 .
[10] 田洋, 毕秀丽, 肖斌, 李伟生, 马建峰. 基于离散切比雪夫变换的图像接缝裁剪篡改检测[J]. 计算机科学, 2021, 48(6A): 43 -50 .