首页 > 论文 > 激光与光电子学进展 > 55卷 > 5期(pp:51012--1)

基于BSLDP和典型相关分析的掌纹掌脉融合识别

Palmprint and Palm Vein Feature Fusion Recognition Based on BSLDP and Canonical Correlation Analysis

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对非接触采集图像时容易出现模糊,导致识别系统稳健性下降、识别效果不佳的问题,提出一种基于分块增强局部方向模式(BSLDP)和典型相关分析的掌纹掌脉融合识别方法。首先对传统局部方向模式(LDP)进行了改进,提出BSLDP来获取掌纹掌脉图像的纹理方向特征,然后基于典型相关分析法实现掌纹掌脉特征的有效融合,最后根据融合特征向量间的卡方距离进行匹配识别,并在CASIA-M图库及自建非接触图库上进行实验测试,最小等误率分别为0.63%和1.21%。结果表明与其他传统及最新算法相比,本文方法能够消除冗余信息、准确地保留掌纹掌脉的有效特征信息,提高系统识别性能。

Abstract

Aiming at the problems of non-contact images acquisition such as blur phenomenon, poor system identification systems and poor recognition effect, a palmprint and palm vein feature fusion recognition method based on block strengthened local directional pattern(BSLDP) and canonical correlation analysis is proposed. Firstly, we improve the traditional local directional pattern(LDP),and proposed the BSLDP algorithm to obtain the texture direction feature of palmprint and palm vein images. Secondly, the palmprint and palm vein feature fusion is realized effectively based on the canonical correlation analysis. Finally, the match identification is realized based on the chi-square distance. The experimental results show that the equal error rate is only 0.63% and 1.21% in the CASIA-M and the self-built non-contact image database. The results indicate that compared with other traditional and newest algorithms, the proposed method can eliminate redundant information, retain accurate feature information of palmprint and palm vein and improve system identification performance.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/lop55.051012

所属栏目:图像处理

基金项目:辽宁省教育厅科学研究一般项目(L2014132)、辽宁省自然科学基金面上项目(2015020100)

收稿日期:2017-09-29

修改稿日期:2017-11-30

网络出版日期:--

作者单位    点击查看

李新春:辽宁工程技术大学电子与信息工程学院, 辽宁 葫芦岛 125105
张春华:辽宁工程技术大学研究生学院, 辽宁 葫芦岛 125105
林森:辽宁工程技术大学电子与信息工程学院, 辽宁 葫芦岛 125105

联系人作者:张春华(1226617885@qq.com)

备注:李新春(1963—),男,本科,高级工程师,硕士生导师,主要从事无线传感器网络、数字图像处理等方面的研究。E-mail: lixinchun@lntu.edu.cn

【1】Amiruddin A B, Khalifa O O, Rabih F A F. Performance evaluation of human identification based on ECG signal[C]∥Proceedings of International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering, 2015: 479-484.

【2】Aravinth J, Valarmathy S. Multi classifier-based score level fusion of multi-modal biometric recognition and its application to remote biometrics authentication[J]. The Imaging Science Journal, 2016, 64(1): 1-14.

【3】Naderi H, Soleimani B H, Matwin S, et al. Fusing iris,palmprint and fingerprint in a multi-biometric recognition system[C]∥Proceedings of 13th Conference on Computer and Robot Vision, 2016: 327-334.

【4】Li Z N, Zhong C L, Yang L M. A non-contact method and apparatus of the fingerprint 3D: 106127172A[P]. 2016-11-16.
李治农, 仲崇亮, 杨李木. 一种非接触3D指纹采集的装置及方法: 106127172A[P]. 2016-11-16.

【5】Zhao S. Fuzzy image recognition algorithm based on SIFT operator[D]. Suzhou: Soochow University, 2014.
赵帅. 基于SIFT算子的模糊图像识别算法[D]. 苏州: 苏州大学, 2014.

【6】Wang J G, Yau W Y, Suwandy A, et al. Fusion of palmprint and palm vein images for person recognition based on "Laplacianpalm" feature[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2007: 1-8.

【7】Lin S, Zhang J Y, Guo J Y, et al. Application of local direction pattern in non-contact palmprint recognition[J]. Chinese Journal of Scientific Instrument, 2015, 36(1): 201-208.
林森, 张俊宇, 郭金玉, 等. 局部方向模式在非接触掌纹识别中的应用[J]. 仪器仪表学报, 2015, 36(1): 201-208.

【8】Sang H F, Wu H J, He D K. Hand shape,palmprint and palm vein multimodal fusion recognition[J]. Chinese Journal of Scientific Instrument, 2015, 36(6): 1356-1362.
桑海峰, 武红娇, 何大阔. 手形、掌纹和掌静脉多特征融合识别[J]. 仪器仪表学报, 2015, 36(6): 1356-1362.

【9】Chen P, Sun Z H, Dang Y J, et al. A palmprint palm vein image layer fusion method based on wavelet transform and Gabor filter: 01610298658.4[P]. 2016-10-12.
陈朋, 孙中海, 党源杰, 等. 一种基于小波变换和Gabor滤波器的掌纹掌静脉图像层融合方法: 201610298658.4[P]. 2016-10-12.

【10】Hui X W, Zhang J Y, Lin S, et al. Application of improved local directional pattern in palm vein recognition[J]. Laser & Optoelectronics Progress, 2015, 52(7): 071001.
惠晓威, 张俊宇, 林森, 等. 改进局部方向模式在掌脉识别中的应用[J]. 激光与光电子学进展, 2015, 52(7): 071001.

【11】Xu T, Wu Q, Niu H Q, et al. An improved algorithm based on infrared image edge extraction of cable terminal[J]. Insulators and Surge Arresters, 2016(6): 26-31.
徐涛, 吴倩, 牛海清, 等. 一种改进的瓷套式电缆终端红外图像边缘提取算法[J]. 电瓷避雷器, 2016(6): 26-31.

【12】Lang Y. An improved Sobel edge detection operator[J]. Light Industry Science and Technology, 2011, 27(5): 59-60.
郎瑶. 一种改进的Sobel边缘检测算子[J]. 轻工科技, 2011, 27(5): 59-60.

【13】Wilms I, Croux C. Robust sparse canonical correlation analysis[J]. BMC Systems Biology, 2016, 10(10): 72.

【14】Yang X F. Palmprint and vein feature fusion algorithm[D]. Beijing: Beijing Jiaotong University, 2017.
杨晓凤. 掌纹和静脉特征融合算法的研究[D]. 北京: 北京交通大学, 2017.

【15】Xu T Y, Hui X W, Lin S. A near infrared finger vein recognition approach based on wavelet grayscale surface matching[J]. Laser & Optoelectronics Progress, 2016, 53(4): 041005.
徐天扬, 惠晓威, 林森. 基于小波灰度曲面的近红外手指静脉识别方法[J]. 激光与光电子学进展, 2016, 53(4): 041005.

【16】Lin S, Wang Y, Xu T, et al. Palmprint and palm vein multimodal fusion biometrics based on MMNBP[C]∥Proceedings of 11th Chinese Conference on Biometric Recognition, 2016: 326-336.

【17】Li C F, Chen X H. Vehicle type recognition based on combining local binary pattern and Hu matrix feature[J]. Laser & Optoelectronics Progress, 2016, 53(10): 101503.
李澄非, 陈新华. 融合局部二值模式和Hu矩特征的车型识别[J]. 激光与光电子学进展, 2016, 53(10): 101503.

【18】Xia J, Pei D, Wang Q Z, et al. Face recognition based on local adaptive ternary derivative[J]. Laser & Optoelectronics Progress, 2016, 53(11): 111004.
夏军, 裴东, 王全州, 等. 融合Gabor特征的局部自适应三值微分模式的人脸识别[J]. 激光与光电子学进展, 2016, 53(11): 111004.

【19】Yuan L, Huang J, Liu Y Q, et al. Developed palm vein image enhancement based on image fusion[J]. Science Technology and Engineering, 2016, 16(36): 48-54.
袁玲, 黄靖, 刘娅琴, 等. 基于图像融合的去掌纹手掌静脉图像增强方法[J]. 科学技术与工程, 2016, 16(36): 48-54.

引用该论文

Li Xinchun,Zhang Chunhua,Lin Sen. Palmprint and Palm Vein Feature Fusion Recognition Based on BSLDP and Canonical Correlation Analysis[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051012

李新春,张春华,林森. 基于BSLDP和典型相关分析的掌纹掌脉融合识别[J]. 激光与光电子学进展, 2018, 55(5): 051012

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF