广东工业大学学报 ›› 2022, Vol. 39 ›› Issue (03): 55-62.doi: 10.12052/gdutxb.210023

• • 上一篇    下一篇

余弦相似度保持的掌纹识别算法

丘展春, 费伦科, 滕少华, 张巍   

  1. 广东工业大学 计算机学院, 广东 广州 510006
  • 收稿日期:2021-03-03 出版日期:2022-05-10 发布日期:2022-05-19
  • 通信作者: 费伦科(1982-),男,副教授,博士,主要研究方向为机器学习和生物特征识别,E-mail:flksxm@126.com
  • 作者简介:丘展春(1995–)，男，硕士研究生，主要研究方向为掌纹识别
  • 基金资助:
    国家自然科学基金资助项目(62176066，61972102)；广东省自然科学基金资助项目(2019A1515011811)；广东省重点研发计划项目(2020B010166006)；广州市科技计划项目(202002030110)

Palmprint Recognition Based on Cosine Similarity

Qiu Zhan-chun, Fei Lun-ke, Teng Shao-hua, Zhang Wei   

  1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2021-03-03 Online:2022-05-10 Published:2022-05-19

HTML

PDF (PC)

2270

摘要： 掌纹识别作为一种新兴的生物特征识别技术，具有识别率高、特征稳定等优点。传统的基于手工提取特征的掌纹识别算法使用先验知识提取掌纹主线和细节点，存在可扩展性低、提取图像特征困难、无法挖掘数据的隐藏信息等问题。为了解决这些问题，本文提出了一种基于学习的掌纹识别算法。首先提取掌纹图像的像素值差向量(Pixel Different Vector，PDV)特征。然后，通过余弦相似度保持模型，同时学习PDV特征的二进制表示及其映射函数，以减少PDV特征的信息冗余。最后，为了处理掌纹位置偏移和光照变化等噪音，将学习得到的二进制特征编码成直方图描述子。在3个广泛使用的掌纹数据库上的实验结果表明，所提出的算法能更好地挖掘掌纹图像的内在特征，有效地提高掌纹识别精度。

关键词: 计算机图像处理, 生物特征识别, 掌纹识别, 特征提取

Abstract: Palmprint recognition, as a promising biometric recognition technology, has the advantages of high recognition accuracy and stable characteristics. Conventional hand-craft based palmprint recognition methods extract the principal lines and minutiae points depending on prior knowledge, which suffer from various limitations, such as the difficulties of scalability, feature extraction and information learning. To address this, a learning-based palmprint recognition method is proposed. Specifically, the Pixel Different Feature (PDV) feature is first extracted from palmprint image. Then, the binary representation and projection function based on PDV features is simultaneously learned via a cosine similarity preserving model. To alleviate the effects of noise such as palmprint position shifting and illumination changing, the binary representation is finally converted into a histogram descriptor. The experimental results on three widely used palmprint databases demonstrate that the proposed method can better excavate the intrinsic structure of palmprint images and significantly improve the performance of palmprint recognition.

Key words: computer image processing, biometric recognition, palmprint recognition, feature extraction

中图分类号: 

  • TP391.4
[1] ANIL K, KARTHIK N, ARUN R. 50 years of biometric research: accomplishments, challenges, and opportunities [J]. Pattern Recognition Letters, 2016, 79(1): 80-105.
[2] 钟德星, 朱劲松, 杜学峰. 掌纹识别综述[J]. 模式识别与人工智能, 2019, 32(5): 436-445.
ZHONG D X, ZHU J S, DU X F. Progress of palmprint recognition: a review [J]. Pattern Recognition and Artificial Intelligence, 2019, 32(5): 436-445.
[3] DING Y H, ZHUANG D, WANG K. A study of hand vein recognition method[C]//IEEE International Conference Mechatronics and Automation. Niagara Falls: IEEE, 2005: 2106-2110.
[4] KUMAR A, WONG D C M, SHEN H C, et al. Personal verification using palmprint and hand geometry biometric[C]// International Conference on Audio and Video Based Biometric Person Authentication. Berlin: Springer, 2003: 668-678.
[5] ZHOU M, ZHANG X, YIN F, et al. Discriminative quadratic feature learning for handwritten Chinese character recognition [J]. Pattern Recognition, 2016, 49(1): 7-18.
[6] SARKAR S, PHILLIPS P J, LIU Z, et al. The humanoid gait challenge problem: data sets, performance, and analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(2): 162-177.
[7] SHU W, ZHANG D. Automated personal identification by palmprint [J]. Optical Engineering, 1998, 37(8): 2359-2362.
[8] ZHANG D, SHU W. Two novel characteristics in palmprint verification: datum point invariance and line feature matching [J]. Pattern Recognition, 1999, 32(4): 691-702.
[9] ZHANG D, KONG W K, YOU J, et al. Online palmprint identification [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(9): 1041-1050.
[10] DAI J, ZHOU J, MEMBER S. Multifeature-based high-resolution palmprint recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 945-957.
[11] FEI L, TENG S, WU J. Enhanced minutiae extraction for high-resolution [J]. International Journal of Image and Graphics, 2017, 17(4): 1-15.
[12] BOUNNECHE M, BOUBCHIR L, BOURIDANE A, et al. Multi-spectral palmprint recognition based on oriented multiscale log-gabor filters [J]. Neurocomputing, 2016, 205(9): 274-286.
[13] GUO Z, ZHANG D, ZHANG L, et al. Feature band selection for online multispectral palmprint recognition [J]. IEEE Transactions on Information Forensics and Security, 2012, 7(3): 1094-1099.
[14] ZHANG D, GUO Z, LU G, et al. An online system of multispectral palmprint verification [J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(2): 480-490.
[15] ZHANG D, LU G, LI W, et al. Palmprint recognition using 3-d information [J]. IEEE Transactions on Systems Man and Cybernetics-Part C, 2009, 39(5): 505-519.
[16] ZHANG D, KANHANGAD V, LUO N, et al. Robust palmprint verification using 2D and 3D features [J]. Pattern Recognition, 2010, 43(1): 358-368.
[17] 林森, 苑玮琦. 掌纹感兴趣区域定位与选择方法[J]. 计算机工程与应用, 2011, 47(14): 21-24.
LIN S, YUAN W Q. Survey on orientation and selection methods for palmprint region of interest [J]. Computer Engineering and Applications, 2011, 47(14): 21-24.
[18] HUANG D, JIA W, ZHANG D. Palmprint verification based on principal lines [J]. Pattern Recognition, 2008, 41(4): 1316-1328.
[19] SUN Z, TAN T, WANG Y, et al. Ordinal palmprint representation for personal identification[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 279-284.
[20] KONG A W K, ZHANG D. Competitive coding scheme for palmprint verification[C] //Proceedings of 17th International Conference on Pattern Recognition. Cambridge: IEEE, 2004: 520-523.
[21] XU Y, FEI L K, WEN J, et al. Discriminative and robust competitive code for palmprint recognition [J]. IEEE Transactions on Systems Man and Cybernetics Systems, 2018, 48(2): 232-241.
[22] GUO Z H, ZHANG D, ZHANG L, et al. Palmprint verification using binary orientation co-occurrence vector [J]. Pattern Recognition Letter, 2009, 30(13): 1219-1227.
[23] ZHENG Q, KUMAR A, PAN G. A 3D feature descriptor recovered from a single 2D palmprint image [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(6): 1272-1279.
[24] FEI L, ZHANG B, ZHANG W, et al. Local apparent and latent direction extraction for palmprint recognition [J]. Information Sciences, 2019, 473: 59-72.
[25] JIA W, HU R X, LEI Y K, et al. Histogram of oriented lines for palmprint recognition [J]. IEEE Transactions on Systems Man and Cybernetics:Systems, 2013, 44(3): 385-395.
[26] ZHAO S P, ZHANG B. Learning complete and discriminative direction pattern for robust palmprint recognition [J]. IEEE Transactions on Image Processing, 2021, 30(6): 1001-1014.
[27] FEI L K, ZHANG B, ZHANG L. Learning compact multifeature codes for palmprint recognition from a single training image per palm [J]. IEEE Transactions on Multimedia, 2020, 44(3): 385-395.
[28] LU G M, ZHANG D, WANG K Q. Palmprint recognition using eigenpalms features [J]. Pattern Recognition Letters, 2003, 24(9): 1463-1467.
[29] 裴昱, 温洁嫦. 基于独立分量分析的一种改进的掌纹识别算法[J]. 广东工业大学学报, 2010, 27(1): 51-54.
PEI Y, WEN J C. An improved method of palmprint recognition based on independent component analysis [J]. Journal of Guangdong University of Technology, 2010, 27(1): 51-54.
[30] HU D W, FENG G Y, ZHOU Z T. Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition [J]. Pattern Recognition, 2007, 40(1): 339-342.
[31] SVOBODA J, MASCI J, BRONSTEIN M M. Palmprint recognition via discriminative index learning[C] //International Conference on Pattern Recognition. Cancun: IEEE, 2017: 4232-4237.
[32] ZHANG L, CHENG Z X, SHEN Y, et al. Palmprint and palmvein recognition based on DCNN and a new large-scale contactless palmvein dataset [J]. Symmetry, 2018, 10(4): 78-92.
[33] LU J W, LIONG V E, ZHOU X Z, et al. Learning compact binary face descriptor for face recognition [J]. IEEE Transaction on Pattern Analysis Machine Intelligence, 2015, 37(10): 2041-2056.
[34] SHEN F M, SHEN C H, LIU W, et al. Supervised discrete hashing[C] //IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 37-45.
[35] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].(2015-04-10)[2019-12-11].https://arxiv.org/pdf/1409.1556.pdf
[36] 贾梦琦. 非接触式掌纹识别算法研究[D]. 青岛: 青岛大学, 2017.
[37] HUANG D, SHAN C F. Local binary patterns and its application to facial image analysis: a survey [J]. IEEE Transactions on Systems Man and Cybernetics-Part C, 2011, 41(6): 765-781.
[1] 杨孟军, 苏成悦, 陈静, 张洁鑫. 基于卷积神经网络的视觉闭环检测研究[J]. 广东工业大学学报, 2018, 35(05): 31-37.
[2] 戴知圣， 潘晴， 常桂林， 陈健刚. 基于机器视觉的贴片引脚焊接缺陷检测[J]. 广东工业大学学报, 2016, 33(03): 65-69.
[3] 邹丽娜，凌捷. 一种基于特征提取的二级文本分类方法[J]. 广东工业大学学报, 2012, 29(4): 65-68.
[4] 裴昱, 温洁嫦. 基于独立分量分析的一种改进的掌纹识别方法[J]. 广东工业大学学报, 2010, 27(1): 51-54.
[5] 张烈平； 张俞伟； 莫玮； . RBF神经网络在诱发脑电信号分类中的应用研究[J]. 广东工业大学学报, 2004, 21(4): 16-20.
[6] 周维忠； 赵海洋； 孙国基； 冯心海； . 基于自适应小波的光频数据分类[J]. 广东工业大学学报, 1999, 16(3): 52-56.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发