基于深度学习紧致二进制编码的指纹索引

白超超; 王伟强; 赵彤; 王如心; 李明强

doi:10.1631/FITEE.1700420

Your Location：

Home >

Browse articles >

基于深度学习紧致二进制编码的指纹索引

常规文章 | Updated：2022-05-19

- 基于深度学习紧致二进制编码的指纹索引
- Deep learning compact binary codes for fingerprint indexing
- 信息与电子工程前沿（英文） 2018年19卷第9期页码：1112-1123
- Affiliations：
  
  School of Computer and Control, University of Chinese Academy of Sciences, Beijing 101408, China
  School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
  Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing 100080, China
- Author bio：
  
  Tong ZHAO, E-mail: zhaotong@ucas.ac.cn
- Funds：
  
  Project supported by the National Natural Science Foundation of China (Nos. 11331012, 11571014, and 11731013)
- DOI：10.1631/FITEE.1700420
  中图分类号： TP311
- 收稿：2017-06-26，
  
  修回：2018-;6-;7，
  
  网络出版：2018-09-12，
  
  纸质出版：2018-09
- Accepted：
Scan QR Code
白超超, 王伟强, 赵彤, 等. 基于深度学习紧致二进制编码的指纹索引[J]. 信息与电子工程前沿（英文）, 2018,19(9):1112-1123.

Chao-chao BAI, Wei-qiang WANG, Tong ZHAO, et al. Deep learning compact binary codes for fingerprint indexing[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(9): 1112-1123.
白超超, 王伟强, 赵彤, 等. 基于深度学习紧致二进制编码的指纹索引[J]. 信息与电子工程前沿（英文）, 2018,19(9):1112-1123. DOI： 10.1631/FITEE.1700420.

Chao-chao BAI, Wei-qiang WANG, Tong ZHAO, et al. Deep learning compact binary codes for fingerprint indexing[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(9): 1112-1123. DOI： 10.1631/FITEE.1700420.

摘要

随着指纹数据库迅速发展，有必要开发一种卓越的指纹索引方法满足系统高效性和准确性要求。实值特征的指纹索引已进行广泛研究，但二进制编码特征的研究相对较少，并且二进制编码特征更适合大规模指纹数据库的高效检索。首先，提出高效的有区分度的深度紧致二进制细节点圆柱体编码（deep compact binary minutia cylinder code，DCBMCC）作为指纹索引特征。具体分析了最新细节点圆柱体编码（minutia cylinder code，MCC），并发现其缺点。提出一种新颖的深度神经网络学习指纹索引特征DCBMCC，设置网络倒数第二层直接输出为二进制编码。将独立性、平衡性、量化损失最小和相似性保持等重要属性结合在学习过程中。最后，设计了基于多索引哈希（multi-index hashing，MIH）的指纹索引模式，从而在汉明空间中进行高效精确的搜索。此外，许多公开数据库上的实验表明，本文提出的方法是一个卓越的指纹索引方法，在穿透率非常低的情况下仍然具有非常小的错误率。

Abstract

With the rapid growth in fingerprint databases

it has become necessary to develop excellent fingerprint indexing to achieve efficiency and accuracy. Fingerprint indexing has been widely studied with real-valued features

but few studies focus on binary feature representation

which is more suitable to identify fingerprints efficiently in large-scale fingerprint databases. In this study

we propose a deep compact binary minutia cylinder code (DCBMCC) as an effective and discriminative feature representation for fingerprint indexing. Specifically

the minutia cylinder code (MCC)

as the state-of-the-art fingerprint representation

is analyzed and its shortcomings are revealed. Accordingly

we propose a novel fingerprint indexing method based on deep neural networks to learn DCBMCC. Our novel network restricts the penultimate layer to directly output binary codes. Moreover

we incorporate independence

balance

quantization-loss-minimum

and similarity-preservation properties in this learning process. Eventually

a multi-index hashing (MIH) based fingerprint indexing scheme further speeds up the exact search in the Hamming space by building multiple hash tables on binary code substrings. Furthermore

numerous experiments on public databases show that the proposed approach is an outstanding fingerprint indexing method since it has an extremely small error rate with a very low penetration rate.

关键词

Keywords

references

C Bai , , , T Zhao , , , W Wang , , , 等 . . An efficient indexing scheme based on K-plet representation for fingerprint database . . Int Conf on Intelligent Computing , , 2015 . . p.247 - - 257 . . DOI: 10.1007/978-3-319-22180-9-25 http://doi.org/10.1007/978-3-319-22180-9-25 . .

C Bai , , , W Wang , , , T Zhao , , , 等 . . Learning compact binary quantization of minutia cylinder code . . Int Conf on Biometrics , , 2016 . . p.1 - - 6 . . DOI: 10.1109/ICB.2016.7550054 http://doi.org/10.1109/ICB.2016.7550054 . .

B Bhanu , , , X Tan . . Fingerprint indexing based on novel features of minutiae triplets . . IEEE Trans Patt Anal Mach Intell , , 2003 . . 25 ( ( 5 ): ): 616 - - 622 . . DOI: 10.1109/TPAMI.2003.1195995 http://doi.org/10.1109/TPAMI.2003.1195995 . .

R Cappelli , , , M Ferrara , , , D Maltoni . . Minutia cylindercode: a new representation and matching technique for fingerprint recognition . . IEEE Trans Patt Anal Mach Intell , , 2010 . . 32 ( ( 12 ): ): 2128 - - 2141 . . DOI: 10.1109/TPAMI.2010.52 http://doi.org/10.1109/TPAMI.2010.52 . .

R Cappelli , , , M Ferrara , , , D Maltoni . . Fingerprint indexing based on minutia cylinder-code . . IEEE Trans Patt Anal Mach Intell , , 2011 . . 33 ( ( 5 ): ): 1051 - - 1057 . . DOI: 10.1109/TPAMI.2010.228 http://doi.org/10.1109/TPAMI.2010.228 . .

T Do , , , A Doan , , , N Cheung . . Learning to hash with binary deep neural network . . European Conf on Computer Vision , , 2016 . . p.219 - - 234 . . DOI: 10.1007/978-3-319-46454-1-14 http://doi.org/10.1007/978-3-319-46454-1-14 . .

M Ferrara , , , D Maltoni , , , R Cappelli . . Noninvertible minutia cylinder-code representation . . IEEE Trans Inform Forens Secur , , 2012 . . 7 ( ( 6 ): ): 1727 - - 1737 . . DOI: 10.1109/TIFS.2012.2215326 http://doi.org/10.1109/TIFS.2012.2215326 . .

R Germain , , , A Califano , , , S Colville . . Fingerprint matching using transformation parameter clustering . . IEEE Comput Sci Eng , , 1997 . . 4 ( ( 4 ): ): 42 - - 49 . . DOI: 10.1109/99.641608 http://doi.org/10.1109/99.641608 . .

Y Gong , , , S Lazebnik . . Iterative quantization: a procrustean approach to learning binary codes . . IEEE Int Conf on Computer Vision and Pattern Recognition , , 2011 . . p.817 - - 824 . . DOI: 10.1109/CVPR.2011.5995432 http://doi.org/10.1109/CVPR.2011.5995432 . .

Y Gong , , , S Lazebnik , , , A Gordo , , , 等 . . Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval . . IEEE Trans Patt Anal Mach Intell , , 2013 . . 35 2916 - - 2929 . . DOI: 10.1109/TPAMI.2012.193 http://doi.org/10.1109/TPAMI.2012.193 . .

J Heo , , , Y Lee , , , J He , , , 等 . . Spherical hashing . . IEEE Int Conf on Computer Vision and Pattern Recognition , , 2012 . . p.2957 - - 2964 . . DOI: 10.1109/CVPR.2012.6248024 http://doi.org/10.1109/CVPR.2012.6248024 . .

J Heo , , , Y Lee , , , J He , , , 等 . . Spherical hashing: binary code embedding with hyperspheres . . IEEE Trans Patt Anal Mach Intell , , 2015 . . 37 ( ( 11 ): ): 2304 - - 2316 . . DOI: 10.1109/TPAMI.2015.2408363 http://doi.org/10.1109/TPAMI.2015.2408363 . .

O Iloanusi . . Fusion of finger types for fingerprint indexing using minutiae quadruplets . . Patt Recogn Lett , , 2014 . . 38 8 - - 14 . . DOI: 10.1016/j.patrec.2013.10.019 http://doi.org/10.1016/j.patrec.2013.10.019 . .

O Iloanusi , , , A Gyaourova , , , A Ross . . Indexing fingerprints using minutiae quadruplets . . IEEE Int Conf on Computer Vision and Pattern Recognition Workshops , , 2011 . . p.127 - - 133 . . DOI: 10.1109/CVPRW.2011.5981825 http://doi.org/10.1109/CVPRW.2011.5981825 . .

X Jiang , , , M Liu , , , A Kot . . Fingerprint retrieval for identification . . IEEE Trans Inform Forens Secur , , 2006 . . 1 ( ( 4 ): ): 532 - - 542 . . DOI: 10.1109/TIFS.2006.885021 http://doi.org/10.1109/TIFS.2006.885021 . .

S Lee , , , Y Kim , , , G Park . . A feature map consisting of orientation and inter-ridge spacing for fingerprint retrieval . . Int Conf on Audio- and Video-Based Biometric Person Authentication , , 2005 . . p.184 - - 190 . . DOI: 10.1007/11527923-19 http://doi.org/10.1007/11527923-19 . .

X Liang , , , T Asano , , , A Bishnu . . Distorted fingerprint indexing using minutia detail and Delaunay triangle . . IEEE Int Symp on Voronoi Diagrams in Science and Engineering , , 2006 . . p.217 - - 223 . . DOI: 10.1109/ISVD.2006.42 http://doi.org/10.1109/ISVD.2006.42 . .

X Liang , , , A Bishnu , , , T Asano . . A robust fingerprint indexing scheme using minutia neighborhood structure and low-order Delaunay triangles . . IEEE Trans Inform Forens Secur , , 2007 . . 2 ( ( 4 ): ): 721 - - 733 . . DOI: 10.1109/TIFS.2007.910242 http://doi.org/10.1109/TIFS.2007.910242 . .

M Liu , , , P Yap . . Invariant representation of orientation fields for fingerprint indexing . . Patt Recogn , , 2012 . . 45 ( ( 7 ): ): 2532 - - 2542 . . DOI: 10.1016/j.patcog.2012.01.014 http://doi.org/10.1016/j.patcog.2012.01.014 . .

M Liu , , , X Jiang , , , A Kot . . Efficient fingerprint search based on database clustering . . Patt Recogn , , 2007 . . 40 ( ( 6 ): ): 1793 - - 1803 . . DOI: 10.1016/j.patcog.2006.11.007 http://doi.org/10.1016/j.patcog.2006.11.007 . .

D Maltoni , , , D Maio , , , A Jain , , , 等 . . Handbook of Fingerprint Recognition . . Springer-Verlag, London, UK , , 2009 . . DOI: 10.1007/978-1-84882-254-2 http://doi.org/10.1007/978-1-84882-254-2 . .

M Norouzi , , , A Punjani , , , D Fleet . . Fast search in hamming space with multi-index hashing . . IEEE Int Conf on Computer Vision and Pattern Recognition , , 2012 . . p.3108 - - 3115 . . DOI: 10.1109/CVPR.2012.6248043 http://doi.org/10.1109/CVPR.2012.6248043 . .

M Norouzi , , , A Punjani , , , D Fleet . . Fast exact search in hamming space with multi-index hashing . . IEEE Trans Patt Anal Mach Intell , , 2014 . . 36 ( ( 6 ): ): 1107 - - 1119 . . DOI: 10.1109/TPAMI.2013.231 http://doi.org/10.1109/TPAMI.2013.231 . .

F Shen , , , C Shen , , , W Liu , , , 等 . . Supervised discrete hashing . . IEEE Int Conf on Computer Vision and Pattern Recognition , , 2015 . . p.37 - - 45 . . DOI: 10.1109/CVPR.2015.7298598 http://doi.org/10.1109/CVPR.2015.7298598 . .

Y Wang , , , J Hu , , , D Phillips . . A fingerprint orientation model based on 2D Fourier expansion (FOMFE) and its application to singular-point detection and fingerprint indexing . . IEEE Trans Patt Anal Mach Intell , , 2007 . . 29 ( ( 4 ): ): 573 - - 585 . . DOI: 10.1109/TPAMI.2007.1003 http://doi.org/10.1109/TPAMI.2007.1003 . .

Y Weiss , , , A Torralba , , , R Fergus . . Spectral hashing . . Advances in Neural Information Processing Systems , , 2009 . . p.1753 - - 1760 . . . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

FlowDNN: a physics-informed deep neural network for fast and accurate flow prediction

Associative affinity network learning for multi-object tracking