Full Text:   <901>

Summary:  <171>

CLC number: TP311

On-line Access: 2018-09-12

Received: 2017-06-26

Revision Accepted: 2018-09-30

Crosschecked: 2018-06-07

Cited: 0

Clicked: 1536

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Tong Zhao

http://orcid.org/0000-0002-7587-3573

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2018 Vol.19 No.9 P.1112-1123

http://doi.org/10.1631/FITEE.1700420


Deep learning compact binary codes for fingerprint indexing


Author(s):  Chao-chao Bai, Wei-qiang Wang, Tong Zhao, Ru-xin Wang, Ming-qiang Li

Affiliation(s):  School of Computer and Control, University of Chinese Academy of Sciences, Beijing 101408, China; more

Corresponding email(s):   zhaotong@ucas.ac.cn

Key Words:  Fingerprint indexing, Minutia cylinder code, Deep neural network, Multi-index hashing


Chao-chao Bai, Wei-qiang Wang, Tong Zhao, Ru-xin Wang, Ming-qiang Li. Deep learning compact binary codes for fingerprint indexing[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(9): 1112-1123.

@article{title="Deep learning compact binary codes for fingerprint indexing",
author="Chao-chao Bai, Wei-qiang Wang, Tong Zhao, Ru-xin Wang, Ming-qiang Li",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="19",
number="9",
pages="1112-1123",
year="2018",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1700420"
}

%0 Journal Article
%T Deep learning compact binary codes for fingerprint indexing
%A Chao-chao Bai
%A Wei-qiang Wang
%A Tong Zhao
%A Ru-xin Wang
%A Ming-qiang Li
%J Frontiers of Information Technology & Electronic Engineering
%V 19
%N 9
%P 1112-1123
%@ 2095-9184
%D 2018
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1700420

TY - JOUR
T1 - Deep learning compact binary codes for fingerprint indexing
A1 - Chao-chao Bai
A1 - Wei-qiang Wang
A1 - Tong Zhao
A1 - Ru-xin Wang
A1 - Ming-qiang Li
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 19
IS - 9
SP - 1112
EP - 1123
%@ 2095-9184
Y1 - 2018
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1700420


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.

基于深度学习紧致二进制编码的指纹索引

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。

关键词:指纹索引;细节点圆柱体编码;深度神经网络;多索引哈希

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Bai C, Zhao T, Wang W, et al., 2015. An efficient indexing scheme based on K-plet representation for fingerprint database. Int Conf on Intelligent Computing, p.247-257.

[2]Bai C, Wang W, Zhao T, et al., 2016. Learning compact binary quantization of minutia cylinder code. Int Conf on Biometrics, p.1-6.

[3]Bhanu B, Tan X, 2003. Fingerprint indexing based on novel features of minutiae triplets. IEEE Trans Patt Anal Mach Intell, 25(5):616-622.

[4]Cappelli R, Ferrara M, Maltoni D, 2010. Minutia cylinder-code: a new representation and matching technique for fingerprint recognition. IEEE Trans Patt Anal Mach Intell, 32(12):2128-2141.

[5]Cappelli R, Ferrara M, Maltoni D, 2011. Fingerprint indexing based on minutia cylinder-code. IEEE Trans Patt Anal Mach Intell, 33(5):1051-1057.

[6]Do T, Doan A, Cheung N, 2016. Learning to hash with binary deep neural network. European Conf on Computer Vision, p.219-234.

[7]Ferrara M, Maltoni D, Cappelli R, 2012. Noninvertible minutia cylinder-code representation. IEEE Trans Inform Forens Secur, 7(6):1727-1737.

[8]Germain R, Califano A, Colville S, 1997. Fingerprint matching using transformation parameter clustering. IEEE Comput Sci Eng, 4(4):42-49.

[9]Gong Y, Lazebnik S, 2011. Iterative quantization: a procrustean approach to learning binary codes. IEEE Int Conf on Computer Vision and Pattern Recognition, p.817-824.

[10]Gong Y, Lazebnik S, Gordo A, et al., 2013. Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans Patt Anal Mach Intell, 35:2916-2929.

[11]Heo J, Lee Y, He J, et al., 2012. Spherical hashing. IEEE Int Conf on Computer Vision and Pattern Recognition, p.2957-2964.

[12]Heo J, Lee Y, He J, et al., 2015. Spherical hashing: binary code embedding with hyperspheres. IEEE Trans Patt Anal Mach Intell, 37(11):2304-2316.

[13]Iloanusi O, 2014. Fusion of finger types for fingerprint indexing using minutiae quadruplets. Patt Recogn Lett, 38:8-14.

[14]Iloanusi O, Gyaourova A, Ross A, 2011. Indexing fingerprints using minutiae quadruplets. IEEE Int Conf on Computer Vision and Pattern Recognition Workshops, p.127-133.

[15]Jiang X, Liu M, Kot A, 2006. Fingerprint retrieval for identification. IEEE Trans Inform Forens Secur, 1(4):532-542.

[16]Lee S, Kim Y, Park G, 2005. A feature map consisting of orientation and inter-ridge spacing for fingerprint retrieval. Int Conf on Audio- and Video-Based Biometric Person Authentication, p.184-190.

[17]Liang X, Asano T, Bishnu A, 2006. Distorted fingerprint indexing using minutia detail and Delaunay triangle. IEEE Int Symp on Voronoi Diagrams in Science and Engineering, p.217-223.

[18]Liang X, Bishnu A, Asano T, 2007. A robust fingerprint indexing scheme using minutia neighborhood structure and low-order Delaunay triangles. IEEE Trans Inform Forens Secur, 2(4):721-733.

[19]Liu M, Yap P, 2012. Invariant representation of orientation fields for fingerprint indexing. Patt Recogn, 45(7):2532-2542.

[20]Liu M, Jiang X, Kot A, 2007. Efficient fingerprint search based on database clustering. Patt Recogn, 40(6):1793-1803.

[21]Maltoni D, Maio D, Jain A, et al., 2009. Handbook of Fingerprint Recognition. Springer-Verlag, London, UK.

[22]Norouzi M, Punjani A, Fleet D, 2012. Fast search in hamming space with multi-index hashing. IEEE Int Conf on Computer Vision and Pattern Recognition, p.3108-3115.

[23]Norouzi M, Punjani A, Fleet D, 2014. Fast exact search in hamming space with multi-index hashing. IEEE Trans Patt Anal Mach Intell, 36(6):1107-1119.

[24]Shen F, Shen C, Liu W, et al., 2015. Supervised discrete hashing. IEEE Int Conf on Computer Vision and Pattern Recognition, p.37-45.

[25]Wang Y, Hu J, Phillips D, 2007. 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, 29(4):573-585.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE