基于深度卷积神经网络的指纹活体检测算法研究

doi:10.3969/j.issn.1671-1122.2018.06.004

信息网络安全 ›› 2018, Vol. 18 ›› Issue (6): 28-35.doi: 10.3969/j.issn.1671-1122.2018.06.004

基于深度卷积神经网络的指纹活体检测算法研究

龙敏^1,², 龙啸海¹(), 马莉³

1.长沙理工大学计算机与通信工程学院,湖南长沙410114
2.长沙理工大学综合交通运输大数据智能处理湖南省重点实验室,湖南长沙410114
3. 69026部队,新疆乌鲁木齐 830002

收稿日期:2018-01-04 出版日期:2018-06-15 发布日期:2020-05-11
作者简介:
作者简介：龙敏（1977—）,女,湖南,教授,博士,主要研究方向为混沌理论及应用、无线通信及安全;龙啸海（1992—）,男,湖南,硕士研究生,主要研究方向为信息安全;马莉（1971—）,女,青海,工程师,本科,主要研究方向为通信、网络安全。
基金资助:
国家自然科学基金[61572182, 61370225];湖南省自然科学基金[15JJ2007]

Research on a Fingerprint Liveness Detection Algorithm Based on Deep Convolution Neural Networks

Min LONG^1,², Xiaohai LONG¹(), Li MA³

1. School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha Hunan 410114, China
2. Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, ChangshaHunan 410114, China
3. Troops 69026, Urumqi Xinjiang 830002, China

Received:2018-01-04 Online:2018-06-15 Published:2020-05-11

摘要/Abstract

摘要：

近年来,随着指纹认证系统的广泛应用,伪造指纹检测受到人们的日益关注。文章结合卷积神经网络在计算机视觉、人脸识别和图像分类领域的应用特征,提出一个指纹活体检测算法F-net。算法采用BN层、inception结构和全局均值池化层对网络进行优化,以减少F-net网络的大量参数和计算复杂度,这也使得算法在采用大学习率进行网络训练的同时获得了较高的泛化能力。文章在LivDet2011和LivDet2013数据集上进行了多种算法测试。实验结果表明,文章提出的F-net具有较高的泛化能力和实时检测性能。

关键词: 指纹活体检测, 指纹反欺骗, 卷积神经网络, inception结构

Abstract:

With the wide application of fingerprint authentication system in recent years, forged fingerprint detection has been paid more and more attentions. Based on the application characteristics of convolutional neural network in the fields of computer vision, face recognition and image classification, this paper proposes a fingerprint liveness detection algorithm called F-net. The algorithm uses BN layer, inception structure and global mean pool level to optimize the network, so as to reduce the large number of parameters in F-net network and the computational complexity. This also makes the algorithm get a higher recognition rate when the algorithm uses a large learning rate to train the network. Many algorithms are tested on LivDet2011 and LivDet2013 datasets. The experimental results show that F-net has high recognition rate and real-time detection performance.

Key words: fingerprint liveness detection, fingerprint anti-spoofing, convolution neural network, inception structure

中图分类号:

TP309

龙敏, 龙啸海, 马莉. 基于深度卷积神经网络的指纹活体检测算法研究[J]. 信息网络安全, 2018, 18(6): 28-35.

Min LONG, Xiaohai LONG, Li MA. Research on a Fingerprint Liveness Detection Algorithm Based on Deep Convolution Neural Networks[J]. Netinfo Security, 2018, 18(6): 28-35.

图/表 11

图1

图2

图3

图4

图5

表1

表2

图6

表3

表4

表5

参考文献 23

[1]	TANG Yu, LIU Jiayong, TANG Dianhua.A Cancelable Fingerprint Template Protection Scheme[J].Netinfo Security,2015, 15(1):72-75.
	唐宇,刘嘉勇,汤殿华.一种可撤销的指纹模板保护方案[J].信息网络安全,2015, 15(1):72-75.
[2]	MARTINSEN O G, CLAUSEN S, NYSAETHER J B, et al.Utilizing Characteristic Electrical Properties of the Epidermal Skin Layers to Detect Fake Fingers in Biometric Fingerprint Systems-A Pilot Study.[J]. IEEE Transactions on Biomedical Engineering, 2007, 54(5):891-894.
[3]	YALLA V, BOLES C B, DALEY R C, et al. System and Method for Three-dimensional Biometric Data Feature Detection and Recognition: US, US9141844[P].2015-9-22.
[4]	OJALA T, PIETIKAINEN M, MAENPAA T.Multiresolution Gray-scale and Rotation Invariant Texture Classification with Local Binary Patterns[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 24(7):971-987.
[5]	GRAGNANIELLO D, POGGI G, SANSONE C, et al.Local Contrast Phase Descriptor for Fingerprint Liveness Detection[J]. Pattern Recognition, 2015, 48(4):1050-1058.
[6]	CHOI H, KANG R, CHOI K, et al. Fake-fingerprint Detection Using Multiple Static Features[J]. Optical Engineering, 2009, 48(4):047202(1-13).
[7]	GOTTSCHLICH C, MARASCO E, YANG A Y, et al.Fingerprint Liveness Detection Based on Histograms of Invariant Gradients[C]// IEEE. 2014 IEEE International Joint Conference on Biometrics, September 29-October 2 ,2014, Clearwater, FL, USA. NJ:IEEE, 2014:1-7.
[8]	NOGUEIRA R F, LOTUFO R D A, MACHADO R C. Evaluating Software-based Fingerprint Liveness Detection Using Convolutional Networks and Local Binary Patterns[EB/OL].,2017-12-20.
[9]	MENOTTI D, CHIACHIA G, PINTO A, et al.Deep Representations for Iris, Face, and Fingerprint Spoofing Detection[J]. IEEE Transactions on Information Forensics & Security, 2017, 10(4):864-879.
[10]	NOGUEIRA R F, LOTUFO R D A, MACHADO R C. Fingerprint Liveness Detection Using Convolutional Neural Networks[J]. IEEE Transactions on Information Forensics & Security, 2017, 11(6):1206-1213.
[11]	KRISH R P, FIERREZ J, RAMOS D, et al.Pre-registration for Improved Latent Fingerprint Identification[C]// IEEE. 2014 22nd International Conference on Pattern Recognition, August 24-28, 2014, Stockholm, Sweden.NJ:IEEE, 2014:696-701.
[12]	LUO Xiping, TIAN Jie.Image Enhancement and Minutia Matching Algorithms in Automated Fingerprint Identification System[J]. Journal of Software, 2002, 13(5):946-956.
	罗希平,田捷.自动指纹识别中的图像增强和细节匹配算法[J].软件学报, 2002, 13(5):946-956.
[13]	CUI Zhengyang, HU Aiqun, PENG Linning.A Method of RF Fingerprint Recognition Based on Contour Feature[J]. Netinfo Security,2017, 17(10):75-80.
	崔正阳, 胡爱群, 彭林宁. 一种基于轮廓特征的射频指纹识别方法[J].信息网络安全, 2017, 17(10):75-80.
[14]	ZEILER M D, FERGUS R.Visualizing and Understanding Convolutional Networks[M]// Springer. Computer Vision - ECCV 2014.Cham :Springer,Cham, 2014:818-833.
[15]	KRIZHEVSKY Alex, SUTSKEVER I, HINTON G E.ImageNet Classification with Deep Convolutional Neural Networks[J]. Communications of the Acm, 2017, 60(6):84-90.
[16]	LIN Min, CHEN Qiang, YAN Shuicheng. Network In Network[EB/OL]., 2017-12-20.
[17]	IOFFE S, SZEGEDY C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift[EB/OL]. paperuri:(4634f864791a3f3a0817edabeacf4c49) , 2017-12-20.
[18]	Github. Caffe[EB/OL]., 2017-12-20.
[19]	JIA Yangqing, SHELHAMER E, DONAHUE J, et al.Caffe: Convolutional Architecture for Fast Feature Embedding[C]// ACM. The 22nd Acm International Conference on Multimedia, November 3 - 7, 2014, Orlando, Florida, USA. New York: ACM, 2014:675-678.
[20]	YAMBAY D, GHIANI L, DENTI P, et al.LivDet 2011 — Fingerprint Liveness Detection Competition 2011[C]//IEEE. 2012 International Conference on Biometrics (ICB), March 29 - April 1, 2012, New Delhi, India. NJ:IEEE, 2012:208-215.
[21]	GHIANI L,YAMBAY D, MURA V, et al.LivDet 2013— Fingerprint Liveness Detection Competition 2013[C]// IEEE. 2013 International Conference on Biometrics (ICB), June 4-7, 2013, Madrid, Spain. NJ:IEEE, 2013:1-6.
[22]	GRAGNANIELLO D, POGGI G, SANSONE C, et al.An Investigation of Local Descriptors for Biometric Spoofing Detection[J]. IEEE Transactions on Information Forensics & Security, 2015, 10(4):849-863.
[23]	HU Qing,LIU Benyong.Speaker Recognition Algorithm Based on Convolutional Nerual Networks[J].Netinfo Security,2016, 16(4):55-60.
	胡青, 刘本永. 基于卷积神经网络分类的说话人识别算法[J].信息网络安全, 2016, 16(4):55-60.

基于深度卷积神经网络的指纹活体检测算法研究

Research on a Fingerprint Liveness Detection Algorithm Based on Deep Convolution Neural Networks

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 23

相关文章 3

编辑推荐

Metrics

本文评价

[1]	王蓉, 马春光, 武朋. 基于联邦学习和卷积神经网络的入侵检测方法[J]. 信息网络安全, 2020, 20(4): 47-54.
[2]	夏玉明, 胡绍勇, 朱少民, 刘丽丽. 基于卷积神经网络的网络攻击检测方法研究[J]. 信息网络安全, 2017, 17(11): 32-36.
[3]	胡青, 刘本永. 基于卷积神经网络分类的说话人识别算法[J]. 信息网络安全, 2016, 16(4): 55-60.