C2CL: Contact to Contactless Fingerprint Matching

被引:30
作者
Grosz, Steven A. [1 ]
Engelsma, Joshua J. [1 ]
Liu, Eryun [2 ]
Jain, Anil K. [1 ]
机构
[1] Michigan State Univ, Dept Comp Sci & Engn, E Lansing, MI 48824 USA
[2] Zhejiang Univ, Coll Informat Sci & Elect Engn, Hangzhou 310027, Peoples R China
基金
美国国家科学基金会;
关键词
Image segmentation; Databases; Cameras; Indexes; Nonlinear distortion; Feature extraction; Strain; Fingerprint recognition; sensor interoperability; contact to contactless fingerprint matching; RECTIFICATION;
D O I
10.1109/TIFS.2021.3134867
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Matching contactless fingerprints or finger photos to contact-based fingerprint impressions has received increased attention in the wake of COVID-19 due to the superior hygiene of the contactless acquisition and the widespread availability of low cost mobile phones capable of capturing photos of fingerprints with sufficient resolution for verification purposes. This paper presents an end-to-end automated system, called C2CL, comprised of a mobile finger photo capture app, preprocessing, and matching algorithms to handle the challenges inhibiting previous cross-matching methods; namely i) low ridge-valley contrast of contactless fingerprints, ii) varying roll, pitch, yaw, and distance of the finger to the camera, iii) non-linear distortion of contact-based fingerprints, and vi) different image qualities of smartphone cameras. Our preprocessing algorithm segments, enhances, scales, and unwarps contactless fingerprints, while our matching algorithm extracts both minutiae and texture representations. A sequestered dataset of 9, 888 contactless 2D fingerprints and corresponding contact-based fingerprints from 206 subjects (2 thumbs and 2 index fingers for each subject) acquired using our mobile capture app is used to evaluate the cross-database performance of our proposed algorithm. Furthermore, additional experimental results on 3 publicly available datasets show substantial improvement in the state-of-the-art for contact to contactless fingerprint matching (TAR in the range of 96.67% to 98.30% at FAR=0.01%).
引用
收藏
页码:196 / 210
页数:15
相关论文
共 51 条
[1]  
Alonso-Fernandez F., 2006, PROC 9 INT C CONTROL, P1
[2]   A Large-Scale Study of Fingerprint Matching Systems for Sensor Interoperability Problem [J].
AlShehri, Helala ;
Hussain, Muhammad ;
AboAlSamh, Hatim ;
AlZuair, Mansour .
SENSORS, 2018, 18 (04)
[3]  
[Anonymous], LABELME IMAGE POLYGO
[4]   Fingerprint matching by thin-plate spline modelling of elastic deformations [J].
Bazen, AM ;
Gerez, SH .
PATTERN RECOGNITION, 2003, 36 (08) :1859-1867
[5]   Towards smartphone-based touchless fingerprint recognition [J].
Birajadar, Parmeshwar ;
Haria, Meet ;
Kulkarni, Pranav ;
Gupta, Shubham ;
Joshi, Prasad ;
Singh, Brijesh ;
Gadre, Vikram .
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, 2019, 44 (07)
[6]  
Cao K., 2018, ARXIV180408122
[7]   End-to-End Latent Fingerprint Search [J].
Cao, Kai ;
Dinh-Luan Nguyen ;
Tymoszek, Cori ;
Jain, Anil K. .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 (15) :880-894
[8]  
Cappelli R., 2001, PROC INT C ADV PATTE, P371, DOI DOI 10.1007/3-540-44732-6_38
[9]  
Dabouei A., 2019, INT CONF BIOMETR, P1
[10]   Fingerprint Distortion Rectification using Deep Convolutional Neural Networks [J].
Dabouei, Ali ;
Kazemi, Hadi ;
Iranmanesh, Seyed Mehdi ;
Dawson, Jeremy ;
Nasrabadi, Nasser M. .
2018 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB), 2018, :1-8