On the use of spectral minutiae in high-resolution palmprint recognition

Ruifang Wang; Raymond N.J. Veldhuis; Daniel Ramos; Lieuwe Jan Spreeuwers; Julian Fierrez; H. Xu

doi:10.1109/IWBF.2013.6547308

On the use of spectral minutiae in high-resolution palmprint recognition

Ruifang Wang, Raymond N.J. Veldhuis, Daniel Ramos, Lieuwe Jan Spreeuwers, Julian Fierrez, H. Xu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

128 Downloads (Pure)

Abstract

The spectral minutiae representation has been proposed as a novel method to minutiae-based fingerprint recognition, which can handle minutiae translation and rotation and improve matching speed. As high-resolution palmprint recognition is also mainly based on minutiae sets, we apply spectral minutiae representation to palmprints and implement spectral minutiae based matching. We optimize key parameters for the method by experimental study on the characteristics of spectral minutiae using both fingerprints and palmprints. However, experimental results show that spectral minutiae representation has much worse performance for palmprints than that for fingerprints. EER 15.89% and 14.2% are achieved on the public high-resolution palmprint database THUPALMLAB using location-based spectral minutiae representation (SML) and the complex spectral minutiae representation (SMC) respectively while 5.1% and 3.05% on FVC2002 DB2A fingerprint database. Based on statistical analysis, we find the worse performance for palmprints mainly due to larger non-linear distortion and much larger number of minutiae.

Original language	Undefined
Title of host publication	Proceedings of the International Workshop on Biometrics and Forensics (IWBF), 2013
Place of Publication	USA
Publisher	IEEE
Pages	1-4
Number of pages	4
ISBN (Print)	978-1-4673-4987-1
DOIs	https://doi.org/10.1109/IWBF.2013.6547308
Publication status	Published - 4 Apr 2013
Event	International Workshop on Biometrics and Forensics, IWBF 2013 - Lisbon, Portugal Duration: 4 Apr 2013 → 5 Apr 2013

Publication series

Name
Publisher	IEEE Computer Society

Workshop

Workshop	International Workshop on Biometrics and Forensics, IWBF 2013
Period	4/04/13 → 5/04/13
Other	4-5 April 2013

Keywords

METIS-297768
minutiae-based fingerprint recognition
high-resolution palmprint recognition
spectral minutiae based matching
EWI-23567
Nonlinear distortion
Statistical Analysis
palmprint database
key parameter optimization
location-based spectral minutiae representation
minutiae rotation
minutiae translation
IR-86963
Complex spectral minutiae representation
SCS-Safety

Access to Document

10.1109/IWBF.2013.6547308

Cite this

@inproceedings{0c4011292db842338b593072061b5c8a,

title = "On the use of spectral minutiae in high-resolution palmprint recognition",

abstract = "The spectral minutiae representation has been proposed as a novel method to minutiae-based fingerprint recognition, which can handle minutiae translation and rotation and improve matching speed. As high-resolution palmprint recognition is also mainly based on minutiae sets, we apply spectral minutiae representation to palmprints and implement spectral minutiae based matching. We optimize key parameters for the method by experimental study on the characteristics of spectral minutiae using both fingerprints and palmprints. However, experimental results show that spectral minutiae representation has much worse performance for palmprints than that for fingerprints. EER 15.89% and 14.2% are achieved on the public high-resolution palmprint database THUPALMLAB using location-based spectral minutiae representation (SML) and the complex spectral minutiae representation (SMC) respectively while 5.1% and 3.05% on FVC2002 DB2A fingerprint database. Based on statistical analysis, we find the worse performance for palmprints mainly due to larger non-linear distortion and much larger number of minutiae.",

keywords = "METIS-297768, minutiae-based fingerprint recognition, high-resolution palmprint recognition, spectral minutiae based matching, EWI-23567, Nonlinear distortion, Statistical Analysis, palmprint database, key parameter optimization, location-based spectral minutiae representation, minutiae rotation, minutiae translation, IR-86963, Complex spectral minutiae representation, SCS-Safety",

author = "Ruifang Wang and Veldhuis, {Raymond N.J.} and Daniel Ramos and Spreeuwers, {Lieuwe Jan} and Julian Fierrez and H. Xu",

note = "10.1109/IWBF.2013.6547308 ; null ; Conference date: 04-04-2013 Through 05-04-2013",

year = "2013",

month = apr,

day = "4",

doi = "10.1109/IWBF.2013.6547308",

language = "Undefined",

isbn = "978-1-4673-4987-1",

publisher = "IEEE",

pages = "1--4",

booktitle = "Proceedings of the International Workshop on Biometrics and Forensics (IWBF), 2013",

}

TY - GEN

T1 - On the use of spectral minutiae in high-resolution palmprint recognition

AU - Wang, Ruifang

AU - Veldhuis, Raymond N.J.

AU - Ramos, Daniel

AU - Spreeuwers, Lieuwe Jan

AU - Fierrez, Julian

AU - Xu, H.

N1 - 10.1109/IWBF.2013.6547308

PY - 2013/4/4

Y1 - 2013/4/4

N2 - The spectral minutiae representation has been proposed as a novel method to minutiae-based fingerprint recognition, which can handle minutiae translation and rotation and improve matching speed. As high-resolution palmprint recognition is also mainly based on minutiae sets, we apply spectral minutiae representation to palmprints and implement spectral minutiae based matching. We optimize key parameters for the method by experimental study on the characteristics of spectral minutiae using both fingerprints and palmprints. However, experimental results show that spectral minutiae representation has much worse performance for palmprints than that for fingerprints. EER 15.89% and 14.2% are achieved on the public high-resolution palmprint database THUPALMLAB using location-based spectral minutiae representation (SML) and the complex spectral minutiae representation (SMC) respectively while 5.1% and 3.05% on FVC2002 DB2A fingerprint database. Based on statistical analysis, we find the worse performance for palmprints mainly due to larger non-linear distortion and much larger number of minutiae.

AB - The spectral minutiae representation has been proposed as a novel method to minutiae-based fingerprint recognition, which can handle minutiae translation and rotation and improve matching speed. As high-resolution palmprint recognition is also mainly based on minutiae sets, we apply spectral minutiae representation to palmprints and implement spectral minutiae based matching. We optimize key parameters for the method by experimental study on the characteristics of spectral minutiae using both fingerprints and palmprints. However, experimental results show that spectral minutiae representation has much worse performance for palmprints than that for fingerprints. EER 15.89% and 14.2% are achieved on the public high-resolution palmprint database THUPALMLAB using location-based spectral minutiae representation (SML) and the complex spectral minutiae representation (SMC) respectively while 5.1% and 3.05% on FVC2002 DB2A fingerprint database. Based on statistical analysis, we find the worse performance for palmprints mainly due to larger non-linear distortion and much larger number of minutiae.

KW - METIS-297768

KW - minutiae-based fingerprint recognition

KW - high-resolution palmprint recognition

KW - spectral minutiae based matching

KW - EWI-23567

KW - Nonlinear distortion

KW - Statistical Analysis

KW - palmprint database

KW - key parameter optimization

KW - location-based spectral minutiae representation

KW - minutiae rotation

KW - minutiae translation

KW - IR-86963

KW - Complex spectral minutiae representation

KW - SCS-Safety

U2 - 10.1109/IWBF.2013.6547308

DO - 10.1109/IWBF.2013.6547308

M3 - Conference contribution

SN - 978-1-4673-4987-1

SP - 1

EP - 4

BT - Proceedings of the International Workshop on Biometrics and Forensics (IWBF), 2013

PB - IEEE

CY - USA

Y2 - 4 April 2013 through 5 April 2013

ER -