Indexing Fingerprint Databases Based on Multiple Features

J. de Boer, A.M. Bazen, Sabih H. Gerez

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

70 Downloads (Pure)

Abstract

In a fingerprint identification system, a person is identified only by his fingerprint. To accomplish this, a database is searched by matching all entries to the given fingerprint. However, the maximum size of the database is limited, since each match takes some amount of time and has a small probability of error. A solution to this problem is to reduce the number of fingerprints that have to be matched. This is achieved by extracting features from the fingerprints and first matching the fingerprints that have the smallest feature distance to the query fingerprint. Using this indexing method, modern systems are able to search databases up to a few hundred fingerprints. In this paper, three possible fingerprint indexing features are discussed: the registered directional field estimate, FingerCode and minutiae triplets. It is shown that indexing schemes that are based on these features, are able to search a database more effectively than a simple linear scan. Next, a new indexing scheme is constructed that is based on advanced methods of combining these features. It is shown that this scheme results in a considerably better performance than the schemes that are based on the individual features or on more naive methods of combining the features, thus allowing much larger fingerprint databases to be searched.
Original languageEnglish
Title of host publicationProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop
Place of PublicationVeldhoven, The Netherlands
PublisherSTW
Pages300-306
Number of pages7
ISBN (Print)90-73461-29-4
Publication statusPublished - 29 Nov 2001
Event14th ProRISC Workshop on Circuits, Systems and Signal Processing 2003 - Veldhoven, Netherlands
Duration: 25 Nov 200327 Nov 2003
Conference number: 14

Publication series

Name
PublisherSTW

Workshop

Workshop14th ProRISC Workshop on Circuits, Systems and Signal Processing 2003
Abbreviated titleProRISC
CountryNetherlands
CityVeldhoven
Period25/11/0327/11/03

Fingerprint

Identification (control systems)

Keywords

  • EWI-13288
  • SCS-Safety
  • METIS-201600
  • fingerprint image classification
  • database search
  • multiple classifiers
  • Image Processing
  • IR-62437

Cite this

de Boer, J., Bazen, A. M., & Gerez, S. H. (2001). Indexing Fingerprint Databases Based on Multiple Features. In ProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop (pp. 300-306). Veldhoven, The Netherlands: STW.
de Boer, J. ; Bazen, A.M. ; Gerez, Sabih H. / Indexing Fingerprint Databases Based on Multiple Features. ProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop. Veldhoven, The Netherlands : STW, 2001. pp. 300-306
@inproceedings{3472da93f637451ab6348c8f198f7905,
title = "Indexing Fingerprint Databases Based on Multiple Features",
abstract = "In a fingerprint identification system, a person is identified only by his fingerprint. To accomplish this, a database is searched by matching all entries to the given fingerprint. However, the maximum size of the database is limited, since each match takes some amount of time and has a small probability of error. A solution to this problem is to reduce the number of fingerprints that have to be matched. This is achieved by extracting features from the fingerprints and first matching the fingerprints that have the smallest feature distance to the query fingerprint. Using this indexing method, modern systems are able to search databases up to a few hundred fingerprints. In this paper, three possible fingerprint indexing features are discussed: the registered directional field estimate, FingerCode and minutiae triplets. It is shown that indexing schemes that are based on these features, are able to search a database more effectively than a simple linear scan. Next, a new indexing scheme is constructed that is based on advanced methods of combining these features. It is shown that this scheme results in a considerably better performance than the schemes that are based on the individual features or on more naive methods of combining the features, thus allowing much larger fingerprint databases to be searched.",
keywords = "EWI-13288, SCS-Safety, METIS-201600, fingerprint image classification, database search, multiple classifiers, Image Processing, IR-62437",
author = "{de Boer}, J. and A.M. Bazen and Gerez, {Sabih H.}",
year = "2001",
month = "11",
day = "29",
language = "English",
isbn = "90-73461-29-4",
publisher = "STW",
pages = "300--306",
booktitle = "ProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop",

}

de Boer, J, Bazen, AM & Gerez, SH 2001, Indexing Fingerprint Databases Based on Multiple Features. in ProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop. STW, Veldhoven, The Netherlands, pp. 300-306, 14th ProRISC Workshop on Circuits, Systems and Signal Processing 2003, Veldhoven, Netherlands, 25/11/03.

Indexing Fingerprint Databases Based on Multiple Features. / de Boer, J.; Bazen, A.M.; Gerez, Sabih H.

ProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop. Veldhoven, The Netherlands : STW, 2001. p. 300-306.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Indexing Fingerprint Databases Based on Multiple Features

AU - de Boer, J.

AU - Bazen, A.M.

AU - Gerez, Sabih H.

PY - 2001/11/29

Y1 - 2001/11/29

N2 - In a fingerprint identification system, a person is identified only by his fingerprint. To accomplish this, a database is searched by matching all entries to the given fingerprint. However, the maximum size of the database is limited, since each match takes some amount of time and has a small probability of error. A solution to this problem is to reduce the number of fingerprints that have to be matched. This is achieved by extracting features from the fingerprints and first matching the fingerprints that have the smallest feature distance to the query fingerprint. Using this indexing method, modern systems are able to search databases up to a few hundred fingerprints. In this paper, three possible fingerprint indexing features are discussed: the registered directional field estimate, FingerCode and minutiae triplets. It is shown that indexing schemes that are based on these features, are able to search a database more effectively than a simple linear scan. Next, a new indexing scheme is constructed that is based on advanced methods of combining these features. It is shown that this scheme results in a considerably better performance than the schemes that are based on the individual features or on more naive methods of combining the features, thus allowing much larger fingerprint databases to be searched.

AB - In a fingerprint identification system, a person is identified only by his fingerprint. To accomplish this, a database is searched by matching all entries to the given fingerprint. However, the maximum size of the database is limited, since each match takes some amount of time and has a small probability of error. A solution to this problem is to reduce the number of fingerprints that have to be matched. This is achieved by extracting features from the fingerprints and first matching the fingerprints that have the smallest feature distance to the query fingerprint. Using this indexing method, modern systems are able to search databases up to a few hundred fingerprints. In this paper, three possible fingerprint indexing features are discussed: the registered directional field estimate, FingerCode and minutiae triplets. It is shown that indexing schemes that are based on these features, are able to search a database more effectively than a simple linear scan. Next, a new indexing scheme is constructed that is based on advanced methods of combining these features. It is shown that this scheme results in a considerably better performance than the schemes that are based on the individual features or on more naive methods of combining the features, thus allowing much larger fingerprint databases to be searched.

KW - EWI-13288

KW - SCS-Safety

KW - METIS-201600

KW - fingerprint image classification

KW - database search

KW - multiple classifiers

KW - Image Processing

KW - IR-62437

M3 - Conference contribution

SN - 90-73461-29-4

SP - 300

EP - 306

BT - ProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop

PB - STW

CY - Veldhoven, The Netherlands

ER -

de Boer J, Bazen AM, Gerez SH. Indexing Fingerprint Databases Based on Multiple Features. In ProRISC the 12th Annual Workshop on Circuits, Systems and Signal Processing Workshop. Veldhoven, The Netherlands: STW. 2001. p. 300-306