Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system

Beng Jin Teoh, N. C.L. David

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Today, minutiae-based and image-based are the two major approaches for the purpose of fingerprint authentication. Image based approach offers much higher computation efficiency with minimum pre-processing and proves also effective even when the image quality is too low to allow a reliable minutia extraction. However, this approach is vulnerable to shape distortions as well as variation in position, scale and orientation angle. In this paper, a novel method of image based fingerprint matching based on the features extracted from the integrated Wavelet and the Fourier-Mellin Transform (WFMT is proposed. Wavelet transform is used to smooth and preserve the local edges after image decomposition, and hence making the fingerprint images less sensitive to shape distortion whilst Fourier-Mellin transform served to produce a translation, rotation and scale invariant feature. Multiple WFMT features can be used to form a reference invariant feature through the linearity property of Fourier-Mellin Transform and hence reduce the variability of the input fingerprint images. The experiments show the verification accuracy is over 96% and 99% of verification rate is achieved when multiple WFMT features are used.

Original languageEnglish
Title of host publicationProceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003
PublisherAssociation for Computing Machinery, Inc
Pages82-88
Number of pages7
ISBN (Electronic)1581137796, 9781581137798
DOIs
Publication statusPublished - 2003 Nov 8
Event2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003 - Berkley, United States
Duration: 2003 Nov 8 → …

Other

Other2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003
CountryUnited States
CityBerkley
Period03/11/8 → …

Fingerprint

Fingerprint Verification
Fingerprint
Mellin Transform
Fourier transforms
Wavelets
Fourier transform
Invariant
Image Decomposition
Method of Images
Wavelet transforms
Authentication
Image quality
Rotation Invariant
Scale Invariant
Linearity
Image Quality
Wavelet Transform
Decomposition
Preprocessing
Processing

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Control and Systems Engineering
  • Artificial Intelligence
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Teoh, B. J., & David, N. C. L. (2003). Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system. In Proceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003 (pp. 82-88). Association for Computing Machinery, Inc. https://doi.org/10.1145/982507.982523
Teoh, Beng Jin ; David, N. C.L. / Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system. Proceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003. Association for Computing Machinery, Inc, 2003. pp. 82-88
@inproceedings{8c18ecaf884a45debc1a24a032387765,
title = "Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system",
abstract = "Today, minutiae-based and image-based are the two major approaches for the purpose of fingerprint authentication. Image based approach offers much higher computation efficiency with minimum pre-processing and proves also effective even when the image quality is too low to allow a reliable minutia extraction. However, this approach is vulnerable to shape distortions as well as variation in position, scale and orientation angle. In this paper, a novel method of image based fingerprint matching based on the features extracted from the integrated Wavelet and the Fourier-Mellin Transform (WFMT is proposed. Wavelet transform is used to smooth and preserve the local edges after image decomposition, and hence making the fingerprint images less sensitive to shape distortion whilst Fourier-Mellin transform served to produce a translation, rotation and scale invariant feature. Multiple WFMT features can be used to form a reference invariant feature through the linearity property of Fourier-Mellin Transform and hence reduce the variability of the input fingerprint images. The experiments show the verification accuracy is over 96{\%} and 99{\%} of verification rate is achieved when multiple WFMT features are used.",
author = "Teoh, {Beng Jin} and David, {N. C.L.}",
year = "2003",
month = "11",
day = "8",
doi = "10.1145/982507.982523",
language = "English",
pages = "82--88",
booktitle = "Proceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003",
publisher = "Association for Computing Machinery, Inc",

}

Teoh, BJ & David, NCL 2003, Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system. in Proceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003. Association for Computing Machinery, Inc, pp. 82-88, 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003, Berkley, United States, 03/11/8. https://doi.org/10.1145/982507.982523

Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system. / Teoh, Beng Jin; David, N. C.L.

Proceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003. Association for Computing Machinery, Inc, 2003. p. 82-88.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system

AU - Teoh, Beng Jin

AU - David, N. C.L.

PY - 2003/11/8

Y1 - 2003/11/8

N2 - Today, minutiae-based and image-based are the two major approaches for the purpose of fingerprint authentication. Image based approach offers much higher computation efficiency with minimum pre-processing and proves also effective even when the image quality is too low to allow a reliable minutia extraction. However, this approach is vulnerable to shape distortions as well as variation in position, scale and orientation angle. In this paper, a novel method of image based fingerprint matching based on the features extracted from the integrated Wavelet and the Fourier-Mellin Transform (WFMT is proposed. Wavelet transform is used to smooth and preserve the local edges after image decomposition, and hence making the fingerprint images less sensitive to shape distortion whilst Fourier-Mellin transform served to produce a translation, rotation and scale invariant feature. Multiple WFMT features can be used to form a reference invariant feature through the linearity property of Fourier-Mellin Transform and hence reduce the variability of the input fingerprint images. The experiments show the verification accuracy is over 96% and 99% of verification rate is achieved when multiple WFMT features are used.

AB - Today, minutiae-based and image-based are the two major approaches for the purpose of fingerprint authentication. Image based approach offers much higher computation efficiency with minimum pre-processing and proves also effective even when the image quality is too low to allow a reliable minutia extraction. However, this approach is vulnerable to shape distortions as well as variation in position, scale and orientation angle. In this paper, a novel method of image based fingerprint matching based on the features extracted from the integrated Wavelet and the Fourier-Mellin Transform (WFMT is proposed. Wavelet transform is used to smooth and preserve the local edges after image decomposition, and hence making the fingerprint images less sensitive to shape distortion whilst Fourier-Mellin transform served to produce a translation, rotation and scale invariant feature. Multiple WFMT features can be used to form a reference invariant feature through the linearity property of Fourier-Mellin Transform and hence reduce the variability of the input fingerprint images. The experiments show the verification accuracy is over 96% and 99% of verification rate is achieved when multiple WFMT features are used.

UR - http://www.scopus.com/inward/record.url?scp=84994749064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994749064&partnerID=8YFLogxK

U2 - 10.1145/982507.982523

DO - 10.1145/982507.982523

M3 - Conference contribution

AN - SCOPUS:84994749064

SP - 82

EP - 88

BT - Proceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003

PB - Association for Computing Machinery, Inc

ER -

Teoh BJ, David NCL. Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system. In Proceedings of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003. Association for Computing Machinery, Inc. 2003. p. 82-88 https://doi.org/10.1145/982507.982523