Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching

Shreyansh Daftry, Saloni Dawar

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

Abstract

Fingerprint verification is an important biometric technique for personal identification. This paper presents a performance evaluation of different fingerprint feature extraction methods. Fingerprint matching scheme based on transform features, like DCT (Discrete Cosine Transform), FFT (Fast Fourier Transform) and DWT (Discrete wavelet transform), have been presented and compared. In the fingerprint recognition application utilizing more information other than minutiae is much helpful. The technique described here obviates the need for extracting minutiae points to match fingerprint images. The transform coefficients are used to obtain the feature vector in terms of standard deviation and energy. Matching is performed using fast Euclidean distance between two feature vectors. The algorithms have been tested on database available from University of Bologna. Our comparison shows that DCT and FFT yields better GAR (Genuine acceptance rate) at low FAR (False acceptance rate) with reduced computational complexity over existing DWT and Gabor based algorithms. Because of reduced computational complexity these algorithms can be easily implemented as an embedded automatic fingerprint identification system (AFIS).

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012
Pages132-137
Number of pages6
DOIs
Publication statusPublished - 08-08-2012
Externally publishedYes
EventIASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012 - Crete, Greece
Duration: 18-06-201220-06-2012

Conference

ConferenceIASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012
CountryGreece
CityCrete
Period18-06-1220-06-12

Fingerprint

Authentication
Feature extraction
Discrete cosine transforms
Discrete wavelet transforms
Fast Fourier transforms
Computational complexity
Biometrics
Identification (control systems)

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Daftry, S., & Dawar, S. (2012). Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching. In Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012 (pp. 132-137) https://doi.org/10.2316/P.2012.778-018
Daftry, Shreyansh ; Dawar, Saloni. / Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching. Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012. 2012. pp. 132-137
@inproceedings{b503cf5555174e46ae8567246a4275c9,
title = "Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching",
abstract = "Fingerprint verification is an important biometric technique for personal identification. This paper presents a performance evaluation of different fingerprint feature extraction methods. Fingerprint matching scheme based on transform features, like DCT (Discrete Cosine Transform), FFT (Fast Fourier Transform) and DWT (Discrete wavelet transform), have been presented and compared. In the fingerprint recognition application utilizing more information other than minutiae is much helpful. The technique described here obviates the need for extracting minutiae points to match fingerprint images. The transform coefficients are used to obtain the feature vector in terms of standard deviation and energy. Matching is performed using fast Euclidean distance between two feature vectors. The algorithms have been tested on database available from University of Bologna. Our comparison shows that DCT and FFT yields better GAR (Genuine acceptance rate) at low FAR (False acceptance rate) with reduced computational complexity over existing DWT and Gabor based algorithms. Because of reduced computational complexity these algorithms can be easily implemented as an embedded automatic fingerprint identification system (AFIS).",
author = "Shreyansh Daftry and Saloni Dawar",
year = "2012",
month = "8",
day = "8",
doi = "10.2316/P.2012.778-018",
language = "English",
isbn = "9780889869219",
pages = "132--137",
booktitle = "Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012",

}

Daftry, S & Dawar, S 2012, Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching. in Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012. pp. 132-137, IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012, Crete, Greece, 18-06-12. https://doi.org/10.2316/P.2012.778-018

Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching. / Daftry, Shreyansh; Dawar, Saloni.

Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012. 2012. p. 132-137.

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

TY - GEN

T1 - Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching

AU - Daftry, Shreyansh

AU - Dawar, Saloni

PY - 2012/8/8

Y1 - 2012/8/8

N2 - Fingerprint verification is an important biometric technique for personal identification. This paper presents a performance evaluation of different fingerprint feature extraction methods. Fingerprint matching scheme based on transform features, like DCT (Discrete Cosine Transform), FFT (Fast Fourier Transform) and DWT (Discrete wavelet transform), have been presented and compared. In the fingerprint recognition application utilizing more information other than minutiae is much helpful. The technique described here obviates the need for extracting minutiae points to match fingerprint images. The transform coefficients are used to obtain the feature vector in terms of standard deviation and energy. Matching is performed using fast Euclidean distance between two feature vectors. The algorithms have been tested on database available from University of Bologna. Our comparison shows that DCT and FFT yields better GAR (Genuine acceptance rate) at low FAR (False acceptance rate) with reduced computational complexity over existing DWT and Gabor based algorithms. Because of reduced computational complexity these algorithms can be easily implemented as an embedded automatic fingerprint identification system (AFIS).

AB - Fingerprint verification is an important biometric technique for personal identification. This paper presents a performance evaluation of different fingerprint feature extraction methods. Fingerprint matching scheme based on transform features, like DCT (Discrete Cosine Transform), FFT (Fast Fourier Transform) and DWT (Discrete wavelet transform), have been presented and compared. In the fingerprint recognition application utilizing more information other than minutiae is much helpful. The technique described here obviates the need for extracting minutiae points to match fingerprint images. The transform coefficients are used to obtain the feature vector in terms of standard deviation and energy. Matching is performed using fast Euclidean distance between two feature vectors. The algorithms have been tested on database available from University of Bologna. Our comparison shows that DCT and FFT yields better GAR (Genuine acceptance rate) at low FAR (False acceptance rate) with reduced computational complexity over existing DWT and Gabor based algorithms. Because of reduced computational complexity these algorithms can be easily implemented as an embedded automatic fingerprint identification system (AFIS).

UR - http://www.scopus.com/inward/record.url?scp=84864771857&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864771857&partnerID=8YFLogxK

U2 - 10.2316/P.2012.778-018

DO - 10.2316/P.2012.778-018

M3 - Conference contribution

AN - SCOPUS:84864771857

SN - 9780889869219

SP - 132

EP - 137

BT - Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012

ER -

Daftry S, Dawar S. Performance evaluation of transform based feature extraction methods for identity authentication system using fingerprint matching. In Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, SPPRA 2012. 2012. p. 132-137 https://doi.org/10.2316/P.2012.778-018