An adaptive multiresolution approach to fingerprint recognition

Amina Chebira, Luis P. Coelho, Aliaksei Sandryhaila, Stephen Lin, William G. Jenkinson, Jeremiah MacSleyne, Christopher Hoffman, Philipp Cuadra, Charles Jackson, Markus Püschel, Jelena Kovacevic

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

Abstract

We propose an adaptive multiresolution (MR) approach to the classification of fingerprint images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. In our previous work on classification of protein subcellular location images, we showed that the space-frequency localized information in the MR subspaces adds significantly to the discriminative power of the system. Here, we go one step farther; We develop a new weighting method which allows for the discriminative power of each subband to be expressed and examined within each class. This, in turn, allows us to evaluate the importance of the information contained within a specific subband. Moreover, we develop a pruning procedure to eliminate the subbands that do not contain useful information. This leads to potential identification of the appropriate MR decomposition both on a per class basis and for a given dataset. With this new approach, we make the system adaptive, flexible as well as more accurate and efficient.

Original languageEnglish (US)
Title of host publication2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
Volume1
DOIs
StatePublished - Dec 1 2006
Event14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States
Duration: Sep 16 2007Sep 19 2007

Other

Other14th IEEE International Conference on Image Processing, ICIP 2007
CountryUnited States
CitySan Antonio, TX
Period9/16/079/19/07

Fingerprint

Decomposition
Adaptive systems
Classifiers
Proteins

Keywords

  • Biometrics
  • Classification
  • Fingerprint images
  • Multiresolution techniques

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Chebira, A., Coelho, L. P., Sandryhaila, A., Lin, S., Jenkinson, W. G., MacSleyne, J., ... Kovacevic, J. (2006). An adaptive multiresolution approach to fingerprint recognition. In 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings (Vol. 1). [4378990] https://doi.org/10.1109/ICIP.2007.4378990

An adaptive multiresolution approach to fingerprint recognition. / Chebira, Amina; Coelho, Luis P.; Sandryhaila, Aliaksei; Lin, Stephen; Jenkinson, William G.; MacSleyne, Jeremiah; Hoffman, Christopher; Cuadra, Philipp; Jackson, Charles; Püschel, Markus; Kovacevic, Jelena.

2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 1 2006. 4378990.

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

Chebira, A, Coelho, LP, Sandryhaila, A, Lin, S, Jenkinson, WG, MacSleyne, J, Hoffman, C, Cuadra, P, Jackson, C, Püschel, M & Kovacevic, J 2006, An adaptive multiresolution approach to fingerprint recognition. in 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. vol. 1, 4378990, 14th IEEE International Conference on Image Processing, ICIP 2007, San Antonio, TX, United States, 9/16/07. https://doi.org/10.1109/ICIP.2007.4378990
Chebira A, Coelho LP, Sandryhaila A, Lin S, Jenkinson WG, MacSleyne J et al. An adaptive multiresolution approach to fingerprint recognition. In 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 1. 2006. 4378990 https://doi.org/10.1109/ICIP.2007.4378990
Chebira, Amina ; Coelho, Luis P. ; Sandryhaila, Aliaksei ; Lin, Stephen ; Jenkinson, William G. ; MacSleyne, Jeremiah ; Hoffman, Christopher ; Cuadra, Philipp ; Jackson, Charles ; Püschel, Markus ; Kovacevic, Jelena. / An adaptive multiresolution approach to fingerprint recognition. 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 1 2006.
@inproceedings{2b13c029651441dab4f89f31da65478e,
title = "An adaptive multiresolution approach to fingerprint recognition",
abstract = "We propose an adaptive multiresolution (MR) approach to the classification of fingerprint images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. In our previous work on classification of protein subcellular location images, we showed that the space-frequency localized information in the MR subspaces adds significantly to the discriminative power of the system. Here, we go one step farther; We develop a new weighting method which allows for the discriminative power of each subband to be expressed and examined within each class. This, in turn, allows us to evaluate the importance of the information contained within a specific subband. Moreover, we develop a pruning procedure to eliminate the subbands that do not contain useful information. This leads to potential identification of the appropriate MR decomposition both on a per class basis and for a given dataset. With this new approach, we make the system adaptive, flexible as well as more accurate and efficient.",
keywords = "Biometrics, Classification, Fingerprint images, Multiresolution techniques",
author = "Amina Chebira and Coelho, {Luis P.} and Aliaksei Sandryhaila and Stephen Lin and Jenkinson, {William G.} and Jeremiah MacSleyne and Christopher Hoffman and Philipp Cuadra and Charles Jackson and Markus P{\"u}schel and Jelena Kovacevic",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICIP.2007.4378990",
language = "English (US)",
isbn = "1424414377",
volume = "1",
booktitle = "2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings",

}

TY - GEN

T1 - An adaptive multiresolution approach to fingerprint recognition

AU - Chebira, Amina

AU - Coelho, Luis P.

AU - Sandryhaila, Aliaksei

AU - Lin, Stephen

AU - Jenkinson, William G.

AU - MacSleyne, Jeremiah

AU - Hoffman, Christopher

AU - Cuadra, Philipp

AU - Jackson, Charles

AU - Püschel, Markus

AU - Kovacevic, Jelena

PY - 2006/12/1

Y1 - 2006/12/1

N2 - We propose an adaptive multiresolution (MR) approach to the classification of fingerprint images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. In our previous work on classification of protein subcellular location images, we showed that the space-frequency localized information in the MR subspaces adds significantly to the discriminative power of the system. Here, we go one step farther; We develop a new weighting method which allows for the discriminative power of each subband to be expressed and examined within each class. This, in turn, allows us to evaluate the importance of the information contained within a specific subband. Moreover, we develop a pruning procedure to eliminate the subbands that do not contain useful information. This leads to potential identification of the appropriate MR decomposition both on a per class basis and for a given dataset. With this new approach, we make the system adaptive, flexible as well as more accurate and efficient.

AB - We propose an adaptive multiresolution (MR) approach to the classification of fingerprint images. The system adds MR decomposition in front of a generic classifier consisting of feature computation and classification in each MR subspace, yielding local decisions, which are then combined into a global decision using a weighting algorithm. In our previous work on classification of protein subcellular location images, we showed that the space-frequency localized information in the MR subspaces adds significantly to the discriminative power of the system. Here, we go one step farther; We develop a new weighting method which allows for the discriminative power of each subband to be expressed and examined within each class. This, in turn, allows us to evaluate the importance of the information contained within a specific subband. Moreover, we develop a pruning procedure to eliminate the subbands that do not contain useful information. This leads to potential identification of the appropriate MR decomposition both on a per class basis and for a given dataset. With this new approach, we make the system adaptive, flexible as well as more accurate and efficient.

KW - Biometrics

KW - Classification

KW - Fingerprint images

KW - Multiresolution techniques

UR - http://www.scopus.com/inward/record.url?scp=48149103932&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48149103932&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2007.4378990

DO - 10.1109/ICIP.2007.4378990

M3 - Conference contribution

AN - SCOPUS:48149103932

SN - 1424414377

SN - 9781424414376

VL - 1

BT - 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings

ER -