Deep Minutiae Fingerprint Extraction Using Equivariance Priors

Margarida Gouveia, Margarida Gouveia, Eduardo Castro, Eduardo Castro, Ana Rebelo, Jaime Cardoso, Jaime Cardoso, Bruno Patrão, Bruno Patrão

2023

Abstract

Currently, fingerprints are one of the most explored characteristics in biometric systems. These systems typically rely on minutiae extraction, a task highly dependent on image quality, orientation, and size of the fingerprint images. In this paper, a U-Net model capable of performing minutiae extraction is proposed (position, angle, and type). Based on this model, we explore two different ways of regularizing the model based on equivariance priors. First, we adapt the model architecture so that it becomes equivariant to rotations. Second, we use a multi-task learning approach in order to extract a more comprehensive set of information from the fingerprints (binary images, segmentation, frequencies, and orientation maps). The two approaches improved accuracy and generalization capability in comparison with the baseline model. On the 16 test datasets of the Fingerprint Verification Competition, we obtained an average Equal-Error Rate (EER) of 2.26, which was better than a well-optimized commercial product.

Paper Citation

in Harvard Style

Gouveia M., Castro E., Rebelo A., Cardoso J. and Patrão B. (2023). Deep Minutiae Fingerprint Extraction Using Equivariance Priors. In Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 4: BIOSIGNALS; ISBN 978-989-758-631-6, SciTePress, pages 241-251. DOI: 10.5220/0011673500003414

in Bibtex Style

@conference{biosignals23,
author={Margarida Gouveia and Eduardo Castro and Ana Rebelo and Jaime Cardoso and Bruno Patrão},
title={Deep Minutiae Fingerprint Extraction Using Equivariance Priors},
booktitle={Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 4: BIOSIGNALS},
year={2023},
pages={241-251},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011673500003414},
isbn={978-989-758-631-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 4: BIOSIGNALS
TI - Deep Minutiae Fingerprint Extraction Using Equivariance Priors
SN - 978-989-758-631-6
AU - Gouveia M.
AU - Castro E.
AU - Rebelo A.
AU - Cardoso J.
AU - Patrão B.
PY - 2023
SP - 241
EP - 251
DO - 10.5220/0011673500003414
PB - SciTePress