- Reference number: MR-02
- PREPRINT: https://arxiv.org/abs/2002.03809
- Old database: https://andrewyzy.github.io/L3-SF/
- Video presentation (L3-SF): https://youtu.be/AueL2WUEjD4
- A public database of L3 and L2 synthetic fingerprint images, each one containing five subsets of 148 identities, with 10 samples per identity, totaling 14800 high-resolution fingerprint images.
- We include sweat pore annotations for 740 images to assist in pore detection research.
- The synthetic fingerprints contain L3 traits, such as distinct ridge contours and incipient ridges, features that increase the reliability of fingerprint recognition.
- Huge texture improvement on the fingerprint images.
- Scratches on fingerprint images.
- André Brasil Vieira Wyzykowski
- Mauricio Pamplona Segundo
- Rubisley de Paula Lemes
@misc{wyzykowski2020level,
title={Level Three Synthetic Fingerprint Generation},
author={André Brasil Vieira Wyzykowski and Mauricio Pamplona Segundo and Rubisley de Paula Lemes},
year={2020},
eprint={2002.03809},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
Copyright (c) 2021, André Brasil Vieira Wyzykowski, Mauricio Pamplona Segundo, Rubisley de Paula Lemes, Federal University of Bahia, Salvador, Brazil
This work is licensed under the Attribution-NonCommercial-ShareAlike 4.0 International License.
To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-sa/4.0/
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.