Fast Fingerprint Classification with Deep Neural Networks

Daniel Michelsanti, Andreea-Daniela Ene, Yanis Guichi, Rares Stef, Kamal Nasrollahi, Thomas B. Moeslund

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

8 Citations (Scopus)
1727 Downloads (Pure)

Abstract

Reducing the number of comparisons in automated fingerprint identification systems is essential when dealing with a large database. Fingerprint classification allows to achieve this goal by dividing fingerprints into several categories, but it presents still some challenges due to the large intra-class variations and the small inter-class variations. The vast majority of the previous methods uses global characteristics, in particular the orientation image, as features of a classifier. This makes the feature extraction stage highly dependent on preprocessing techniques and usually computationally expensive. In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage.
Original languageEnglish
Title of host publicationVISiGRAPP 2017 : Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
EditorsFrancisco Imai, Alain Tremeau, Jose Braz
Volume5
PublisherSCITEPRESS Digital Library
Publication date2017
Pages202-209
ISBN (Print)978-989-758-226-4
DOIs
Publication statusPublished - 2017
EventInternational Conference on Computer Vision Theory and Applications - Porto, Portugal
Duration: 27 Feb 20171 Mar 2017
Conference number: 12
http://www.visapp.visigrapp.org

Conference

ConferenceInternational Conference on Computer Vision Theory and Applications
Number12
CountryPortugal
CityPorto
Period27/02/201701/03/2017
Internet address

Fingerprint

Feature extraction
Identification (control systems)
Classifiers
Neural networks
Deep neural networks

Cite this

Michelsanti, D., Ene, A-D., Guichi, Y., Stef, R., Nasrollahi, K., & Moeslund, T. B. (2017). Fast Fingerprint Classification with Deep Neural Networks. In F. Imai, A. Tremeau, & J. Braz (Eds.), VISiGRAPP 2017: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 5, pp. 202-209). SCITEPRESS Digital Library. https://doi.org/10.5220/0006116502020209
Michelsanti, Daniel ; Ene, Andreea-Daniela ; Guichi, Yanis ; Stef, Rares ; Nasrollahi, Kamal ; Moeslund, Thomas B. / Fast Fingerprint Classification with Deep Neural Networks. VISiGRAPP 2017: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. editor / Francisco Imai ; Alain Tremeau ; Jose Braz. Vol. 5 SCITEPRESS Digital Library, 2017. pp. 202-209
@inproceedings{e8c9084c62fd4cec9fd8f36a636fcb78,
title = "Fast Fingerprint Classification with Deep Neural Networks",
abstract = "Reducing the number of comparisons in automated fingerprint identification systems is essential when dealing with a large database. Fingerprint classification allows to achieve this goal by dividing fingerprints into several categories, but it presents still some challenges due to the large intra-class variations and the small inter-class variations. The vast majority of the previous methods uses global characteristics, in particular the orientation image, as features of a classifier. This makes the feature extraction stage highly dependent on preprocessing techniques and usually computationally expensive. In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage.",
author = "Daniel Michelsanti and Andreea-Daniela Ene and Yanis Guichi and Rares Stef and Kamal Nasrollahi and Moeslund, {Thomas B.}",
year = "2017",
doi = "10.5220/0006116502020209",
language = "English",
isbn = "978-989-758-226-4",
volume = "5",
pages = "202--209",
editor = "Francisco Imai and Alain Tremeau and Jose Braz",
booktitle = "VISiGRAPP 2017",
publisher = "SCITEPRESS Digital Library",

}

Michelsanti, D, Ene, A-D, Guichi, Y, Stef, R, Nasrollahi, K & Moeslund, TB 2017, Fast Fingerprint Classification with Deep Neural Networks. in F Imai, A Tremeau & J Braz (eds), VISiGRAPP 2017: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. vol. 5, SCITEPRESS Digital Library, pp. 202-209, International Conference on Computer Vision Theory and Applications, Porto, Portugal, 27/02/2017. https://doi.org/10.5220/0006116502020209

Fast Fingerprint Classification with Deep Neural Networks. / Michelsanti, Daniel; Ene, Andreea-Daniela; Guichi, Yanis; Stef, Rares; Nasrollahi, Kamal; Moeslund, Thomas B.

VISiGRAPP 2017: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. ed. / Francisco Imai; Alain Tremeau; Jose Braz. Vol. 5 SCITEPRESS Digital Library, 2017. p. 202-209.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Fast Fingerprint Classification with Deep Neural Networks

AU - Michelsanti, Daniel

AU - Ene, Andreea-Daniela

AU - Guichi, Yanis

AU - Stef, Rares

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2017

Y1 - 2017

N2 - Reducing the number of comparisons in automated fingerprint identification systems is essential when dealing with a large database. Fingerprint classification allows to achieve this goal by dividing fingerprints into several categories, but it presents still some challenges due to the large intra-class variations and the small inter-class variations. The vast majority of the previous methods uses global characteristics, in particular the orientation image, as features of a classifier. This makes the feature extraction stage highly dependent on preprocessing techniques and usually computationally expensive. In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage.

AB - Reducing the number of comparisons in automated fingerprint identification systems is essential when dealing with a large database. Fingerprint classification allows to achieve this goal by dividing fingerprints into several categories, but it presents still some challenges due to the large intra-class variations and the small inter-class variations. The vast majority of the previous methods uses global characteristics, in particular the orientation image, as features of a classifier. This makes the feature extraction stage highly dependent on preprocessing techniques and usually computationally expensive. In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage.

U2 - 10.5220/0006116502020209

DO - 10.5220/0006116502020209

M3 - Article in proceeding

SN - 978-989-758-226-4

VL - 5

SP - 202

EP - 209

BT - VISiGRAPP 2017

A2 - Imai, Francisco

A2 - Tremeau, Alain

A2 - Braz, Jose

PB - SCITEPRESS Digital Library

ER -

Michelsanti D, Ene A-D, Guichi Y, Stef R, Nasrollahi K, Moeslund TB. Fast Fingerprint Classification with Deep Neural Networks. In Imai F, Tremeau A, Braz J, editors, VISiGRAPP 2017: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Vol. 5. SCITEPRESS Digital Library. 2017. p. 202-209 https://doi.org/10.5220/0006116502020209