Cover Image

Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali

Fingerprint presentation attack, which involves presenting spoof fingerprints to fingerprint bio metric sensors to gain illicit access, is a significant challenge faced by Automatic Fingerprint Identification Systems (AFIS). As a result, various hardware-based and software-based approaches have been...

Full description

Saved in:
Bibliographic Details
Main Authors: S. Ametefe, Divine, S. Seroja, Suzi, M. Ali, Darmawaty
Format: Article
Language:English
Published: Universiti Teknologi MARA 2021
Subjects:
Electric apparatus and materials. Electric circuits. Electric networks
Radio frequency identification systems
Scanning systems
Online Access:https://ir.uitm.edu.my/id/eprint/52075/1/52075.pdf
https://ir.uitm.edu.my/id/eprint/52075/
https://jeesr.uitm.edu.my/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uitm.ir.52075
record_format eprints
spelling my.uitm.ir.520752021-10-07T09:23:56Z https://ir.uitm.edu.my/id/eprint/52075/ Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali S. Ametefe, Divine S. Seroja, Suzi M. Ali, Darmawaty Electric apparatus and materials. Electric circuits. Electric networks Radio frequency identification systems Scanning systems Fingerprint presentation attack, which involves presenting spoof fingerprints to fingerprint bio metric sensors to gain illicit access, is a significant challenge faced by Automatic Fingerprint Identification Systems (AFIS). As a result, various hardware-based and software-based approaches have been posited to help remedy this concern. However, the software-based methods have seen enormous utilization relative to the hardware-based techniques due to their robust cognitive feature extraction for spoof detection. Nonetheless, most software-based techniques that utilize handcrafted features proffer shallow features for discriminating against spoofs due to their manual feature extraction process, which, as a result, affects the model's robustness. Motivated by this concern, we propose a deep transfer learning approach to automatically learn deep hierarchical semantic fingerprint features as a means of discriminating against spoofs. Experiments were conducted on the LivDet competition standard database, encompassing datasets from LivDet-2009, 2011, 2013, and 2015, resulting in the acquisition of real fingerprints and fake fingerprints fabricated from twelve (12) different spoofing materials. The developed model recorded an average classification accuracy of 99.8%, a sensitivity of 99.73% and a specificity of 99.77%, showcasing a state-of-the-art performance. Universiti Teknologi MARA 2021-10 Article PeerReviewed text en https://ir.uitm.edu.my/id/eprint/52075/1/52075.pdf ID52075 S. Ametefe, Divine and S. Seroja, Suzi and M. Ali, Darmawaty (2021) Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali. Journal of Electrical and Electronic Systems Research (JEESR), 19: 11. pp. 95-105. ISSN 1985-5389 https://jeesr.uitm.edu.my/
institution Universiti Teknologi Mara
building Tun Abdul Razak Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Mara
content_source UiTM Institutional Repository
url_provider http://ir.uitm.edu.my/
language English
topic Electric apparatus and materials. Electric circuits. Electric networks
Radio frequency identification systems
Scanning systems
spellingShingle Electric apparatus and materials. Electric circuits. Electric networks
Radio frequency identification systems
Scanning systems
S. Ametefe, Divine
S. Seroja, Suzi
M. Ali, Darmawaty
Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali
description Fingerprint presentation attack, which involves presenting spoof fingerprints to fingerprint bio metric sensors to gain illicit access, is a significant challenge faced by Automatic Fingerprint Identification Systems (AFIS). As a result, various hardware-based and software-based approaches have been posited to help remedy this concern. However, the software-based methods have seen enormous utilization relative to the hardware-based techniques due to their robust cognitive feature extraction for spoof detection. Nonetheless, most software-based techniques that utilize handcrafted features proffer shallow features for discriminating against spoofs due to their manual feature extraction process, which, as a result, affects the model's robustness. Motivated by this concern, we propose a deep transfer learning approach to automatically learn deep hierarchical semantic fingerprint features as a means of discriminating against spoofs. Experiments were conducted on the LivDet competition standard database, encompassing datasets from LivDet-2009, 2011, 2013, and 2015, resulting in the acquisition of real fingerprints and fake fingerprints fabricated from twelve (12) different spoofing materials. The developed model recorded an average classification accuracy of 99.8%, a sensitivity of 99.73% and a specificity of 99.77%, showcasing a state-of-the-art performance.
format Article
author S. Ametefe, Divine
S. Seroja, Suzi
M. Ali, Darmawaty
author_facet S. Ametefe, Divine
S. Seroja, Suzi
M. Ali, Darmawaty
author_sort S. Ametefe, Divine
title Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali
title_short Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali
title_full Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali
title_fullStr Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali
title_full_unstemmed Fingerprint presentation attack detection using deep transfer learning and densenet201 network / Divine S. Ametefe, Suzi S. Seroja, and Darmawaty M. Ali
title_sort fingerprint presentation attack detection using deep transfer learning and densenet201 network / divine s. ametefe, suzi s. seroja, and darmawaty m. ali
publisher Universiti Teknologi MARA
publishDate 2021
url https://ir.uitm.edu.my/id/eprint/52075/1/52075.pdf
https://ir.uitm.edu.my/id/eprint/52075/
https://jeesr.uitm.edu.my/
_version_ 1713202960850223104
score 13.211869

Similar Items