Staff View: An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification

An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification

Finger vein biometrics is one of the most promising ways to identify a person because it can provide uniqueness, protection against forgery, and bioassay. Due to the limitations of the imaging environments, however, the finger vein images that are taken can quickly become low-contrast, blurry, and v...

Full description

Saved in:

Bibliographic Details
Main Authors:	Sulaiman, Dawlat Mustafa, Abdulazeez, Adnan Mohsin, Asaad Zebar, Dilovan, Diyar Qader Zeebaree, Diyar Qader Zeebaree, A. Mostafa, Salama, Saleem Sadiq, Shereen
Format:	Article
Language:	English
Published:	IIETA 2023
Subjects:	T Technology (General)
Online Access:	http://eprints.uthm.edu.my/9062/1/J15753_aac300d0e453cca2bcb3c5f096e94385.pdf http://eprints.uthm.edu.my/9062/ https://doi.org/10.18280/ts.390611
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uthm.eprints.9062
record_format	eprints
spelling	my.uthm.eprints.90622023-06-25T07:09:25Z http://eprints.uthm.edu.my/9062/ An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification Sulaiman, Dawlat Mustafa Abdulazeez, Adnan Mohsin Asaad Zebar, Dilovan Diyar Qader Zeebaree, Diyar Qader Zeebaree A. Mostafa, Salama Saleem Sadiq, Shereen T Technology (General) Finger vein biometrics is one of the most promising ways to identify a person because it can provide uniqueness, protection against forgery, and bioassay. Due to the limitations of the imaging environments, however, the finger vein images that are taken can quickly become low-contrast, blurry, and very noisy. Therefore, more robust and relevant feature extraction from the finger vein images is still open research that should be addressed. In this paper, we propose a new technique of deep learning that is based on the attention mechanisms for human finger vein image identification and recognition and is called deep regional learning. Our proposed model relies on an unsupervised learning method that depends on optimized K-Means clustering for localized finger vein mask generation. The generated binary mask is used to build our attention learning model by making the deep learning structure focus on the region-of-interest (ROI) learning instead of learning the whole feature domain. This technique makes the Deep Regional Attention Model learn more significant features with less time and computational resources than the regular deep learning model. For experimental validation, we used different finger vein imaging datasets that have been extracted and generated using our model. Original finger vein images, localized finger vein images (with no background), localized grayscale finger vein images (grayscale images with no background and projected finger vein lines), and localized colored finger vein images (colored images with no background and projected finger vein lines) are used to train and test our model, which gets better results than traditional deep learning and other methods IIETA 2023 Article PeerReviewed text en http://eprints.uthm.edu.my/9062/1/J15753_aac300d0e453cca2bcb3c5f096e94385.pdf Sulaiman, Dawlat Mustafa and Abdulazeez, Adnan Mohsin and Asaad Zebar, Dilovan and Diyar Qader Zeebaree, Diyar Qader Zeebaree and A. Mostafa, Salama and Saleem Sadiq, Shereen (2023) An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification. Traitement du Signal, 39 (6). pp. 1991-2001. https://doi.org/10.18280/ts.390611
institution	Universiti Tun Hussein Onn Malaysia
building	UTHM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Tun Hussein Onn Malaysia
content_source	UTHM Institutional Repository
url_provider	http://eprints.uthm.edu.my/
language	English
topic	T Technology (General)
spellingShingle	T Technology (General) Sulaiman, Dawlat Mustafa Abdulazeez, Adnan Mohsin Asaad Zebar, Dilovan Diyar Qader Zeebaree, Diyar Qader Zeebaree A. Mostafa, Salama Saleem Sadiq, Shereen An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification
description	Finger vein biometrics is one of the most promising ways to identify a person because it can provide uniqueness, protection against forgery, and bioassay. Due to the limitations of the imaging environments, however, the finger vein images that are taken can quickly become low-contrast, blurry, and very noisy. Therefore, more robust and relevant feature extraction from the finger vein images is still open research that should be addressed. In this paper, we propose a new technique of deep learning that is based on the attention mechanisms for human finger vein image identification and recognition and is called deep regional learning. Our proposed model relies on an unsupervised learning method that depends on optimized K-Means clustering for localized finger vein mask generation. The generated binary mask is used to build our attention learning model by making the deep learning structure focus on the region-of-interest (ROI) learning instead of learning the whole feature domain. This technique makes the Deep Regional Attention Model learn more significant features with less time and computational resources than the regular deep learning model. For experimental validation, we used different finger vein imaging datasets that have been extracted and generated using our model. Original finger vein images, localized finger vein images (with no background), localized grayscale finger vein images (grayscale images with no background and projected finger vein lines), and localized colored finger vein images (colored images with no background and projected finger vein lines) are used to train and test our model, which gets better results than traditional deep learning and other methods
format	Article
author	Sulaiman, Dawlat Mustafa Abdulazeez, Adnan Mohsin Asaad Zebar, Dilovan Diyar Qader Zeebaree, Diyar Qader Zeebaree A. Mostafa, Salama Saleem Sadiq, Shereen
author_facet	Sulaiman, Dawlat Mustafa Abdulazeez, Adnan Mohsin Asaad Zebar, Dilovan Diyar Qader Zeebaree, Diyar Qader Zeebaree A. Mostafa, Salama Saleem Sadiq, Shereen
author_sort	Sulaiman, Dawlat Mustafa
title	An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification
title_short	An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification
title_full	An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification
title_fullStr	An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification
title_full_unstemmed	An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification
title_sort	attention-based deep regional learning model for enhanced finger vein identification
publisher	IIETA
publishDate	2023
url	http://eprints.uthm.edu.my/9062/1/J15753_aac300d0e453cca2bcb3c5f096e94385.pdf http://eprints.uthm.edu.my/9062/ https://doi.org/10.18280/ts.390611
_version_	1769845134049935360
score	13.223943

An Attention-Based Deep Regional Learning Model for Enhanced Finger Vein Identification

Similar Items