Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction

Finger vein identification is a potential new area in biometric systems. Finger vein patterns contain highly discriminative characteristics, which are difficult to be forged because they reside underneath the skin of the finger and require a specific device to capture them. Research have been carrie...

Full description

Saved in:

Bibliographic Details
Main Author:	Akintoye, Kayode Akinlekan
Format:	Thesis
Language:	English
Published:	2019
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/96178/1/KayodeAkinlekanAkintoyePSC2019.pdf.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.96178
record_format	uketd_dc
spelling	my-utm-ep.961782022-07-04T08:04:16Z Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction 2019 Akintoye, Kayode Akinlekan QA75 Electronic computers. Computer science Finger vein identification is a potential new area in biometric systems. Finger vein patterns contain highly discriminative characteristics, which are difficult to be forged because they reside underneath the skin of the finger and require a specific device to capture them. Research have been carried out in this field but there is still an unresolved issue related to low-quality data due to data capturing and processing. Low-quality data have caused errors in the feature extraction process and reduced identification performance rate in finger vein identification. To address this issue, a new image enhancement and feature extraction methods were developed to improve finger vein identification. The image enhancement, Composite Median-Wiener (CMW) filter would improve image quality and preserve the edges of the finger vein image. Next, the feature extraction method, Hierarchical Centroid Feature Method (HCM) was fused with statistical pixel-based distribution feature method at the feature-level fusion to improve the performance of finger vein identification. These methods were evaluated on public SDUMLA-HMT and FV-USM finger vein databases. Each database was divided into training and testing sets. The average result of the experiments conducted was taken to ensure the accuracy of the measurements. The k-Nearest Neighbor classifier with city block distance to match the features was implemented. Both these methods produced accuracy as high as 97.64% for identification rate and 1.11% of equal error rate (EER) for measures verification rate. These showed that the accuracy of the proposed finger vein identification method is higher than the one reported in the literature. As a conclusion, the results have proven that the CMW filter and HCM have significantly improved the accuracy of finger vein identification. 2019 Thesis http://eprints.utm.my/id/eprint/96178/ http://eprints.utm.my/id/eprint/96178/1/KayodeAkinlekanAkintoyePSC2019.pdf.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:142063 phd doctoral Universiti Teknologi Malaysia Faculty of Engineering - School of Computing
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA75 Electronic computers Computer science
spellingShingle	QA75 Electronic computers Computer science Akintoye, Kayode Akinlekan Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction
description	Finger vein identification is a potential new area in biometric systems. Finger vein patterns contain highly discriminative characteristics, which are difficult to be forged because they reside underneath the skin of the finger and require a specific device to capture them. Research have been carried out in this field but there is still an unresolved issue related to low-quality data due to data capturing and processing. Low-quality data have caused errors in the feature extraction process and reduced identification performance rate in finger vein identification. To address this issue, a new image enhancement and feature extraction methods were developed to improve finger vein identification. The image enhancement, Composite Median-Wiener (CMW) filter would improve image quality and preserve the edges of the finger vein image. Next, the feature extraction method, Hierarchical Centroid Feature Method (HCM) was fused with statistical pixel-based distribution feature method at the feature-level fusion to improve the performance of finger vein identification. These methods were evaluated on public SDUMLA-HMT and FV-USM finger vein databases. Each database was divided into training and testing sets. The average result of the experiments conducted was taken to ensure the accuracy of the measurements. The k-Nearest Neighbor classifier with city block distance to match the features was implemented. Both these methods produced accuracy as high as 97.64% for identification rate and 1.11% of equal error rate (EER) for measures verification rate. These showed that the accuracy of the proposed finger vein identification method is higher than the one reported in the literature. As a conclusion, the results have proven that the CMW filter and HCM have significantly improved the accuracy of finger vein identification.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Akintoye, Kayode Akinlekan
author_facet	Akintoye, Kayode Akinlekan
author_sort	Akintoye, Kayode Akinlekan
title	Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction
title_short	Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction
title_full	Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction
title_fullStr	Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction
title_full_unstemmed	Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction
title_sort	improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction
granting_institution	Universiti Teknologi Malaysia
granting_department	Faculty of Engineering - School of Computing
publishDate	2019
url	http://eprints.utm.my/id/eprint/96178/1/KayodeAkinlekanAkintoyePSC2019.pdf.pdf
_version_	1747818643366871040

Improved methods for finger vein identification using composite median-wiener filter and hierarchical centroid features extraction

Similar Items