Finger Vein Recognition Using Pattern Map As Feature Extraction

Today, finger vein has become a new biometric technology. The challenge of finger vein recognition comes to during the process of feature extraction. Since the low contrast finger vein images may contain shading and noise, it is important to precisely preprocess, extract and preserve the vein pat...

Full description

Saved in:

Bibliographic Details
Main Author:	Teoh, Saw Beng
Format:	Thesis
Language:	English
Published:	2012
Subjects:	TK1-9971 Electrical engineering Electronics Nuclear engineering
Online Access:	http://eprints.usm.my/60803/1/24%20Pages%20from%2000001780130.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.60803
record_format	uketd_dc
spelling	my-usm-ep.608032024-07-09T05:02:39Z Finger Vein Recognition Using Pattern Map As Feature Extraction 2012-11 Teoh, Saw Beng TK1-9971 Electrical engineering. Electronics. Nuclear engineering Today, finger vein has become a new biometric technology. The challenge of finger vein recognition comes to during the process of feature extraction. Since the low contrast finger vein images may contain shading and noise, it is important to precisely preprocess, extract and preserve the vein patterns. Algorithms such as Gabor Filter, Local Line Binary Pattern (LLBP) and Principal Component Analysis (PCA) have been proposed in recent study to extract finger vein features. In this thesis, a modified pattern map feature extraction method is proposed for finger vein recognition. Instead of obtaining fmger vein features from multi-filtered images, the features images are generated from pattern templates which are the eigenveins obtained from PCA process. Every fmger vein image is then transformed into pattern map images from a pattern matching process between an input finger vein image and the pattern templates. Finally, nearest neighbour classifier with Euclidean distance metrics is used for classification. The main contribution of this thesis is the new way of generating pattern templates, which selects small blocks from every class within an area of constraint. Additionally, pattern map is implemented in finger vein recognition for the first time. Experimental results show that the proposed pattern map algorithm has better performance with a consistent identification rate of 99% and above compared to existing methods such as PCA and Gabor with FVCode. This shows that pattern map is a reliable feature extraction method and is able to represent finger vein pattern effectively. 2012-11 Thesis http://eprints.usm.my/60803/ http://eprints.usm.my/60803/1/24%20Pages%20from%2000001780130.pdf application/pdf en public masters Perpustakaan Hamzah Sendut Pusat Pengajian Kejuruteraan Elektrik & Elektronik
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	TK1-9971 Electrical engineering Electronics Nuclear engineering
spellingShingle	TK1-9971 Electrical engineering Electronics Nuclear engineering Teoh, Saw Beng Finger Vein Recognition Using Pattern Map As Feature Extraction
description	Today, finger vein has become a new biometric technology. The challenge of finger vein recognition comes to during the process of feature extraction. Since the low contrast finger vein images may contain shading and noise, it is important to precisely preprocess, extract and preserve the vein patterns. Algorithms such as Gabor Filter, Local Line Binary Pattern (LLBP) and Principal Component Analysis (PCA) have been proposed in recent study to extract finger vein features. In this thesis, a modified pattern map feature extraction method is proposed for finger vein recognition. Instead of obtaining fmger vein features from multi-filtered images, the features images are generated from pattern templates which are the eigenveins obtained from PCA process. Every fmger vein image is then transformed into pattern map images from a pattern matching process between an input finger vein image and the pattern templates. Finally, nearest neighbour classifier with Euclidean distance metrics is used for classification. The main contribution of this thesis is the new way of generating pattern templates, which selects small blocks from every class within an area of constraint. Additionally, pattern map is implemented in finger vein recognition for the first time. Experimental results show that the proposed pattern map algorithm has better performance with a consistent identification rate of 99% and above compared to existing methods such as PCA and Gabor with FVCode. This shows that pattern map is a reliable feature extraction method and is able to represent finger vein pattern effectively.
format	Thesis
qualification_level	Master's degree
author	Teoh, Saw Beng
author_facet	Teoh, Saw Beng
author_sort	Teoh, Saw Beng
title	Finger Vein Recognition Using Pattern Map As Feature Extraction
title_short	Finger Vein Recognition Using Pattern Map As Feature Extraction
title_full	Finger Vein Recognition Using Pattern Map As Feature Extraction
title_fullStr	Finger Vein Recognition Using Pattern Map As Feature Extraction
title_full_unstemmed	Finger Vein Recognition Using Pattern Map As Feature Extraction
title_sort	finger vein recognition using pattern map as feature extraction
granting_institution	Perpustakaan Hamzah Sendut
granting_department	Pusat Pengajian Kejuruteraan Elektrik & Elektronik
publishDate	2012
url	http://eprints.usm.my/60803/1/24%20Pages%20from%2000001780130.pdf
_version_	1804888999950548992

Finger Vein Recognition Using Pattern Map As Feature Extraction

Similar Items