Identification of individuals using palm vein classification

In this paper, a new algorithm is introduced for palm identification using Gabor filter. First, our proposed method processes images using Gaussian filter and histogram equalization methods. The features are then extracted using bank of Gabor filters. We apply L2-max norm of superposition into outpu...

Full description

Saved in:
Bibliographic Details
Main Authors: Sater, Maha Halla Abdul, Kanaan, Hussein, Ayache, Mohammad
Format: Conference Proceeding
Language:English
Subjects:
bank of Gabor Filter
Biometrics (access control)
execution time
Feature extraction
Gabor filters
Image recognition
multi support vector machine
nearest neighbour's method
Palm vein
Pattern recognition
Support vector machines
Veins
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a new algorithm is introduced for palm identification using Gabor filter. First, our proposed method processes images using Gaussian filter and histogram equalization methods. The features are then extracted using bank of Gabor filters. We apply L2-max norm of superposition into output of Gabor filter to reduce the dimension of the features vector. Finally support vector machine (SVM) and Nearest Neighbours classifiers are used for palm vein verification. Our proposed method is evaluated using a public dataset, named VP. The efficiency of the identification process by the proposed methods is highly compared to the traditional one where simplified extraction features methods is used. The experimental results confirm that the introduced approach is efficient compared to the traditional methods.
ISSN:2377-5696
DOI:10.1109/ICABME47164.2019.8940324