Local line binary pattern and Fuzzy K-NN for palm vein recognition

Holle, Khadijah Fahmi Hayati and Sari, Jayanti Yusmah and Pasrun, Yuwanda Purnamasari (2017) Local line binary pattern and Fuzzy K-NN for palm vein recognition. Journal of Theoretical and Applied Information Technology, 95 (13). pp. 2906-2912. ISSN 1992-8645

[img]
Preview
Text (full text)
2587.pdf - Published Version

Download (694kB) | Preview
Full text available at: http://www.jatit.org/volumes/ninetyfive13.php

Abstract

Recently, palm vein recognition has been studied to overcome the problem in terms of convenience and performance of conventional systems in biometrics technologies such as fingerprint, palm print, face, and iris recognitions. However, palm vein images that are used in palm vein recognition systems are not always clear but sometimes can show irregular shadings and highly saturated regions that can slow the processing time. To overcome this problem, we propose palm vein recognition system using Local Line Binary Pattern (LLBP) method that was reliable against irregular shadings and highly saturated regions. LLBP is a texture descriptor based on the gray level comparison of a neighborhood of pixels. Proposed method have been conducted in three major steps: preprocessing that includes Region of Interest (ROI) detection, image resizing, noise removal and image enhancement, feature extraction using LLBP method, and matching using Fuzzy k-NN classifier. We use CASIA Multi-Spectral Image Database as dataset to examine proposed method. Experimental results show that the proposed method using LLBP has a good performance with 93.2% recognition accuracy.

Item Type: Journal Article
Keywords: Fuzzy K-NN; LLBP; Local line binary pattern; Palm vein
Divisions: Faculty of Technology > Department of Informatics Engineering
Depositing User: Dian Anesti
Date Deposited: 28 May 2018 04:41

Downloads

Downloads per month over past year

Origin of downloads

Actions (login required)

View Item View Item