INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
A NOVAL APPROACH TO IRIS RECOGNITION BASED ON FEATURE LEVEL FUSION USING CLASSIFICATION TECHNIQUES �
Authors Name:
SAJJAD SHAIK
, CHAITANYA KONDA
Unique Id:
IJSDR1707047
Published In:
Volume 2 Issue 7, July-2017
Abstract:
Now a days, Security demands are increasing in networked society. With these increases in biometric systems for accurate user authentication are becoming more popular. Iris Recognition System is one of the most popular authentication approach based on Iris of an individual. Every Iris has fine unique texture and does not change overtime. This project proposes a new iris recognition system based on feature level fusion using PCA to improve speed and accuracy of authentication. The iris textures are extracted from 2DGabor filters and Haar wavelet. In this textures are fused and then used to identify genuine users. In order to classify the extracted features process this project is using different classification techniques like KNN, Decision Trees, Multilayer Perceptron, Support Vector Machine (SVM) and Navie Bayes techniques. The proposed Iris recognition system is evaluated basing on Equal Error Rate using FAR and FRR.
Keywords:
filters, PCA, SVM, KNN classifications.
Cite Article:
" A NOVAL APPROACH TO IRIS RECOGNITION BASED ON FEATURE LEVEL FUSION USING CLASSIFICATION TECHNIQUES �", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.2, Issue 7, page no.287 - 292, July-2017, Available :http://www.ijsdr.org/papers/IJSDR1707047.pdf
Downloads:
000336256
Publication Details:
Published Paper ID: IJSDR1707047
Registration ID:170652
Published In: Volume 2 Issue 7, July-2017
DOI (Digital Object Identifier):
Page No: 287 - 292
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn