Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/17476
Title: Performance Analysis and Recognition of Iris Patterns for Human Authentication Using a Modified Approach
Researcher: G.Savithri
Guide(s): Dr.A.Murugan
Keywords: computer, Performance Analysis, Iris, Human
Upload Date: 18-Mar-2014
University: Mother Teresa Womens University
Completed Date: 29/08/2013
Abstract: With the increasing demand for profound security in our daily lives, reliable newlinepersonal identification through biometrics is currently an active topic in the literature of newlinepattern recognition. Iris recognition is one of important biometric recognition approach in a newlinehuman identification that is becoming very active topic in research and practical newlineapplication. Once the image of the iris has been captured using a standard camera, the newlineauthentication process, involving the comparison of current subject s iris with the stored newlineversion, is one of the most accurate with very low false acceptance and rejection rates. newlineThe main aim of the thesis is to study about iris recognition system which includes iris newlinelocalization and normalization by using rubber sheet model, feature extraction using Gabor newlineWavelet as well as template matching by Hamming distance. Compression technique is used newlineto compress the eye image and this compressed eye is used for the localization of the inner newlineand outer boundaries of the iris region. We investigated that the effect of compression on iris newlinerecognition system accurately identifies individual s using different distance measures. newlineIn this thesis work, we proved that it is possible to improve the reliability of the newlinesystem by choosing a portion of the iris instead of whole extension of the iris. Initially, newlineportion of the iris pattern is extracted using Gabor Wavelet(GW) and later, different newlinetechniques such as Histogram of Oriented Gradient (HOG) and Local Binary Pattern newline(LBP) are used for feature extraction to identify a person in successful manner with low newlinefalse acceptance rate and with low false rejection rate. newlineFinally, the iris features extracted using GW, HOG and LBP are taken as input and newlinefed to Back Propagation Neural Network for classification. We implemented prominent newlineiris recognition algorithm in MATLAB. newlineThe system is to be composed of a number of sub-systems which correspond to each stage of iris recognition.
Pagination: 124
URI: http://hdl.handle.net/10603/17476
Appears in Departments:Department of Computer Science

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File23.41 kBAdobe PDFView/Open
02_certificate.pdf9.94 kBAdobe PDFView/Open
03_abstract.pdf12.95 kBAdobe PDFView/Open
04_declaration.pdf9.4 kBAdobe PDFView/Open
05_acknowledgement.pdf15.11 kBAdobe PDFView/Open
06_contents.pdf27.3 kBAdobe PDFView/Open
07_list_of_tables.pdf10.04 kBAdobe PDFView/Open
08_list_of_figures.pdf15.03 kBAdobe PDFView/Open
09_chapter 1.pdf7.63 MBAdobe PDFView/Open
10_chapter 2.pdf4.16 MBAdobe PDFView/Open
11_chapter 3.pdf157.01 kBAdobe PDFView/Open
12_chapter 4.pdf309.57 kBAdobe PDFView/Open
13_chapter 5.pdf1.05 MBAdobe PDFView/Open
14_chapter 6.pdf2.48 MBAdobe PDFView/Open
15_conclusion.pdf20.39 kBAdobe PDFView/Open
16_bibliography.pdf100.4 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.