Cover Image

Access Windows by Iris Recognition

This project aims to design and develop an iris recognition system for accessing Microsoft Windows. The system is built using digital camera and Pentium 4 with SVGA display adapter. MATLAB ver. 7.0 is used to preprocess the taken images convert the images into code and compare the picture code with...

Full description

Saved in:
Bibliographic Details
Main Author: Ali, Musab A. M
Format: Thesis
Language:English
English
Published: 2009
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
QA76.76 Fuzzy System.
Online Access:https://etd.uum.edu.my/1604/1/Musab_A.M._Ali.pdf
https://etd.uum.edu.my/1604/2/1.Musab_A.M._Ali.pdf
https://etd.uum.edu.my/1604/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uum.etd.1604
record_format eprints
spelling my.uum.etd.16042022-04-21T03:28:51Z https://etd.uum.edu.my/1604/ Access Windows by Iris Recognition Ali, Musab A. M TK Electrical engineering. Electronics Nuclear engineering QA76.76 Fuzzy System. This project aims to design and develop an iris recognition system for accessing Microsoft Windows. The system is built using digital camera and Pentium 4 with SVGA display adapter. MATLAB ver. 7.0 is used to preprocess the taken images convert the images into code and compare the picture code with the stored database. The project involves two main steps: (1) applying image processing techniques on the picture of an eye for data acquisition. (2)applying Neural Networks techniques for identification .The image processing techniques display the steps for getting a very clear iris image necessary for extracting data from the acquisition of eye image in standard lighting and focusing. In a use of your images, the images are enhanced and segmented into 100 parts. The standard deviation is computed for every part in which the values are used for identification using NN techniques. Locating the iris is done by following the darkness density of the pupil. For all networks, the weights and output values are stored in a text file to be used later in identification. The Backprobagation network succeeded in identification and getting best results because it attained to (False Acceptance Rate = 10% - False Rejection Rate = 10%), while the Linear Associative Memory network attained to (False Acceptance Rate = 20% - False Rejection Rate = 20%) 2009 Thesis NonPeerReviewed text en https://etd.uum.edu.my/1604/1/Musab_A.M._Ali.pdf text en https://etd.uum.edu.my/1604/2/1.Musab_A.M._Ali.pdf Ali, Musab A. M (2009) Access Windows by Iris Recognition. Masters thesis, Universiti Utara Malaysia.
institution Universiti Utara Malaysia
building UUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Utara Malaysia
content_source UUM Electronic Theses
url_provider http://etd.uum.edu.my/
language English
English
topic TK Electrical engineering. Electronics Nuclear engineering
QA76.76 Fuzzy System.
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
QA76.76 Fuzzy System.
Ali, Musab A. M
Access Windows by Iris Recognition
description This project aims to design and develop an iris recognition system for accessing Microsoft Windows. The system is built using digital camera and Pentium 4 with SVGA display adapter. MATLAB ver. 7.0 is used to preprocess the taken images convert the images into code and compare the picture code with the stored database. The project involves two main steps: (1) applying image processing techniques on the picture of an eye for data acquisition. (2)applying Neural Networks techniques for identification .The image processing techniques display the steps for getting a very clear iris image necessary for extracting data from the acquisition of eye image in standard lighting and focusing. In a use of your images, the images are enhanced and segmented into 100 parts. The standard deviation is computed for every part in which the values are used for identification using NN techniques. Locating the iris is done by following the darkness density of the pupil. For all networks, the weights and output values are stored in a text file to be used later in identification. The Backprobagation network succeeded in identification and getting best results because it attained to (False Acceptance Rate = 10% - False Rejection Rate = 10%), while the Linear Associative Memory network attained to (False Acceptance Rate = 20% - False Rejection Rate = 20%)
format Thesis
author Ali, Musab A. M
author_facet Ali, Musab A. M
author_sort Ali, Musab A. M
title Access Windows by Iris Recognition
title_short Access Windows by Iris Recognition
title_full Access Windows by Iris Recognition
title_fullStr Access Windows by Iris Recognition
title_full_unstemmed Access Windows by Iris Recognition
title_sort access windows by iris recognition
publishDate 2009
url https://etd.uum.edu.my/1604/1/Musab_A.M._Ali.pdf
https://etd.uum.edu.my/1604/2/1.Musab_A.M._Ali.pdf
https://etd.uum.edu.my/1604/
_version_ 1731228096083787776
score 13.211869

Similar Items