الفهرس Only 14 pages are availabe for public view
 |  | from | 151 |  |  |
| | | from | 151 | | |
Abstract
Security will always remain an issue of a great importance either in business or in al life. Biometric.based security systems offer several advantages over traditional tication systems, and it is gaining higher interest each day from researchers or market. is considered more reliable for security systems as the biometric system takes its ’on based on the question (who are you?) rather than (what do you have?). Biometric have now been deployed in various commercial, civilian, and forensic applications as of establishing identity.
Biometrics is described as the science of recognizing an individual based on his/her or behavioral traits. The human iris is a physiological biometric characteristic. It is ed to be one of the best biometrics. It has unique features and is complex enough to be as a biometric signature. Human iris never changes during a person’s lifetime. No two can be identical in two different persons even in identical twins. It also can not be
’cally modified without unacceptable risk to vision.
The aim of the thesis is to study and compare some different algorithms of iris ization/segmentation in iris images as well as feature extraction and recognition of rent persons based on their iris images. Studying and analyzing the performance of rent algorithms will enable us to enhance recognition rates of iris recognition systems to and its use in security systems, leading to its development and performance enhancement.
In this thesis 2D-DWT and 2D-DCT were used for feature extraction. Different inations of DWT detail coefficients were used and a new method for applying DCT on selected iris template is used as well. DCT showed the best results in recognition rates mpared to the other 4 methods even with the increase of the number of classes (subjects in identification.