الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 167 |  |  |
| | | from | 167 | | |
Abstract
The main aim of biometry is verifying the claimed identity of an individual based on a single or multiple biometric characteristics, such as fingerprint, face, iris, signature, etc. Each biometric has its strengths and weaknesses, and the choice depends on the application.No single biometric is expected to effectively meet the requirements of all the applications. In other words, no biometric is “optimal”. The match between a specific biometric and an application is determined depending upon the operational mode of the application and the properties of the biometric characteristic. The objective of this thesis is to enhance the performance of the iris recognition system is initially introduced by Daugman and then modified by Masek and Kovesi. The proposed enhancement is two-fold, one to improve system performance and the other to reduce the storage requirements. This thesis presents a new scheme based on template fusion of several iris images of the same eye. The base feature templates formed for each image scan of a given eye are fused to generate one final template. In the fusion process, we weight each bit according to its reliability at enrollment time. The result is a simple and efficient scheme that works with any iris template generation method. This will not only reduce the storage capacity requirements but also enhance the system’s speed during the matching process. The performance of both the proposed algorithm and the overall system will be assessed. This thesis compares the storage requirements of both the proposed iris recognition system and the conventional iris recognition system and showed a reduction of about 60% of the storage requirements. The results from comparing 450 iris images to the 90 fused general templates showed that the proposed technique identifies the presented sample with an accuracy of 99.7%. Finally, the performance of the propsed method is compared to that of the conventional methods. Results showed the performance of the proposed method suppresses that of the conventional one. Subject