الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 108 |  |  |
| | | from | 108 | | |
Abstract
With an increasing emphasis on security, automated personal identification based on biometric features has been receiving extensive attention over the past decade.
Face and iris recognition systems have been chosen as the topic of this research for high security authentication because face recognition is friendly and non-invasive whereas iris recognition is one of the most accurate biometrics. Iris features are unique for each person. it can not duplicate even between identical twins. Iris features forms so early and do not change over a person`s life.
However, both systems may be affected by some conditions which must be compensated to get high accuracy. The fact recognition is a affected by illumination, pose and facial expression. In many applications, face identification systems must be robust to these variations. In the case of Iris recognition, the user must be cooperative. Further, iris images must meet stringent quality criteria, so images of poor quality such as iris with large pupil, or off center images are rejected at the time of acquisition.
Generally, a biometric system can be divided into teo stages. The first one is enrollment, which is responsible for traning the system to identify a given person. During the entrollment stage, a biometric sensor scans the person`s physiognomy to create a digital representation. A feature extractor processess this representation to generate a more compact and expressive representation called a template. The template for each user is stored in a biometric system database; the database can be central or distributed, such as the one in which each user`s template is stored on a smart card and issued to the user. the second one is identification which is responsible for recongnizing the person. During the identification stage, the biometric sensors captures the characteristic of the person to be identified and converts it into the same digital format as the template. The resutling template is fed to the feature matcher, which compares it against the stored template to determine whether the two templates are matched or not and then, it makes decision.
The aim of this work, is to design a MATLAB program for identity verification based on fused face-iris biometrics to overcome a nimber of inherent difficulties which come from using a single biometric.