الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 141 |  |  |
| | | from | 141 | | |
Abstract
A new approach for human identification through neural networks based on iris recognition as the biometric property is presented in this thesis. The proposed algorithm consists of three major components, image preprocessing based on hough transform to localize iris and remove unwanted regions, then the iris image is transformed to have fixed dimensions to ollow comparison, A ID Log-Gabor wavelet has been used to capture both local and global iris characteristics to form a fixed length feature vector, and finally iris matching is implemented using back-propagation neural networks. Experimental results showed that the proposed algorithm has an encouraging performance with acceptable results compared to current similar systems. The proposed technique has proved to give superior recognition result.
The human iris has an extraordinary structure and provides abundant texture information. The spatial patterns that are apparent in the iris are unique to each individual. Individual differences that exist in the development of anatomical structures in the body result in the uniqueness. In particular, the biomedical literature suggests that iris is as distinct as patterns of retinal blood vessels, but an iris image can be more easily obtained than a retina image. Compared with other biometrics, iris is more stable and reliable for identification. Since the iris is an overt body, iris recognition systems can be non-invasive to their users, which is a very important factor for paactical applications.