الفهرس 
chapter 1Only 14 pages are availabe for public view
 |  | from | 242 |  |  |
| | | from | 242 | | |
Abstract
Biometrics is constantly evolving technology which has been widely used in many official and commercial identification applications. The increased concerns in security during recent years have essentially resulted in more attention being given to biometric-based authentication techniques. A biometric-based authentication is basically a pattern recognition problem which makes personal identification based on specific physiological
or behavioral features.
Human iris is one of the most reliable biometric because of its uniqueness, stability and noninvasive nature. Thus it has attracted the attention of biometrics based identification and verification research and development community. Iris recognition has been a fast growing, challenging and interesting area in real-time applications. A large number of iris recognition algorithms have been developed for decades.
This thesis introduces three different algorithms for iris feature extraction, Columns Means, Combined Rows & Columns Means methods and Dual iris recognition based on Columns Means Method. It also presents a comparative study of the performance from the iris authentication using Discrete Cosine Transform (DCT), Haar wavelet transform and the proposed methods.
Here iris recognition is done using the image feature set extracted from DCT, Haar Wavelet transform, Columns Means, Combined Rows & Columns Means Methods and Dual iris Recognition system. Analysis was performed with the mentioned methods, consisting of the False Acceptance Rate (FAR) and the Genuine Acceptance Rate (GAR).
The proposed techniques are tested on an iris image database having 384 images. The iris recognition systems that produced accurate recognition were successfully designed.
Combined Rows & Columns Means and Dual iris recognition based on Columns Means Methods give better performance with the accuracy of 100%, DCT and Columns Means Methods give performance with the accuracy of 98.44% -and Haar Wavelet Transform gives a performance with the accuracy of 97.66%. The proposed Combined Rows & Columns Means Method is superior in having faster and more accurate recognition rate.