A Model Of A Biometric Recognition System Based On The Hough Transform Of Libor Masek and 1-D Log-Gabor Filter

Biometric iris recognition is a very advanced technology for the data protection and identification of individuals. This technology is widely used by multi-national society in terms of data protection and security. A biometric iris recognition system requires an adapted architecture and specific because it generally recommends 5 steps. The acquisition step consists of getting a good quality iris image by digital cameras of high resolution. The segmentation can use an algorithm and mathematical methods such as John Daugman’s Interro Differential Operator [3] or Richard Paul Wildes’s Hough Transform [4]. The normalization phase projects to transform the relevant information from the circular iris image into the rectangular shape. The feature extraction step requires the use of specific filters (1-D Log-Gabor). The end step is the matching that allows us to compare the descriptor of the user with that of the database to determine if the person is authentic or not and this is done using Hamming Distance. The objective of this article is the use of our approach to improving results. The experiments were tested on the Casia V1 [16], MMU1 [17] iris biometric database, which gave very good and encouraging results. We found an accuracy rate of 99.9263 % for Casia V1 and 99.4168 % for MMU1.