Auteurs: | » Hammou Djalal Rafik » Mahmoudi Sidi Ahmed » ADJOUDJ Reda » Mechab Boubaker |
Type : | Conférence Internationale |
Nom de la conférence : | 5th International Conference on Cloud Computing and Artificial Intelligence: Technologies and Applications (CloudTech) |
Lieu : | Pays: |
Lien : » | |
Publié le : | 24-11-2020 |
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 …