الفهرس | Only 14 pages are availabe for public view |
Abstract Most modern security systems depend on encryption and password techniques in data transfer and on biometrics to secure the access to different systems. These traditional systems have suffered for a long time from hacking trials. Hence, the researchers have concentrated on biometric systems to avoid these limitations. These biometric systems require the generation of databases comprising the discriminating features extracted from the biometrics. Unfortunately if the biometric databases have been hacked and stolen, the biometrics saved in this system will be stolen forever. Thus, there is a bad to develop new cancellable biometric systems. The basic concept of cancellable biometrics is to use another version of the original biometric template created through a 1-way transform of a high-security encryption algorithms, which keeps the original biometrics safe and away from utilization in the system. Recognition of the generated cancellable biometrics is performed through feature from them and hence performing the matching with the saved database. The main advantage of this trend is that the original biometrics are kept safe and away from any hacking attempts and from being stolen. If the database is kecked or stolen, the oneway transform or the encryption technique may be changed. The main research challenges in the development of cancellable biometrics systems are the design of efficient one-way transforms, the design of efficient encryption algorithms for biometrics, the set-up of an intelligent system for cancellable biometric systems adopting new learning methodologies such as deep learning. This thesis deals with the issue of cancellable biometrics and presents two efficient algorithms for this purpose. |