Thesis (Ph.D.) - Cairo University - Institute of Statistical Studies and Research - Department of Computer and Information Science

Privacy and Security has become an increasingly serious problem for any biometric systems. Template protection, which mainly prevents from data loss and hacking the stored templates, is one of the most important issues when considering privacy and security. Cancelable biometrics approach Scheme has been proposed to address this problem. On the other hand, the symmetric hash functions might be used to increase the biometric security level by making it is hard to attack the template. In this thesis, we firstly apply a unimodal approach using bio-hash function as a cryptosystem based approach, then a new hybrid approach combining approaches based on transformation and cryptosystem on fingerprints is applied. The results are compared and showed that the new approach is more efficient as the security of biometric template is increased meanwhile the error rate is minimized.

Issued also as CD