Development of Efficient Algorithms for Cancelable Biometrics

Abstract

Biometrics are defined as either signals or images extracted from humans for the purpose of identification. The most common biometrics is fingerprints, faces, iris, and speech signals. The basic idea of operation of biometric systems is to collect the biometrics from some authorized persons, extract discriminating features from the biometrics as a tool for data reduction and store these features in a database along with the associated person’s identities. This is known as the training phase. In the other phase of biometric systems, which is the testing phase, features are extracted from the incoming biometrics for new persons and the detected persons identities are matched to the identities stored in the database. 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 security breaches. Biometric systems require the generation of databases storing the discriminating features extracted from the biometrics. Unfortunately, if the biometric databases are hacked for any reason, the biometrics saved in these systems would be revealed forever. The basic concept of Cancelable biometrics is to use another version of the original biometric template created through a 1-way transformation of a high-security encryption algorithms, which keeps the original biometrics safe and away from utilization in the system. The new biometrics template can be changed easily in emergency cases without the need to change the system at all. For geometric biometrics as in face recognition, it is possible to use some one-way geometric