Mixing Fingerprint Features for Template Security

Most of the authentication systems today don’t just use traditional systems like password or PIN but also rely on biometrics for a better security. Securing the biometric template is thus becoming a major concern in biometrics based systems. Although it is possible to use different biometric traits in combination (multimodal biometrics) to enhance security, it is computationally expensive and time consuming. This paper explores the possibility of combining features from the same biometric trait (fingerprints) i.e keeping it unimodal but still offering the same security as that of the combined biometrics. The algorithm consists of extracting minutiae and orientation features from two different fingerprints and producing a mixed template using these extracted features. The template produced is tested using correlation based matching technique and the correlation co-efficient is calculated. The advantage of creating the mixed template is that it is cancellable and serves as a new virtual identity. Keywords—minutiae,orientation, normalizaiton,spurious minutiae, cross numbering, mixing template,tempalte security,correlation-based matching.