Abstrait

Combined Fingerprint Minutiae Template Generation

Guruprakash.V, Arthur Vasanth.J

We propose here a novel system for protecting fingerprint privacy by combining two different fingerprints into a new identity. Two fingerprints are captured from two different fingers in the enrollment phase. From one fingerprint we extract the minutiae positions. We extract the orientation from other fingerprint. With the extracted information, a combined minutiae template is created and stored in a database. The system requires two query fingerprints, for authentication, from the same two fingers which are used in the enrollment. Any existing fingerprint matching process is proposed for matching the two query fingerprints against a combined minutiae template. Since the combined minutiae template is used in our method, the features of a single fingerprint cannot be easily retrieved even when the database is hacked. Since the created template is not visually realistic, it is difficult for the attacker to separate the two fingerprints. Thus, a new virtual identity is created for the two different fingerprints, which can be matched using minutiae-based fingerprint matching algorithms. Compared with the existing technique, the proposed method has advantage in creating a better new virtual identity when the two different fingerprints are randomly chosen.