On the privacy protection of fingerprint templates

• Main Author: Li, Sheng.
• Other Authors: Kot Chichung, Alex
• Format: Theses and Dissertations
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• Online Access: http://hdl.handle.net/10356/52660
• Institution: Nanyang Technological University

Nowadays, biometrics is widely used in authentication systems. In general, biometrics needs to be stored in a database for subsequent authentication. However, templates stored in the database are at the risk of being stolen or modified. Once the template is stolen, it is difficult to be replaced like passwords and the private personal information associated with the stolen template would also be exposed. Thus, biometric templates have to be stored in the database so that both the privacy of the template and the security of the system are not compromised under various attacks. This thesis focuses on the discussion and protection of the privacy of fingerprint templates. As the minutiae is the most common template stored in a fingerprint recognition system, an investigation on how unsafe it is to store the original minutiae template in a database is carried out at first. A novel scheme is proposed to reconstruct a fingerprint image from the minutiae points based on the amplitude and frequency modulated (AM-FM) fingerprint model. The experimental results clearly demonstrate the importance of developing privacy protection techniques for the minutiae templates. Therefore, a novel system is then proposed to protect the privacy of the minutiae templates. This system does not require a token or key for the privacy protection, where a novel algorithm is proposed for generating a combined minutiae template from two different fingerprints during the enrollment. In the authentication, a two-stage fingerprint matching is further proposed for matching two query fingerprints against the combined minutiae template. The combined minutiae template contains only a partial minutiae feature from each of the two different fingerprints. Therefore, the complete minutiae feature of a single fingerprint will not be compromised when the database is stolen. Furthermore, because of the similarity in topology, it is difficult for the attacker to distinguish the combined minutiae template from the original minutiae templates. The experimental results show that the proposed system can achieve a very low error rate with FRR=0.4% at FAR=0.1%. The thinned fingerprint is another type of fingerprint template, which is a binary image keeping all the fingerprint skeletons. In order to protect the privacy of the thinned fingerprint template, an active approach is proposed for the fingerprint authentication system by incorporating a data hiding technique. During the enrollment, some private personal information will be embedded into the thinned fingerprint template imperceptibly. In the authentication, these hidden data can be extracted from the stored template for verifying the authenticity of the person who provides the query fingerprint. In order to reduce the detectability of the data hiding technique, a novel steganographic scheme is proposed for the thinned fingerprint template. The experimental results show that this scheme has more than sufficient capacity for hiding common personal data. Compared with using the existing binary image data hiding techniques, it causes the least abnormality for a thinned fingerprint.