3-Dimensional Secured Fingerprint Shell

• Published in: Pattern recognition letters Vol. 126; pp. 68 - 77
• Main Authors: Ali, Syed Sadaf, Prakash, Surya
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.09.2019; Elsevier Science Ltd
• Subjects: Biometric security; Biometrics; Diversity; Fingerprint; Fingerprint verification; Fingerprinting; Invariants; Minutiae; Revocability; Template security; Viability; Minutiae; Template security; Fingerprint; Biometric security; Revocability; Diversity
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2018.04.017

•An analysis of the shortcomings of Fingerprint Shell (an existing technique) are displayed.•Proposed technique is highly secured and robust for fingerprint recognition.•Rotation and translation invariant features are utilized for template generation .•Excellent performance is obtained on various databases (including IIT Kanpur large database).•Encouraging results have been obtained under different scenarios and attacks. [Display omitted] Biometric systems relying on fingerprint usually use minutiae points information and store it directly in the database. However, databases are prone to get attacked by an adversary. As fingerprint can be generated using the information of its minutiae points, it is essential to ensure the security of the fingerprint data in biometric systems. Another problem associated with fingerprint authentication systems is the variation among fingerprint images of the same subject, which occurs due to rotation and translation of finger at the time of capturing fingerprints through sensors. A technique called Fingerprint Shell is proposed by Moujahdi et al. as a secured representation of fingerprint template. However, this technique uses only one intra-subject invariant feature, which is the distances between minutiae points and singular point to generate a 2-dimensional spiral curve which is used as a secured user template. In this paper, we analyze the weaknesses of the Fingerprint Shell and propose a highly secured fingerprint template protection technique in which a 3-dimensional spiral curve is generated as a secured user template for a fingerprint. To obtain the proposed secured fingerprint template, we utilize three intra-subject invariant features, namely distances between minutiae points and singular point, the orientation information of minutiae points and the ridge counts between minutiae points and singular point. Outcomes of the experimental analysis conducted on FVC (2000, 2002 and 2004) and IIT Kanpur databases show highly encouraging performance and exhibit the viability of the proposed technique. The technique has also been analyzed with respect to various attacks and is found to be highly secure and robust.