Robust biometric authentication system with a secure user template

• Published in: Image and vision computing Vol. 104; p. 104004
• Main Authors: Ali, Syed Sadaf, Baghel, Vivek Singh, Ganapathi, Iyyakutti Iyappan, Prakash, Surya
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-12-2020
• Subjects: Authentication; Biometric; Fingerprint; Pattern recognition; Security; Biometric; Fingerprint; Pattern recognition; Security; Authentication
• ISSN: 0262-8856; 1872-8138
• DOI: 10.1016/j.imavis.2020.104004

Biometric feature based human authentication systems provide various advantages over the classical authentication systems. Out of numerous biometric features in a human body, the fingerprint is the most commonly used biometric feature for the authentication of a person. Typically, the fingerprint-based systems rely on minutiae points information and use it directly as a user template. Several studies have shown that the use of minutiae points directly as a user template is unreliable as it may lead to the reconstruction of the original fingerprint. As databases are vulnerable to attacks, it is important to secure fingerprint information. In this paper, we propose a technique in which a strong 3-dimensional template is created from the fingerprint of a user. From the minutiae points of the fingerprint, minutiae triplets are computed, through which a secured user template is generated. The user template developed using the proposed technique is found to be robust and shows good revocability, diversity, security, and performance. The experimental results obtained on various fingerprint databases are extremely encouraging and demonstrate the effectiveness of the proposed technique.
•The proposed technique generated a strong 3D template from the fingerprint of a user.•Minutiae triplets are formed through which the original minutiae points are secured.•The proposed technique exhibits good revocability as well as diversity.•The proposed technique can efficiently handle various types of attacks.•The proposed technique is secure and has shown good recognition performance as well.