Coprime Mapping Transformation for Protected and Revocable Fingerprint Template Generation

Abstract

Compromise of biometric data may cause permanent loss of identity since the biometric information is intrinsically linked with the user. To revoke the stolen biometric template, the concept of cancelable biometrics has been introduced. The idea behind cancelable biometric is to transform the original biometric template into a new template and perform matching in the transformed domain. In this paper, a coprime transformation scheme has been proposed to generate the cancelable fingerprint template. The method divides the fingerprint region into a number of sectors with respect to each minutiae point and identifies the nearest-neighbor minutiae in each sector. Then, ridge-based features for all minutiae points are computed and mapped onto co-prime positions of a random matrix to generate the cancelable template. The proposed approach achieves an EER of 1.82, 1.39, 4.02 and 5.77 on DB1, DB2, DB3 and DB4 datasets of the FVC2002 database, respectively. Experimental results indicate that the method outperforms in comparison to the current state-of-the-art. Moreover, the proposed method fulfills the necessary requirements of diversity, revocability, and non-invertibility with a minor performance degradation caused by the transformation.