A CANCELLABLE AND IRREVOCABLE APPROACH FOR FINGERPRINT TEMPLATE PROTECTION USING OPTIMAL ITERATIVE SOLUBILITY ALGORITHM AND SECURE POINT BASE

Abstract

Biometric authentication scheme is a robust, reliable, and convenient way for person authentication with security. It is necessary to protect biometric information for maintaining secrecy. In this paper, fingerprint template protection is carried out using the optimal iterative solubility (OIS) algorithm. The purpose of developing the OIS algorithm is to generate the matrix coefficient of the template protection matrix. The processing steps for fingerprint template protection involve two phases such as enrolment and authentication. In the enrolment phase, the identity vector of the input fingerprint image is generated with the assistance of minutiae points, secure point base (SPB) and OIS algorithm, and then, the database is created. In the authentication phase, the query image is considered as an input, and the identity vector is generated based on the query image in the same manner as enrolment phase. Moreover, the cross indexing-based matching is done using Tanimoto coefficient to make final decisions in order to check whether the user authorization is accepted or rejected. The experimental result demonstrates that the developed OIS algorithm attained a maximum accuracy of 0.96, minimum false acceptance rate (FAR) of 0.077, minimum false rejection rate (FRR) of 0.070, and maximum genuine acceptance rate (GAR) of 0.964, correspondingly.