Evaluation and implement of fuzzy vault scheme using indexed minutiae

Juels et. al proposed a fuzzy vault scheme that extracts secret from inexact biometric information. However, typical feature extracted from fingerprint, called minutiae, is assumed to tolerate against re-ordering minutiae. In order to address the issue, we propose a new scheme of fuzzy vault for fingerprint that assigns identification number to all minutiae and chaff (fake minutia) and determines correct order in greedy short distance algorithm. We evaluate the accuracy and the performance of the proposed scheme in comparison to some of existing schemes.