Using k-nearest neighbors to construct cancelable minutiae templates

TL;DR

This paper introduces a novel cancelable fingerprint template scheme that combines real minutiae with synthetic data using k-nearest neighbors, enhancing privacy while maintaining verification accuracy.

Contribution

The method uniquely integrates real and synthetic templates with k-NN to create cancelable biometric templates, improving security and privacy protection.

Findings

Templates meet cancelable biometrics requirements

High verification accuracy maintained

Effective across multiple databases

Abstract

Fingerprint is widely used in a variety of applications. Security measures have to be taken to protect the privacy of fingerprint data. Cancelable biometrics is proposed as an effective mechanism of using and protecting biometrics. In this paper we propose a new method of constructing cancelable fingerprint template by combining real template with synthetic template. Specifically, each user is given one synthetic minutia template generated with random number generator. Every minutia point from the real template is individually thrown into the synthetic template, from which its k-nearest neighbors are found. The verification template is constructed by combining an arbitrary set of the k-nearest neighbors. To prove the validity of the scheme, testing is carried out on three databases. The results show that the constructed templates satisfy the requirements of cancelable biometrics.