Minutiae Points Extraction Using Faster R-CNN

Abstract

A fingerprint is an impression of the friction ridges of all parts of the finger and it is a widely used biometric trait. In a fingerprint authentication system, minutiae points are used as features to authenticate an individual. There are many traditional techniques which have been proposed to extract minutiae points from a fingerprint. However, efficiently locating minutiae points in a fingerprint image is still a challenging problem. In this paper, we propose a technique to locate and classify the minutiae points based on Faster R-CNN, which is a combination of region proposal network (RPN) and detection network. We use IIT Kanpur fingerprint database to evaluate the proposed technique and to show the performance. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.