A Score-Level Fusion of Fingerprint Matching With Fingerprint Liveness Detection

Yongliang Zhang,Shengyi Pan,Zhiwei Li,Chenhao Gao,Haoze Qiu,Yuanyang Xu

doi:10.1109/access.2020.3027846

Yongliang Zhang, Shengyi Pan + Show 4 more

Open Access

https://doi.org/10.1109/access.2020.3027846

Copy DOI

Abstract

Fingerprint-based recognition is widely deployed in different domains. However, the traditional fingerprint recognition systems are vulnerable to presentation attack, which utilizes an artificial replica of the fingerprint to deceive the sensors. In such scenarios, Fingerprint Liveness Detection (FLD) is required to ensure the actual presence of a live fingerprint. In this paper, a fingerprint matching method fused with liveness detection is proposed. Firstly, the similarity between two fingerprint images is calculated based on Octantal Neatest-Neighborhood Structure (ONNS), where the closest minutia to the central minutia is found from each sector of octant. Secondly, the FLD score of the fingerprint image is obtained by using the modified Residual Network (Slim-ResCNN). Finally, a score-level fusion is performed on the results of fingerprint matching and FLD by generating interaction features and polynomial features as the score feature vector. To classify whether a fingerprint image is a genuine live fingerprint or a spoof attack (including impostor live and fake fingerprints), the score feature vector is processed using logistic regression (LR) classifiers. The proposed method won the first place in the Fingerprint Liveness Detection Competition 2019 with an overall accuracy of 96.88%, which indicates it can effectively protect the fingerprint recognition systems from spoof attacks.

Highlights

Compared with the traditional identity authentication, such as key, card, and password, biometrics are neither easy to steal nor easy to lose
Previous researches have shown that fingerprint sensor can be deceived by fake fingerprints [3], which encourages researchers to aware the harmful of fake fingerprint attacks and devote to developing solutions for these spoof attacks
In non-cooperation methods, the fingerprint mold is indirectly formed by extracting the latent fingerprint, which is hard to fabricate for non-professional people

Summary

INTRODUCTION

Compared with the traditional identity authentication, such as key, card, and password, biometrics are neither easy to steal nor easy to lose. The security of fingerprint recognition systems has become especially important and gradually raised public’s attention, because some studies have shown that fingerprint recognition systems have multiple security threats, such as using fake fingerprints to attack fingerprint sensors, communication modules, software modules, and data storage [2]. Y. Zhang et al.: Score-Level Fusion of Fingerprint Matching With FLD recognition system with a capacitive sensor, only the fake fingerprint with conductive materials can be used to attack successfully. The hardware-based methods need some professional devices to measure the inherent properties of real fingerprint, which increases the overall expenses of fingerprint recognition systems. The software-based methods only detect spoof behaviors by analyze the fingerprint image captured by fingerprint sensor. The fusion scheme effectively prevents spoof attacks on the surface of fingerprint sensor by integrating software- based FLD into fingerprint recognition system, avoiding expensive expenses by integrating additional hardware devices.

RELATED WORKS

SCORES FUSION

Findings

CONCLUSION