DGLFV: Deep Generalized Label Algorithm for Finger-Vein Recognition

Zhiyong Tao,Yalei Hu,Sen Lin,Yueming Han,Ying Liu,Haotong Wang

doi:10.1109/access.2021.3084037

Abstract

With the growing demand for information security, finger-vein recognition has become widespread. However, the robustness of the recognition process becomes a major problem. When identifying unseen categories with traditional finger-vein recognition systems, a few issues remain, such as recognition interference and low efficiency. This paper proposes a Deep Generalized Label Finger-Vein (DGLFV) model to extract feature maps and achieve high-accuracy recognition. The largest rectangular finger-vein region is extracted through image semantic segmentation and the advanced bidirectional traversing and center diffusion method for the known categories. Then we generalize all the unseen categories actively as Class C+1 to reduce interference from unregistered users. Furthermore, an adaptive threshold acquisition algorithm is proposed for Label Receiver Operating Characteristic (LROC), so that the procedures of classification, recognition, and verification are unified. Apart from Shandong University Homologous Multi-modal Traits (SDUMLA-HMT), we have conducted additional experiments on our self-built database, Finger Veins of Signal and Information Processing Laboratory (FV-SIPL). The recognition accuracy of the approach proposed in this paper has reached 99.25% and 99.08% testing on FV-SIPL and SDUMLA-HMT, with a low error rate at 1.481% and 2.228% and little time consumption of 0.157s for a single image, which is better than most state-of-the-art finger-vein recognition methods.

Highlights

Finger-vein recognition belongs to the field of biometrics, similar to some other types, such as faces, fingerprints, irises, and palmprints
CONTRIBUTIONS Focusing on the recognition accuracy and generalization capability, we propose a deep neural network called Deep Generalized Label Finger-Vein (DGLFV)
We propose a recognition method based on a convolutional neural network to identify unseen samples and generalize them into a class

Summary

Introduction

Finger-vein recognition belongs to the field of biometrics, similar to some other types, such as faces, fingerprints, irises, and palmprints. Individuals are usually identified through personal characteristics. With the rapid development of technologies, people pay much more attention to security certification. Deceitful and fabricated systems have emerged one after another, leading to countermeasure systems. They may face a challenging situation when biometric recognition is applied in security prevention and other scenarios. The recognition of finger veins has been a research hotspot in biometrics because of its uniqueness and immutability [1]

Objectives

Methods

Findings

Conclusion