Abstract
Most of the existing finger vein segmentation models require great memory and computational resources, and the global correlation of the models is weak, which may affect the effectiveness of finger vein extraction. In this paper, we propose a global lightweight finger vein segmentation model, TRUnet, and build a lightweight Lightformer module and a plug-and-play module, Global-Lightweight block, in the proposed model respectively. The network not only has global and local correlation to achieve accurate extraction of veins, but also enables the model to maintain its lightweight characteristics. Our approach achieves good results on the public finger vein dataset SDU-FV, MMCBNU_6000.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lei, L., Xi, F., Chen, S., et al.: Iterated graph cut method for automatic and accurate segmentation of finger-vein images. Appl. Intell. 51(2), 673–689 (2021)
Li, X., Lin, J., Pang, Y., et al.: Fingertip blood collection point localization research based on infrared finger vein image segmentation. IEEE Trans. Instrum. Meas. 71, 1–12 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Qin, C., Lin, X., Chen, Y., Zeng, J. (2022). A Lightweight Segmentation Network Based on Extraction. In: Deng, W., et al. Biometric Recognition. CCBR 2022. Lecture Notes in Computer Science, vol 13628. Springer, Cham. https://doi.org/10.1007/978-3-031-20233-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-20233-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20232-2
Online ISBN: 978-3-031-20233-9
eBook Packages: Computer ScienceComputer Science (R0)