Finger Vein Recognition Using DenseNet with a Channel Attention Mechanism and Hybrid Pooling
Electronics · 25.01.2024 · 13 (3) · 501
DOI: 10.3390/electronics13030501 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 25.01.2024. Verfasst von Nikesh Devkota und 1 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF), Industry-Academic Cooperation Based Platform R&D.
Abstract (Originalsprache)
This paper proposes SE-DenseNet-HP, a novel finger vein recognition model that integrates DenseNet with a squeeze-and-excitation (SE)-based channel attention mechanism and a hybrid pooling (HP) mechanism. To distinctively separate the finger vein patterns from their background, original finger vein images are preprocessed using region-of-interest (ROI) extraction, contrast enhancement, median filtering, adaptive thresholding, and morphological operations. The preprocessed images are then fed to SE-DenseNet-HP for robust feature extraction and recognition. The DenseNet-based backbone improves information flow by enhancing feature propagation and encouraging feature reuse through feature map concatenation. The SE module utilizes a channel attention mechanism to emphasize the important features related to finger vein patterns while suppressing less important ones. HP architecture used in the transitional blocks of SE-DenseNet-HP concatenates the average pooling method with a max pooling strategy to preserve both the most discriminative and contextual information. SE-DenseNet-HP achieved recognition accuracy of 99.35% and 93.28% on the good-quality FVUSM and HKPU datasets, respectively, surpassing the performance of existing methodologies. Additionally, it demonstrated better generalization performance on the FVUSM, HKPU, UTFVP, and MMCBNU_6000 datasets, achieving remarkably low equal error rates (EERs) of 0.03%, 1.81%, 0.43%, and 1.80%, respectively.
Förderung
- National Research Foundation of Korea (NRF)
- Industry-Academic Cooperation Based Platform R&D
Zitieren
APA
Devkota, N., & Kim, B. W. (2024). Finger Vein Recognition Using DenseNet with a Channel Attention Mechanism and Hybrid Pooling. Electronics, 13(3), 501. https://doi.org/10.3390/electronics13030501
Vancouver
Devkota N, Kim BW. Finger Vein Recognition Using DenseNet with a Channel Attention Mechanism and Hybrid Pooling. Electronics. 2024;13(3):501. doi:10.3390/electronics13030501
BibTeX
@article{Devkota2024,
author = {Devkota, Nikesh and Kim, Byung Wook},
title = {Finger Vein Recognition Using DenseNet with a Channel Attention Mechanism and Hybrid Pooling},
journal = {Electronics},
year = {2024},
volume = {13},
number = {3},
pages = {501},
doi = {10.3390/electronics13030501}
}
EUVIMED