FVT: Finger Vein Transformer for Authentication

Huang, Junduan; Luo, Weijian; Yang, Weili; Zheng, An; Lian, Feng-Zhao; Kang, Wenxiong

doi:10.1109/tim.2022.3173276

Cited by 29 publications

(20 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In transformer-based methods, our FVCT model surpassed the performance of the FVT model proposed by Huang et al 31 . and the capsule network with transformer (ViT-Cap) proposed by Li et al 32 .…”

Section: Experiments and Resultsmentioning

confidence: 82%

“…Our comparison includes five SOTA methods that have been widely used in the previous studies. Specifically, we selected methods proposed by Hou and Yan, 29 Zhao et al., 30 and Hu et al., 54 which utilize CNN algorithms, as well as methods proposed by Huang et al 31 . and Li et al., 32 which utilize transformer algorithms.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…More recently, transformer-based techniques have demonstrated significant progress in FV identification. Huang et al 31 . proposed the finger vein transformer (FVT) model for authentication, showcasing competitive results.…”

Section: Related Workmentioning

confidence: 99%

“…More recently, transformer-based techniques have demonstrated significant progress in FV identification. Huang et al 31 proposed the finger vein transformer (FVT) model for authentication, showcasing competitive results. Li et al 32 combined the ViT with a capsule network for FV recognition, resulting in effective outcomes.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Hybrid convolutional transformer-based network model for finger vein identification

Boudjellal,

Boukezzoula,

Boudjelal

2023

J. Electron. Imag.

View full text Add to dashboard Cite

.In recent years, finger vein (FV) recognition has garnered significant attention due to its inherent advantages, such as enhanced security, convenience, and the ability to discern living organisms. Notably, use of vision transformers in FV recognition has yielded promising results, primarily owing to their adeptness in capturing extensive spatial relationships within images. Nevertheless, transformers necessitate augmented computational resources and presently fall short compared to established convolutional neural networks (CNNs) concerning performance metrics. We address this predicament and propose the development of an advanced network that surpasses conventional transformers and convolutional networks. By leveraging transformers to capture long-range dependencies and CNNs to extract localized information, we introduce a hybrid architecture named the FV convolutional transformer for FV identification. We validate the efficacy of our approach by conducting extensive experiments on three publicly available FV databases. The experimental results demonstrate that our network achieves state-of-the-art performance, as evidenced by the attainment of the lowest equal error rate across all three datasets

show abstract

Section: Experiments and Resultsmentioning

confidence: 82%

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid convolutional transformer-based network model for finger vein identification

Boudjellal,

Boukezzoula,

Boudjelal

2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Several biometric template protection (BTP) schemes are presented to deal this challenge [6,7]. Even though BTP offers privacy for the finger vein authentication system, they suffer the performance of authentication [8,9]. Authentication depends on the vascular patterns formed by the blood vessels of the human finger in finger nerve biometric systems.…”

Section: Introductionmentioning

confidence: 99%