EUVIMEDEUVIMED entdecken
Crossref

Neural Architecture Search-Based Global–Local Vision Mamba for Palm-Vein Recognition

Huafeng Qin, Yuming Fu, Jing Chen, Mounim A. El-Yacoubi, Xinbo Gao, Feng Xi

IEEE Transactions on Information Forensics and Security · 2026 · 21 · 3766-3780

DOI: 10.1109/tifs.2026.3679936 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Information Forensics and Security, 2026. Verfasst von Huafeng Qin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Chongqing Natural Science Foundation, Chongqing Municipal Education Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Owing to its inherent attributes of high security, privacy preservation, and liveness detection, vein recognition has garnered significant attention, with deep learning (DL) models prevailing in the field. In particular, Mamba, a recent DL architecture showing robust feature representation with linear computational complexity, has been applied successfully for visual tasks. However, Vision Mamba captures long-distance feature dependencies but deteriorates local feature details. Besides, manually designing Mamba architecture based on human prior knowledge is very time-consuming and error-prone. To address these limitations, we propose a hybrid network structure named Global-local Vision Mamba (GLVM) to learn both local correlations and global dependencies within images for comprehensive vein feature representation. Second, we design a Multi-head Mamba to learn the dependencies along different directions, so as to improve the feature representation of Vision Mamba. Third, to learn complementary features, we propose a ConvMamba block consisting of three branches: Multi-head Mamba branch (MHMamba), Feature Iteration Unit branch (FIU), and Convolutional Neural Network (CNN) branch, with FIU aiming to fuse convolutional local features with Mamba global representations. Finally, we propose a Global-local Alternate Neural Architecture Search (GLNAS) method, which alternately searches for the optimal architecture of GLVM through weight entanglement strategy and evolutionary algorithm. We have carried out rigorous experiments on five public vein datasets to assess performance. Our approach achieves the highest 96.84%, 99.63%, 95.73%, 99.72%, 99.14% accuracies and the lowest 0.27%, 0.07%, 0.48%, 0.07%, 0.12% EER among all existing approaches on five public vein datasets, which demonstrates that our approach is capable of learning more complete features than existing approaches. In addition, the visual assessment experiments also show that our approach extracts more global vein architecture and local vein detail for recognition.

Förderung

  • National Natural Science Foundation of China
  • Chongqing Natural Science Foundation
  • Chongqing Municipal Education Commission

Zitieren

APA

Qin, H., Fu, Y., Chen, J., El-Yacoubi, M. A., Gao, X., & Xi, F. (2026). Neural Architecture Search-Based Global–Local Vision Mamba for Palm-Vein Recognition. IEEE Transactions on Information Forensics and Security, 21, 3766-3780. https://doi.org/10.1109/tifs.2026.3679936

Vancouver

Qin H, Fu Y, Chen J, El-Yacoubi MA, Gao X, Xi F. Neural Architecture Search-Based Global–Local Vision Mamba for Palm-Vein Recognition. IEEE Transactions on Information Forensics and Security. 2026;21:3766-3780. doi:10.1109/tifs.2026.3679936

BibTeX
@article{Qin2026,
  author = {Qin, Huafeng and Fu, Yuming and Chen, Jing and El-Yacoubi, Mounim A. and Gao, Xinbo and Xi, Feng},
  title = {Neural Architecture Search-Based Global–Local Vision Mamba for Palm-Vein Recognition},
  journal = {IEEE Transactions on Information Forensics and Security},
  year = {2026},
  volume = {21},
  pages = {3766--3780},
  doi = {10.1109/tifs.2026.3679936}
}
Kostenlos starten →