Open Access

ARTICLE

EFI-SATL: An EfficientNet and Self-Attention Based Biometric Recognition for Finger-Vein Using Deep Transfer Learning

Manjit Singh, Sunil Kumar Singla^*

Department of Electrical and Instrumentation Engineering, Thapar Institute of Engineering and Technology, Patiala, 147004, India

* Corresponding Author: Sunil Kumar Singla. Email:

(This article belongs to the Special Issue: Artificial Intelligence Emerging Trends and Sustainable Applications in Image Processing and Computer Vision)

Computer Modeling in Engineering & Sciences 2025, 142(3), 3003-3029. https://doi.org/10.32604/cmes.2025.060863

Received 12 November 2024; Accepted 06 February 2025; Issue published 03 March 2025

Abstract

Deep Learning-based systems for Finger vein recognition have gained rising attention in recent years due to improved efficiency and enhanced security. The performance of existing CNN-based methods is limited by the puny generalization of learned features and deficiency of the finger vein image training data. Considering the concerns of existing methods, in this work, a simplified deep transfer learning-based framework for finger-vein recognition is developed using an EfficientNet model of deep learning with a self-attention mechanism. Data augmentation using various geometrical methods is employed to address the problem of training data shortage required for a deep learning model. The proposed model is tested using K-fold cross-validation on three publicly available datasets: HKPU, FVUSM, and SDUMLA. Also, the developed network is compared with other modern deep nets to check its effectiveness. In addition, a comparison of the proposed method with other existing Finger vein recognition (FVR) methods is also done. The experimental results exhibited superior recognition accuracy of the proposed method compared to other existing methods. In addition, the developed method proves to be more effective and less sophisticated at extracting robust features. The proposed EffAttenNet achieves an accuracy of 98.14% on HKPU, 99.03% on FVUSM, and 99.50% on SDUMLA databases.

---

Graphic Abstract

---

Keywords

---