2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 20 , Issue 1 , PP: 90-113, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Hashem Alyami 1 *
Doi: https://doi.org/10.54216/FPA.200108
The proposed method creates an advanced Deep Residual Convolutional Neural Network (DR-CNN) for finger vein pattern recognition to enhance both accuracy and computational efficiency of the system. The framework implements DR-CNN to handle the reduction of dimensions together with feature extraction while resolving traditional CNN models' overfitting issues. This research utilizes 6,000 images from the VERA and PLUSVein FV3 and MMCBNU_6000 and UTFV databases which form 80% training data and 20% testing data. The ImageNet training includes 4 pooling layers while also using 4 fully connected layers as well as 13 convolutional layers. The DR-CNN classifier achieves optimal authentication-performance through its implementation of Gray Level Co-occurrence Matrices (GLCM) and Scale-Invariant Feature Transform (SIFT) for extracting features. A performance assessment based on accuracy, sensitivity, specificity, F1-score, false acceptance rate (FAR) and false rejection rate (FRR) proves that DR-CNN surpasses traditional techniques. With its implementation of 5,000 images the proposed model demonstrates better accuracy (94.39%) than CNN (92.45%), RNN (88.99%) and DNN (85.91%). Tests show that the system processes 25,000 images within 2.43 milliseconds establishing fast computation speeds. DR-CNN achieves robustness through minimum mean absolute error values of 19.34. The proposed DR-CNN model delivers a 97.8% recognition rate together with a 0.83% error rate which proves its effectiveness for biometric security applications.
Finger vein recognition , DR-CNN , Gray Level Co-occurrence Matrices , Eature extraction , Biometric authentication , Scale-Invariant Feature Transform , CNN and RNN
[1] Y. Zhang, H. Li, and X. Wu, "Finger vein recognition based on convolutional neural network," Proc. IEEE Int. Conf. Image Process. (ICIP), 2017, pp. 2752-2756.
[2] K. Ramu, S. V. S. R. K. Raju, S. Singh, V. Rachapudi, M. A. Mary, V. Roy, and S. Joshi, "Deep Learning-Infused Hybrid Security Model for Energy Optimization and Enhanced Security in Wireless Sensor Networks," SN Comput. Sci., vol. 5, no. 848, 2024.
[3] Y. Liu, J. Wang, and Q. Zhang, "Deep learning-based finger vein recognition and security: A review," IEEE Access, vol. 6, pp. 48792-48804, 2018.
[4] W. Li, S. Xu, M. Zhang, and Y. Peng, "A Multi-view Fusion Method for Finger Vein Recognition," 2023 8th Int. Conf. Intelligent Comput. Signal Process. (ICSP), pp. 1792-1797, 2023.
[5] J. Wang, T. Chen, and L. Sun, "Deep Learning for Finger Vein Recognition: A Brief Survey of Recent Trends," IEEE Trans. Biometric Syst., vol. 8, no. 3, pp. 134-146, 2020.
[6] A. K. Gona and M. Subramoniam, "Multimodal Biometric Reorganization System using Deep Learning Convolutional Neural Network," 2022 Int. Conf. Edge Comput. Appl. (ICECAA), pp. 1282-1286, 2022.
[7] S. Chen, X. Huang, and Z. Lin, "Finger vein recognition based on lightweight convolutional attention model," IET Image Process., vol. 15, no. 8, pp. 1642-1653, 2021.
[8] A. Kumar, S. Jain, and M. Kumar, "Deep Learning based Fusion for a Multi-Biometric Identification Using LSTM," 2024 1st Int. Conf. Advanced Comput. Emerging Technol. (ACET), pp. 1-6, 2024.
[9] M. Rahman, K. Hasan, and S. Hossain, "Finger vein recognition based on bilinear fusion of multiscale features," IEEE Sensors J., vol. 21, no. 12, pp. 14567-14578, 2021.
[10] P. Kumar, A. Baliyan, K. R. Prasad, N. Sreekanth, P. Jawarkar, V. Roy, and E. T. Amoatey, "Machine Learning Enabled Techniques for Protecting Wireless Sensor Networks by Estimating Attack Prevalence and Device Deployment Strategy for 5G Networks," Wireless Commun. Mobile Comput., vol. 2022, Article ID 5713092, 15 pages, 2022.
[11] S. Kumar and R. Gupta, "Finger Vein Recognition Using Deep Learning Technique," IEEE Trans. Inf. Forensics Security, vol. 17, pp. 2348-2356, 2022.
[12] M. H. Safavipour, M. A. Doostari, and H. Sadjedi, "Deep hybrid multimodal biometric recognition system based on features-level deep fusion of five biometric traits," Comput. Intell. Neurosci., vol. 2023, Article ID 6443786, Jul. 2023.
[13] P. Singh, R. Kumar, and V. Sharma, "A simple and efficient method for finger vein recognition," IEEE Access, vol. 6, pp. 19832-19841, 2018.
[14] S. A. Haider et al., "An improved multimodal biometric identification system employing score-level fuzzification of Finger Texture and Finger Vein biometrics," Sensors (Basel), vol. 23, no. 24, Dec. 2023.
[15] W. Zhao, Y. Chen, and L. Xu, "Convolutional neural network-based finger-vein recognition using NIR image sensors," IEEE Sensors J., vol. 19, no. 5, pp. 2345-2353, 2019.
[16] S. Shukla, V. Roy, and A. Prakash, "Wavelet Based Empirical Approach to Mitigate the Effect of Motion Artifacts from EEG Signal," 2020 IEEE 9th Int. Conf. Commun. Syst. Network Technol. (CSNT), Gwalior, India, pp. 323-326.
[17] X. Huang, J. Luo, and Y. Wei, "Finger Vein Recognition Using DenseNet with a Channel Attention Mechanism," IEEE Trans. Ind. Informatics, vol. 17, no. 7, pp. 4568-4576, 2021.
[18] K. Nguyen, C. Fookes, A. Ross, and S. Sridharan, "Iris Recognition with Off-the-Shelf CNN Features: A Deep Learning Perspective," IEEE Access, vol. 6, pp. 18848-18855, 2017.
[19] Y. Li, Z. Wang, and M. Liu, "Finger Vein Recognition Based on ResNet With Self-Attention," IEEE Trans. Neural Networks Learn. Syst., vol. 34, no. 5, pp. 987-999, 2023.
[20] R. R. Dornala, S. Ponnapalli, A. R. Lakshmi, and K. T. Sai, "An Advanced Cloud Security and Load Balancing in Health Care Systems," 2023 Int. Conf. Self-Sustainable Artif. Intell. Syst. (ICSSAS), pp. 1-6, 2023.
[21] X. Xu, Y. Li, and Z. Wang, "Study of a Full-View 3D Finger Vein Verification Technique," IEEE Trans. Biometrics, Behav. Identity Sci., vol. 4, no. 2, pp. 150-162, 2022.
[22] M. Dharmalingam and P. Rakkimuthu, "Delta Ruled Fully Recurrent Deep Learning for Finger-Vein Verification," Jun. 2020.
[23] V. Roy et al., "Reinforcement Learning for Real-time ICU Patient Management in Critical Care," 2023 Int. Conf. System, Computation, Automation Networking (ISSCAN), 2023.
[24] H. Qin, X. He, X. Yao, and H. Li, "Finger-vein verification based on the curvature in Radon space," Expert Syst. Appl., vol. 82, pp. 151-161, 2017.
[25] J. Liu et al., "Finger vein recognition using a shallow convolutional neural network," Proc. CCBR, pp. 195-202, 2021.
[26] T. Sathish Kumar, Pachaivannan Partheeban, and S. Rajes Kannan, "Finger Vein based Human Identification and Recognition using Gabor Filter," IEEE Comput. Sci., vol. 9, no. 2, pp. 5456-5480, 2022.
[27] A. Rad, M. H. Taheri, and S. S. Mousavi, "Deep Neural Network for Robust Finger Vein Recognition," IEEE Trans. Biometrics, Behav. Identity Sci., vol. 2, no. 3, pp. 190-202, 2020.
[28] W.-F. Ou, L.-M. Po, C. Zhou, Y. A. Rehman, P.-F. Xian, and Y.-J. Zhang, "Fusion loss and inter-class data augmentation for deep finger vein feature learning," Expert Syst. Appl., vol. 171, Jun. 2021.
[29] J. Yang, Y. Shi, and G. Jia, "Finger-vein image matching based on adaptive curve transformation," Pattern Recogn., vol. 66, pp. 34-43, Jun. 2017.
[30] C. Kauba, B. Prommegger, and A. Uhl, "Focusing the beam—A new laser illumination-based data set providing insights to finger-vein recognition," Proc. IEEE 9th Int. Conf. Biometrics Theory Appl. Syst. (BTAS), pp. 1-9, Oct. 2018.
[31] R. Chadha, K. Verma, and P. Singh, "Recurrent Neural Network-Based Finger Vein Recognition for Secure Authentication," IEEE Sensors J., vol. 20, no. 5, pp. 4108-4116, 2020.
[32] S. Kulkarni, R. D. Raut, and P. K. Dakhole, "A Novel Authentication System Based on Hidden Biometric Trait," Procedia Comput. Sci., vol. 85, pp. 255-262, 2016.
[33] S. Sun, X. Yue, S. Bai, and P. Torr, "Visual parser: Representing part-whole hierarchies with transformers," arXiv: 2107.05790, 2021.
[34] S. Xie, L. Fang, Z. Wang, Z. Ma, and J. Li, "Review of personal identification based on near infrared vein imaging of finger," Proc. 2017 2nd Int. Conf. Image Vision Comput. (ICIVC), pp. 206-213, 2–4 Jun. 2017.
[35] N. Dung, T. K. Nguyen, and H. Tran, "Finger Vein Recognition Using Convolutional Neural Networks," IEEE Access, vol. 7, pp. 89734-89745, 2019.
[36] Q. Zhang and Y. Yang, "ResT: An efficient transformer for visual recognition," arXiv: 2105.13677, 2021.
[37] G. Ayappan and A. Shankar, "Finger Vein biometric Authentication System," Int. J. Trend Res. Dev., vol. 4, no. 2, pp. 51-53, Apr. 2017.
[38] N. Alay and H. H. Al-Baity, "Deep learning approach for multimodal biometric recognition system based on fusion of Iris face and finger vein traits," Sensors (Basel), vol. 20, no. 19, pp. 5523, Sep. 2020.
[39] L. Xiao, J. Wang, and Z. Luo, "Finger Vein Authentication Using Residual Network with Transfer Learning," IEEE Trans. Image Process, vol. 30, pp. 4501-4513, 2021.
