PALM VEIN RECOGNITION USING RASPBERRY PI: A VASCULAR BIOMETRICS APPROACH
Article Sidebar
Read Counter : 38
Download : 12
Main Article Content
Abstract
Vein-based biometrics is an identification technology that uses unique vein patterns to enhance security, offering higher safety than other biometric methods like fingerprints and facial recognition. The main challenge in vein recognition lies in capturing clear images and efficiently processing data. This study develops a biometric system prototype using the Raspberry Pi NoIR Camera and Raspberry Pi 5 for biometric data capture and processing. The Raspberry Pi NoIR Camera captures vein patterns in the infrared spectrum, which is effective for revealing vein patterns not visible under normal light. The Raspberry Pi 5 functions as a processor running image processing algorithms and Convolutional Neural Networks (CNN) for feature extraction and palm vein pattern recognition. The image enhancement methods applied include histogram equalization and Contrast Limited Adaptive Histogram Equalization (CLAHE). The results show that CLAHE provides optimal contrast enhancement, achieving a classification accuracy of 90.00%. The precision, recall, and F1-score values for CLAHE are 0.93, 0.90, and 0.90, respectively, outperforming histogram equalization and no enhancement. Thus, CLAHE proves to be an effective method for improving vein image quality and the accuracy of the biometric system. The use of Raspberry Pi makes the system portable, power-efficient, and cost-effective for security applications. Overall, CLAHE delivers the best performance in enhancing vein-based biometric identification
Abstrak
Biometrik berbasis pembuluh darah adalah teknologi identifikasi yang menggunakan pola pembuluh darah unik untuk meningkatkan keamanan, dibandingkan dengan biometrik lainnya seperti sidik jari dan pengenalan wajah. Kendala utama pada pengenalan pembuluh darah adalah pengambilan citra yang jelas dan pengolahan data yang efisien. Penelitian ini mengembangkan prototipe sistem biometrik menggunakan Raspberry Pi NoIR Camera dan Raspberry Pi 5 untuk pengambilan dan pemrosesan data biometrik. Raspberry Pi NoIR Camera menangkap pola pembuluh darah dalam spektrum inframerah, yang efektif untuk mengungkapkan pola pembuluh darah yang tidak terlihat dengan cahaya tampak. Raspberry Pi 5 berfungsi untuk menjalankan algoritma pengolahan citra dan Convolutional Neural Network (CNN) untuk ekstraksi fitur dan pengenalan pola pembuluh darah telapak tangan. Metode peningkatan citra yang diterapkan adalah ekualisasi histogram dan Contrast Limited Adaptive Histogram Equalization (CLAHE). Hasil penelitian menunjukkan CLAHE memberikan peningkatan kontras yang optimal, menghasilkan akurasi klasifikasi sebesar 90,00%. Nilai precision, recall, dan F1-score untuk CLAHE adalah 0,93, 0,90, dan 0,90, yang lebih tinggi dibandingkan dengan ekualisasi histogram dan tanpa peningkatan citra. Dengan demikian, CLAHE terbukti efektif dalam meningkatkan kualitas citra pembuluh darah dan akurasi sistem biometrik. Penggunaan Raspberry Pi menjadikan sistem ini portabel, hemat daya, dan terjangkau untuk aplikasi keamanan. Secara keseluruhan, CLAHE memberikan performa terbaik dalam meningkatkan identifikasi biometrik berbasis pembuluh darah.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
This work is licensed under a TESLA: Jurnal Teknik Elektro Creative Commons Attribution-ShareAlike 4.0 International License. 
Meirista Wulandari, ST., M.Eng, (Scopus ID: 56596692000) Universitas Tarumanagara
References
C. A. Shoniregun and S. Crosier, Securing Biometrics Applications. 2008.
W. Song, T. Kim, H. C. Kim, J. H. Choi, H.-J. Kong, and S.-R. Lee, “A finger-vein verification system using mean curvature,” Pattern Recognit. Lett., vol. 32, no. 11, pp. 1541–1547, 2011.
H. Qin and M. A. El-Yacoubi, “Deep representation-based feature extraction and recovering for finger-vein verification,” IEEE Trans. Inf. Forensics Secur., vol. 12, no. 8, pp. 1816–1829, 2017.
N. Ibrahim et al., “Visualization of Hand Vein Using Raspberry Pi Images in Contactless Vein Detector,” in Proceedings of the 12th National Technical Seminar on Unmanned System Technology 2020: NUSYS’20, 2022, pp. 273–281.
A. B. Abd Rahman, F. Juhim, F. P. Chee, A. Bade, and F. Kadir, “Near Infrared Illumination Optimization for Vein Detection: Hardware and Software Approaches,” Applied Sciences, vol. 12, no. 21. 2022.
G. Halfacree, The official Raspberry Pi Beginner’s Guide: How to use your new computer. Raspberry Pi Press, 2023.
M. Ghute, M. Korde, K. Kamble, S. Khade, and Y. Chavan, “Design of palm vein authentication system,” Biosci. Biotechnol. Res. Commun., vol. 13, no. 14, pp. 273–276, 2020.
A. S. El Sayed, H. M. Ebeid, M. Roushdy, and Z. T. Fayed, “A method for contactless palm ROI extraction,” in 2016 11th International Conference on Computer Engineering & Systems (ICCES), 2016, pp. 193–200.
M. Nixon and A. Aguado, Feature Extraction and Image Processing, Second. London: Academic Press Elsevier, 2008.
M. Wulandari, Basari, and D. Gunawan, “On the Performance of Pretrained CNN Aimed at Palm Vein Recognition Application,” in 2019 11th International Conference on Information Technology and Electrical Engineering, ICITEE 2019, 2019.
K. Zuiderveld, Contrast Limited Adaptive Histograph Equalizatoin. San Diego: Academic Press Professional, 1994.
V. Sze, Y. Chen, T. Yang, and J. S. Emer, “Efficient Processing of Deep Neural Networks: A Tutorial and Survey,” Proc. IEEE, vol. 105, no. 12, pp. 2295–2329, 2017.
S. R. Kodituwakku, “Biometric Authentication: A Review,” Int. J. Trend Res. Dev., vol. 2, no. 4, pp. 113–123, 2015.
A. K. Jain, S. Pankanti, S. Prabhakar, L. Hong, and A. Ross, “Biometrics: a grand challenge,” in Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 2004, vol. 2, pp. 935-942 Vol.2.
S. Marcel, “BEAT – biometrics evaluation and testing,” Biometric Technol. Today, vol. 2013, no. 1, pp. 5–7, 2013.