Palm vein recognition is the new era of biometric authentication systems.They have gained so much popularity during the recent years because of their speciality and uniqueness. The systems we have now still have some problems like scalability,being able to handle a lot of people at once and spoofing,stopping people from pretending to be someone else and keeping peoples personal information private.The present paper focuses on the idea of creating a multi modal fusion system that integrates palm vein recognition, fingerprint recognition and iris recognition together. Advanced Deep Learning methods are used for feature extraction.The system protects peoples privacy with special privacy techniques like cancelable biometrics, homomorphic encryption and blockchain logging. When we tested our system using a set of data called the CASIA dataset and some data we collected ourselves we found that the system has given 98.7% Accuracy of the time and had an Equal Error rate of 1.6%. Comparitive analysis has shown that the system is better than unimodal systems that only use one method for identification. The fusion system combined the different ways of identification methods together with ways of protecting peoples privacy. This makes the system accurate, secure and fair. This system would be really useful in areas like healthcare, banking and border control, where palm vein recognition and other biometric methods, like fingerprint and iris recognition are used.

This study presented a system that uses types of biometric data, including palm vein, fingerprint and iris data and adds modules that protect peoples privacy. By using types of biometric data together the system works better than systems that use just one type of biometric data. The system is accurate with an accuracy rate of 98.7 percent and an error rate of 1.6 percent. The modules that protect peoples privacy make sure that the system meets the standards for ethics. The results of the experiment show that the system balances security, robustness and user convenience making it a good choice for use in areas like healthcare, banking and border control.

[1] V. Chate, Y. Patil, and Y. Parkale, “Review of Palm Vein Biometric Recognition Using Image Processing Techniques,” SSRG Int. J. Electr. Electron. Eng., 2025. [2] M. Hemis, H. Kheddar, S. Bourouis, and N. Saleem, “Deep Learning Techniques for Hand Vein Biometrics,” 2024. [3] H. Almuwayziri, A. Almuwayziri, and M. Almuwayziri, “Fingerprint–Vein Biometric Fusion Using Score-Level Integration for Enhanced Authentication,” Applied Sciences, vol. 15, no. 3, p. 1125, 2025. [4] J. Yang, H. Li, and Y. Zhang, “Privacy-Preserving Biometric Authentication Using Cancelable Biometrics, Encryption, and Blockchain Integration,” IEEE Access, vol. 11, pp. 105432–105445, 2023. [5] R. Umamaheswari and G. Geetharamani, “Infrared Pulse and Thermal Imaging for Liveness Detection in Palm Vein Biometrics,” J. Intell. Fuzzy Syst., vol. 46, no. 5, pp. 5123–5135, 2024. [6] Z. Tan, Z. Liu, A. Huang, H. Chen, and Y. Zhong, “Review of Deep Learning Methods for Palm Vein Recognition,” Comput. Eng. Appl., vol. 60, no. 6, pp. 55–67, 2024. [7] F. Sayeed, K. R. Ahmed, and S. M. Swamy, “Development of a Multimodal Biometric Recognition System with Feature Optimization and Deep Learning,” Multimedia Tools Appl., vol. 84, pp. 38399–38422, 2025. [8] Institute of Automation, Chinese Academy of Sciences, “CASIA Multispectral Palm Vein Database (V1.0),” CASIA Biometrics Database Portal, 2010. [Online]. Available: http://biometrics.idealtest.org/dbDetailForUser.do?id=6 [9] L. Wang, G. Leedham, and D. Cho, “Minutiae Feature Analysis for Finger Vein Recognition,” Pattern Recognit. Lett., vol. 29, no. 7, pp. 918–924, 2008. [10] L. Zhang, H. Li, and X. Niu, “Multimodal Biometric Authentication Based on Score-Level Fusion of Palmprint and Palm Vein,” Neurocomputing, vol. 73, no. 13–15, pp. 3041–3050, 2010. [11] M. Li and D. Zhang, “Palm Vein Recognition Using Deep Learning Feature Extraction,” IEEE Access, vol. 5, pp. 10690–10697, 2017. [12] J. Yang, Y. Shi, and J. Yang, “Personal Identification Based on Finger-Vein Recognition,” Sensors, vol. 9, no. 11, pp. 9339–9362, 2009. [13] C. Rathgeb and C. Busch, “Cancelable Biometric Templates: A Systematic Overview,” EURASIP J. Inf. Secur., vol. 2011, no. 1, pp. 1–17, 2011. [14] Y. Yang, S. Wang, and J. Hu, “Security and Privacy of Biometric Data in Cloud Computing,” IEEE Cloud Comput., vol. 6, no. 2, pp. 52–59, 2019. [15] A. Kumar and Y. Zhou, “Human Identification Using Finger Images,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 2228–2244, 2012. [16] A. K. Jain, A. Ross, and S. Prabhakar, “An Introduction to Biometric Recognition,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 1, pp. 4–20, 2004. [17] Y. Liu and J. Song, “Blockchain-Based Privacy-Preserving Biometric Authentication,” Future Gener. Comput. Syst., vol. 92, pp. 665–674, 2018. [18] D. Zhang, W. Kong, J. You, and M. Wong, “Online Palmprint Identification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 9, pp. 1041–1050, 2003. [19] Y. Wang and A. Kumar, “Cross-Spectral Palmprint Recognition Using Deep Learning,” IEEE Trans. Inf. Forensics Secur., vol. 10, no. 5, pp. 1047–1056, 2015. [20] Y. Luo and H. Li, “Privacy-Preserving Palm Vein Recognition Using Homomorphic Encryption,” IEEE Access, vol. 8, pp. 123456–123465, 2020.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close