Shalini M. K.; Santhosh Kumar K. S.; Hemantha Kumar G.

Advances in Multimodal Biometric Authentication: A Classifier Fusion and Deep Learning Perspective

PDF (1118KB), PP.24-44

Views: 0 Downloads: 0

Author(s)

Shalini M. K. ¹ Santhosh Kumar K. S. ^2,* Hemantha Kumar G. ³

1. Department of Computer Science, Sheshadripuram College, Bangalore, 560020, India

2. Department of Artificial Intelligence and Machine Learning, Mysore University School of Engineering, Mysuru, 570006, India

3. Department of Studies in Computer Science, University of Mysore, Mysuru, 570006, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2026.03.02

Received: 9 Feb. 2026 / Revised: 13 Mar. 2026 / Accepted: 25 Apr. 2026 / Published: 8 Jun. 2026

Index Terms

Deep Learning, Multimodal Biometric Authentication, Face Recognition, Fingerprint Recognition, Anti- Spoofing, Biometric Security

Abstract

The rapid advancements in deep learning and classifier fusion techniques offer promising solutions to enhance the accuracy and robustness of biometric authentication systems in this paper we propose the integration of these methodologies, specifically in multimodal biometric systems that utilize face and fingerprint recognition. The research investigates various deep learning architectures, highlighting their effectiveness in processing diverse biometric datasets. Additionally, it examines classifier fusion techniques, which combine multiple classifiers to improve person identification performance. A significant focus of this research is on spoofing and anti-spoofing measures. Biometric systems, especially those involving facial and fingerprint recognition, are vulnerable to spoofing attacks such as the use of photographs, videos, or artificial fingerprints to impersonate legitimate users. We developed various anti-spoofing strategies that are integrated into the biometric authentication process to mitigate these risks. These include techniques like texture analysis, motion analysis, and liveness detection, which help differentiate between genuine biometric traits and spoofed samples. We benchmarked a comparative analysis of deep learning models and classifier fusion, demonstrated their strengths, weaknesses, and best practices. Additionally, performance evaluations focus on key metrics such as accuracy, computational efficiency, scalability, and the system’s ability to resist spoofing attacks. Ultimately, the paper emphasizes the potential of these advanced techniques to revolutionize biometric systems, with a particular focus on future research directions for optimizing these methodologies, particularly in the context of improving robustness against spoofing and enhancing the overall security of biometric authentication systems. overall system Equal Error Rate (EER), the True Acceptance Rate at a specified False Acceptance Rate (e.g., TAR @ 0.1% FAR), and the accuracy of the anti-spoofing module.

Cite This Paper

Shalini M. K., Santhosh Kumar K. S., Hemantha Kumar G., "Advances in Multimodal Biometric Authentication: A Classifier Fusion and Deep Learning Perspective", International Journal of Intelligent Systems and Applications(IJISA), Vol.18, No.3, pp.24-44, 2026. DOI:10.5815/ijisa.2026.03.02

Reference

[1]A. Sharma and R. Gupta, “Face recognition using deep convolutional neural networks,” IEEE Trans. on Biometrics, Behavior, and Identity Science, vol. 2, no. 3, pp. 223-231, July 2018.
[2]R. K. Pandey and S. Agarwal, “Fingerprint recognition using deep learning: A CNN-based approach,” Pattern Recognition Letters, vol. 118, pp. 14-20, Mar. 2019.
[3]M. Ali, J. Lee, and M. H. Lee, “A hybrid deep learning model combining CNN and LSTM for biometric authentication,” Neurocomputing, vol. 322, pp. 87-95, Nov. 2018.
[4]J. S. Lee, S. K. Park, and W. H. Kim, “Ear recognition based on deep convolutional neural networks,” IEEE Access, vol. 8, pp. 18567-18575, Mar. 2020.
[5]R. Sharma, P. Agarwal, and A. Verma, “Multimodal biometric recognition using a multi-task deep learning framework,” IEEE Trans. on Cybernetics, vol. 49, no. 2, pp. 664-673, Feb. 2019.
[6]A. Patel and P. Ghosh, “Fusion techniques for biometric authentication systems: A review,” IEEE Trans. on Systems, Man, and Cybernetics: Systems, vol. 48, no. 5, pp. 755-766, May 2018.
[7]L. Zhang, K. Xu, and X. Zhang, “Score-level fusion for multimodal biometric systems,” IEEE Trans. on Information Forensics and Security, vol. 13, no. 2, pp. 299-310, Feb. 2018.
[8]V. Kumar and S. Gupta, “Feature-level fusion in multimodal biometric systems,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 33, no. 1, pp. 205-215, Jan. 2019.
[9]R. Singh, N. Yadav, and R. Rajpoot, “Multimodal biometric authentication system using fusion of face, fingerprint, and iris recognition,” IEEE Trans. on Instrumentation and Measurement, vol. 69, no. 4, pp. 1561-1573, Apr. 2020.
[10]M. L. G. K. A. Subramanian, S. M. Salim, and R. J. Williams, “Face and fusion for multimodal biometric authentication,” Proceedings of the IEEE International Conference on Biometrics: Theory, Applications, and Systems, pp. 452-457, 2018.
[11]Y. Wang, L. L. Chen, and Y. Zhang, “Multimodal biometric system based on face, fingerprint, and palmprint fusion,” IEEE Trans. on Biometrics, Behavior, and Identity Science, vol. 2, no. 4, pp. 567-576, Oct. 2019.
[12]H. Liu and W. Huang, “Deep CNN and SVM classifier fusion for multimodal biometric authentication,” IEEE Trans. on Neural Networks and Learning Systems, vol. 30, no. 8, pp. 2345-2355, Aug. 2019.
[13]S. Verma and T. S. Mahapatra, “End-to-end deep learning system for multimodal biometric authentication with fusion,” IEEE Transactions on Artificial Intelligence, vol. 1, no. 3, pp. 222-233, July 2020.
[14]T. Lee, M. Li, and H. Cho, “Fusion of deep learning features for multimodal biometric authentication,” Neural Networks, vol. 120, pp. 116-124, Nov. 2019.
[15]A. Mohapatra, K. B. Pradhan, and A. S. Patra, “Hybrid deep learning-based multimodal biometric authentication using decision fusion,” IEEE Access, vol. 8, pp. 87788-87798, Jun. 2020.
[16]J. K. Patel, R. M. Agarwal, and N. S. Patil, “Deep reinforcement learning for multimodal biometric authentication,” IEEE Access, vol. 7, pp. 105234-105245, Aug. 2019.
[17]P. J. Brown and T. R. Grey, “Challenges in multimodal biometric fusion,” Proceedings of the IEEE International Conference on Image Processing, pp. 274-279, 2018.
[18]S. S. Bhat, M. S. Kumar, and D. K. Dhan, “Deep learning and transfer learning for multimodal biometric authentication,” IEEE Trans. on Artificial Intelligence, vol. 5, no. 1, pp. 52-64, Jan. 2021.
[19]R. Gupta and M. J. Williams, “Security challenges in multimodal biometric systems,” IEEE Transactions on Information Forensics and Security, vol. 15, no. 2, pp. 325-334, Feb. 2020.
[20]H. K. Sharma, L. P. Choudhury, and A. S. Patra, “Deep learning for multimodal biometric authentication: A comprehensive survey,” IEEE Access, vol. 8, pp. 101345-101365, Nov. 2019.
[21]S. Jain and P. Jain, “A multimodal biometric system combining face, fingerprint, and iris recognition,” Pattern Recognition Letters, vol. 89, pp. 47-56, Mar. 2019.
[22]A. Sharma, M. N. Patel, and R. Gupta, “Fusion techniques in multimodal biometric authentication,” Proceedings of the IEEE International Conference on Computational Intelligence and Security, pp. 299-305, 2020.
[23]A. Kumar, R. Rajpoot, and P. Agarwal, “Multimodal biometric fusion for robust identity verification,” IEEE Transactions on Computational Social Systems, vol. 7, no. 3, pp. 704-715, Sept. 2020.
[24]P. R. Sahoo and R. N. K. Bairwa, “Deep feature learning and fusion methods for multimodal biometrics,” Journal of Computer Vision and Image Understanding, vol. 174, pp. 32-45, Apr. 2019.
[25]M. K. Roy, P. S. Kumar, and D. J. Thakur, “Advances in deep learning for multimodal biometric fusion,” IEEE Transactions on Cybernetics, vol. 49, no. 7, pp. 2698-2710, July 2019.

International Journal of Intelligent Systems and Applications (IJISA)