Deep Learning-Based Signature Verification for Secure Banking

Agrawal, Jharna; Al-Ani, Yaser

doi:10.25673/123735

Proceedings of International Conference on Applied Innovation in IT · 2026/03/31 · Vol. 14 · Issue 1 · pp. 1319–1326

Deep Learning-Based Signature Verification for Secure Banking

Jharna Agrawal, Yaser Issam Hamodi Aljanabi and Huthaifa Ayad Al-Ani

📄 Download PDF DOI: 10.25673/123735

Abstract

User authentication is a fundamental part of the present-day banking in the digital transformation era because it must be secure, and, most importantly, reliable. Verification of handwritten signatures due to their legal and cultural acceptability remains an important aspect of the authorization of financial transactions. Nonetheless, the conventional verification systems cannot handle issues like intra-class variations, expert forgeries, and real-time implementation needs. This paper presents a convolutional neural network-based system of Siamese CNN and Capsule Network (CapsNet) using deep learning as an offline signature verification system, with the aim of achieving high precision in detecting forgeries in the banking industry. Various datasets such as GPDS, CEDAR, Persian bank checks, and digital document signatures are used to train the model and test it. It demonstrated a peak accuracy of 97.8 and an Equal Error Rate (EER) of 2.6 that is better than a number of state of the art approaches. The robustness of the model and its generalization to various signature styles have been shown through visual and quantitative analysis, with t-SNE plots, ROC curves, confusion matrices, etc. The given system has a huge potential of being implemented in the secure, scalable, and explainable banking authentication pipelines.

Keywords

Signature Verification Deep Learning Siamese Network Capsule Network Forgery Detection Secure Banking Biometrics Document Authentication Offline Verification Financial Security.

References

K. Roszczewska and E. Niewiadomska-Szynkiewicz, “Online signature biometrics for mobile devices,” Sensors, vol. 24, no. 11, p. 3524, 2024.
M. M. Hameed, R. Ahmad, M. L. M. Kiah, and G. Murtaza, “Machine learning-based offline signature verification systems: A systematic review,” Signal Processing: Image Communication, vol. 93, p. 116139, 2021.
H. H. Kao and C. Y. Wen, “An offline signature verification and forgery detection method based on a single known sample and an explainable deep learning approach,” Applied Sciences, vol. 10, no. 11, p. 3716, 2020.
R. Ghosh, “A Recurrent Neural Network based deep learning model for offline signature verification and recognition system,” Expert Systems with Applications, vol. 168, p. 114249, 2021.
S. Lai, L. Jin, and W. Yang, “Online signature verification using recurrent neural network and length-normalized path signature descriptor,” in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 400-405, IEEE, 2017.
R. Tolosana, R. Vera-Rodriguez, J. Fierrez, and J. Ortega-Garcia, “DeepSign: Deep on-line signature verification,” IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 3, no. 2, pp. 229-239, 2021.
Y. Zhang, W. Bi, and R. Song, “Research on deep learning-based authentication methods for e-signature verification in financial documents,” Academic Journal of Sociology and Management, vol. 2, no. 6, pp. 35-43, 2024.
L. G. Hafemann, R. Sabourin, and L. S. Oliveira, “Learning features for offline handwritten signature verification using deep convolutional neural networks,” Pattern Recognition, vol. 70, pp. 163-176, 2017.
L. Liu, L. Huang, F. Yin, and Y. Chen, “Offline signature verification using a region based deep metric learning network,” Pattern Recognition, vol. 118, p. 108009, 2021.
S. Masoudnia, O. Mersa, B. N. Araabi, A. H. Vahabie, M. A. Sadeghi, and M. N. Ahmadabadi, “Multi-representational learning for offline signature verification using multi-loss snapshot ensemble of CNNs,” Expert Systems with Applications, vol. 133, pp. 317-330, 2019.
A. B. Jagtap, D. D. Sawat, R. S. Hegadi, and R. S. Hegadi, “Verification of genuine and forged offline signatures using Siamese Neural Network (SNN),” Multimedia Tools and Applications, vol. 79, no. 47, pp. 35109-35123, 2020.
W. Xiao and Y. Ding, “A two-stage siamese network model for offline handwritten signature verification,” Symmetry, vol. 14, no. 6, p. 1216, 2022.
E. Parcham, M. Ilbeygi, and M. Amini, “CBCapsNet: A novel writer-independent offline signature verification model using a CNN-based architecture and capsule neural networks,” Expert Systems with Applications, vol. 185, p. 115649, 2021.
S. Shariatmadari, S. Emadi, and Y. Akbari, “Patch-based offline signature verification using one-class hierarchical deep learning,” International Journal on Document Analysis and Recognition (IJDAR), vol. 22, no. 4, pp. 375-385, 2019.
Y. Akbari, M. J. Jalili, J. Sadri, K. Nouri, I. Siddiqi, and C. Djeddi, “A novel database for automatic processing of Persian handwritten bank checks,” Pattern Recognition, vol. 74, pp. 253-265, 2018.
S. Tehsin, A. Hassan, F. Riaz, I. M. Nasir, N. L. Fitriyani, and M. Syafrudin, “Enhancing signature verification using triplet siamese similarity networks in digital documents,” Mathematics, vol. 12, no. 17, p. 2757, 2024.
M. F. Majed and M. Mgohimi, “Numerical Investigation of the Thermosiphon-Thermoelectric Generator by Different Parameters,” Journal of Techniques, vol. 7, no. 2, pp. 46-59, 2025, [Online]. Available: https://doi.org/10.51173/jt.v7i2.2666.
H. Alrammahi and M. T. Mahmood, “An Advanced Framework for Intrusion Detection in Network Security Utilizing Machine Learning Algorithms: Challenges, Solutions, and Future Direction,” InfoTech Spectrum: Iraqi Journal of Data Science, vol. 2, no. 2, pp. 21-31, 2025, [Online]. Available: https://doi.org/10.51173/ijds.v2i2.37.
H. S. Ezzulddin, “Proposed Model for Credit Card Fraud Detection Model Using Machine Learning Technique,” InfoTech Spectrum: Iraqi Journal of Data Science, vol. 3, no. 1, 2025, doi: 10.51173/ijds.v3i1.50.