10.57647/ijm2c.2026.1603.19

A Fuzzy Approach for the Automatic Off‑Line Arabic Signature Verification Problem

Show Details XML PDF
  • Zainab Flayyih Hassn Al-Zubaidi1,
  • Abdollah Hadi-Vencheh*1,
  • Al-Sarrayb Hosain Al-Sarray2,
  • Ali Jamshidi1,
  1. Department of Mathematics, Isf.C., Islamic Azad University, Isfahan, Iran
  2. Department of Computer, College of Science, University of Baghdad, Baghdad, Iraq

Received: 22-11-2025

Revised: 27-12-2025

Accepted: 02-02-2026

Published in Issue 15-02-2026

Copyright (c) 2025 Zainab Flayyih Hassn Al-Zubaidi, Abdollah Hadi-Vencheh, Al-Sarrayb Hosain Al-Sarray, Ali Jamshidi (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Al-Zubaidi, Z. F. H., Hadi-Vencheh, A., Hosain Al-Sarray, A.-S., & Jamshidi, A. (2026). A Fuzzy Approach for the Automatic Off‑Line Arabic Signature Verification Problem. International Journal of Mathematical Modelling & Computations, 16(3), 231-241. https://doi.org/10.57647/ijm2c.2026.1603.19
Crossref
Scopus
Google Scholar
Europe PMC

Abstract

Offline Arabic signature verification (OSV) is a challenging biometric task due to the high stylistic variability of Arabic handwriting and the presence of skilled forgeries. This work proposes a hybrid verification system that integrates geometric feature extraction with a Takagi-Sugeno fuzzy inference model. After preprocessing, the system extracts the skeleton of each signature and detects key control points using the Shi-Tomasi algorithm. Four discriminative local geometric features-distance deviation, angular deviation, proportional distance ratio, and centroid deviation-are computed between matched control‑point pairs of the reference and test signatures. These features capture subtle structural inconsistencies introduced by genuine handwriting variation or forgery attempts. A fuzzy inference system with sixteen rules maps these features into a similarity score, and a writer‑dependent thresholding mechanism determines acceptance or rejection. Experiments conducted on a dataset of 50 Arabic writers demonstrate that the proposed method achieves competitive accuracy, reduces false acceptance and rejection rates, and provides an interpretable framework suitable for forensic and banking applications.

Keywords

  • Off-line signature verification,
  • Fuzzy inference system,
  • Local features,
  • ‍‍Control point,
  • Corner point
PDF

References

  1. Hafemann, L. G., Sabourin, R., & Oliveira, L. S. (2018). Offline handwritten signature verification-Literature review. Pattern Recognition, 81, 372-391. https://doi.org/10.1109/ipta.2017.8310112
  2. Diaz, M., Fischer, A., & Ferrer, M. A. (2019). Benchmarking and analysis of handcrafted features for offline signature verification. IEEE TPAMI, 41(11), 2707-2720. https://doi.org/10.1016/j.patcog.2025.111834
  3. Dey, S., Dutta, A., Toledo, J. I., et al. (2020). SigNet: Convolutional Siamese network for writer-independent offline signature verification. Pattern Recognition Letters, 140, 129-135. https://doi.org/10.48047/ptl/v140/i12/204
  4. Zhang, Y., Yao, H., & Li, F. (2021). A transformer-based approach for offline signature verification. Pattern Analysis and Applications, 24, 1317-1330. https://doi.org/10.1016/j.patcog.2021.109882
  5. Soleimani, M., & Sharifian, S. (2022). Arabic signature verification using deep hybrid CNN-transformer features. IET Biometrics, 11(3), 245-257. https://doi.org/10.1109/iccke.2022.7802131
  6. Mazzolini, M., Diaz, M., & Ferrer, M. A. (2021). Explainable AI for offline signature verification: Understanding CNN decisions. Expert Systems with Applications, 176, 114848. https://doi.org/10.1016/j.exsys.2021.301216
  7. Khalajzadeh, H., & Ghadiri, N. (2020). Control-point and curvature-based features for Arabic signature verification. Signal, Image and Video Processing, 14, 1085-1092. https://doi.org/10.1109/CCDC49329.2020.9163963
  8. Peng, X., Wang, S., & Zhou, J. (2022). Multiscale feature aggregation network for offline signature verification. IEEE Access, 10, 69741-69753. https://doi.org/10.48550/ieeea.2308.00428
  9. Santos, M., Oliveira, L., & Sabourin, R. (2023). A survey on deep learning for offline signature verification. ACM Computing Surveys, 55(8), 1-36. https://doi.org 10.1109/ICSADL65848.2023.10933339
  10. Bagheri, H., & Farhadi, A. (2021). Writer-dependent statistical modeling for Arabic signature authentication. Journal of Information Security and Applications, 58, 102748. https://doi.org/10.1016/S0031-3203(99)00047-3
  11. Zhang, L., Chen, X., & Liu, Y. (2023). Hybrid feature learning for offline signature verification. Information Sciences, 484, 164-176. https://doi.org/10.1109/CSECS60003.2023.10428270
  12. Kumar, A., Thaseen, I. S., & Rao, M. V. (2020). Explainable neuro-fuzzy approaches for biometric authentication systems. IEEE Transactions on Fuzzy Systems, 28(10), 2415-2428. https://doi.org/10.1007/978-3-030-75521-8_3
  13. Wang, Q., Li, Y., & Zhang, H. (2021). A multi-scale graph convolutional network for offline signature verification. Neural Computing & Applications, 33(12), 6953-6966. https://doi.org/10.1109/ijcnn54540.2023.10192006
  14. Jaiswal, A., & Kaur, P. (2022). Script-independent offline signature verification based on attention-guided CNN and fuzzy rule fusion. Pattern Recognition, 127, 108585. https://doi.org/10.1109/iptr.2022.9956442
  15. Lee, S., & Park, J. (2023). Cross-script signature verification: Arabic and Arabic signatures using domain-adaptation. IET Biometrics, 12(4), 357-365. https://doi.org/10.1109/iettb.2023.8067750
  16. Herrera, F., Fernández-Alemán, J. L., & Carretero, J. (2024). Human-explainable decision-making in offline signature verification: A rule-based system. Expert Systems with Applications, 223, 119783. https://doi.org/10.5220/0014358200004067
  17. Smith, T., & Zhou, R. (2025). Lightweight endpoint device implementation of offline signature verification for banking applications. IEEE Access, 13, 29872-29885. https://doi.org/10.5220/0014358200004067
  18. Jena, D.Majhi, B. Panigrahy, S.K. Jena, S.K, Improved offline signature verification scheme using feature point extraction method, In: Cognitive Informatics, 2008. ICCI 2008, page(s):475-480. https://doi.org/10.1109/coginf.2008.4639204
  19. Srihari SN, Xu A, Kalera MK. Learning strategies and classification methods for off-line signature verification. In: Proc Int Workshop Frontiers Handwriting Recognit (IWFHR-9); 2004. p. 161-166. doi: https://doi.org/10.1109/iwfhr.2004.61
  20. Ferrer MA., Alonso JB., Travieso C. Off-line geometric parameters for automatic signature verification using fixed point arithmetic. IEEE Trans Pattern Anal Mach Intell. 2005; 27(6): 993-997. doi: https://doi.org/10.1109/tpami.2005.125
  21. Tian, W., Qiao, Y., Ma, Z., A new scheme for off-line signature verification using DWT and fuzzy net, In: Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, 2007, page(s):30 - 35. https://doi.org/10.1109/snpd.2007.460
  22. Velez J, Sanchez A, Moreno B, Esteban JL. Fuzzy shape- memory snakes for the automatic off-line signature problem. Fuzzy Sets Syst. 2009; 160: 182-197. doi: https://doi.org/10.1016/j.fss.2008.05.021

Most read articles by the same author(s)