Research on neural network algorithms for user dynamic signature recognition in the space of multidimensional curve samples, in comparison with optimal detection–discrimination algorithms for multidimensional signals

Purpose of research. The widespread adoption of dynamic signatures in various biometric technology applicationssupported by clearly defined legal procedures in many countries-drives significant attention toward the reliability of corresponding biometric authentication algorithms. While dynamic signatures are partially free from the drawbacks inherent in static signatures, the problem of authentication reliability remains critical due to the complex interplay of heterogeneous factors. Therefore, the aim of this study is to improve the reliability of user authentication based on the dynamic signature using experimental structural and parametric synthesis of problem-oriented neural networks and comparison with classical detection-discrimination algorithms for multidimensional signals.

Methods. The proposed method involves comprehensive identification of the user's dynamic signature in the sample space of multidimensional curves by means of parallel recognition of curve fragments using multiple detectors/classifiers, followed by integration and analysis of the results.

Results. Neural network algorithms for identifying the user’s dynamic signature in the sample space of multidimensional curves were experimentally studied and compared with optimal detection-discrimination algorithms for multidimensional signals. The experiments demonstrated that 3–5 key parameters-including two stylus coordinates on the tablet plane, screen pressure, and stylus velocity vectors-ensure acceptable identification reliability in the range of 0,8 to 0,95 for a small number of users, and maintain a reliability level of about 0,7 with unlimited user scaling. The average gain in accuracy from using the developed models and algorithms, compared to statistical methods, amounted to 25– 35%, and compared to metric methods, 5–15%.

Conclusion. To achieve the required reliability of user authentication, hardware-software identification models for dynamic signatures should be decomposed into groups with a limited number of users. There exists an optimal combination of algorithms that delivers maximum accuracy in result integration: Euclidean metric, correlation-based, and neural network classifiers.

1. Biometrics in the financial sector 2020: benefits for the consumer. Analytical note. (In Russ.) Available at: https://www.fintechru.org/upload/iblock/659/g6k39ftq1hkehkn4b22znw1vsfa9lsrg.pdf?ysclid=mjlc9613ot802675625 (accessed: 04.09.2025).

2. Lomov N., Petrova D., Ryazantseva Y. Biometrics in the financial sector 2020: Benefits for consumers // Analytical note. URL: https://www.fintechru.org/analytics/analiticheskayazapiska-po-biometrii/?ysclid=lvwb2xh8z610856013 (accessed 06.06.2025).

3. Biometrics: what it is and how it affects the world of finance. Frank Media. (In Russ.) Available at: https://frankmedia.ru/137504?ysclid=lvwb85nb3o106633262 (accessed 05.09.2025).

4. Report on the analysis of the size, share and trends of the global biometric systems market – industry overview and forecast up to 2032. (In Russ.) Available at: https://www.databridgemarketresearch.com/ru/reports/global-biometric-system-market?ysclid=lvwg0cfco7989485412 (accessed 05.09.2025).

5. Marcel S., Nixon M. S., Fierrez J., Evans N. Handbook of Biometric Anti-Spoofing. Presentation Attack Detection and Vulnerability Assessmen. Singapore: Springer; 2023. 595 p.

6. Jain A.K., Griess F.D., Connell S.D. Online signature verification. Pattern Recognition. 2022;(35):2963–2972.

7. Rostovtsev V.S. Artificial neural networks. 4th ed. Saint Petersburg: Lan'; 2024. 216 p. (In Russ.)

8. Bishop K.M. Pattern recognition and machine learning. Saint Petersburg: Dialektika Publ., 2020. 960 p. (In Russ.)

9. Carmona P.L., Salvador S.A., Fred L.N. Mathematical Methodologies in Pattern Recognition and Machine Learning: Contributions from the International Conference on Pattern Recognition Applications and Methods. Springer, 2020. 204 p.

10. Kevin P. Murphy. Probabilistic Machine Learning: Advanced Topics. MIT Press; 2023. 1175 p.

11. Rawlson K. Explainer: Signature Recognition. Available at: https://www.biometricupdate.com/201601/explainer-signature-recognition (accessed 26.09.2025).

12. Signature Verification System. Elsevier. Marketing. Available at: https://www.elsevier.marketing/journal/Pattern-Recognition (accessed 26.09.2025).

13. Tantserov A.Kh., Danilov E.A. Kinematic model of the formation of the etalon dynamic parameters of the user's signature. Vestnik Ryazanskogo gosudarstvennogo radiotekhnicheskogo universiteta = Bulletin of the Ryazan State Radio Engineering University. 2025;(92):170–178. (In Russ.) https://doi.org/10.21667/1995-4565-2025-92-170-178

14. Farabet C., Couprie C., Najman L., LeCun Y. Learning hierarchical features for scene labeling. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;(8):1915– 1929.

15. Xu A., Aminian A. System Design. Machine learning. Preparation for a difficult interview. Saint Petersburg: Piter; 2024. 320 p. (In Russ.)

16. Tantserov A.Kh., Danilov E.A., Martyshkin A.I. Review and comparison of some methods of signature authentication by dynamic parameters. Bulletin of the Russian State Radio Engineering University. 2025;(92):213–224. (In Russ.) https://doi.org/10.21667/1995-4565-2025-92-213-224

17. Antal M., Szabo L. J., Tordai T. Online verification of the signature on the fingerprint case MOBISIG, 2018. (In Russ.) Available at: http://www.ms.sapientia.ro/~manyi/mobisig/MOBISIG.ZIP, (accessed 01.09.2025).

18. Suratgar A.A., Tavakoli M.B., Hoseinabadi A. Modified Levenberg-Marquardt method for neural networks training. 2022. P. 1745–1747.

19. Sousa, C. Neural network learning by the Levenberg-Marquardt algorithm with Bayesian regulation (part 1). Available at: http://crsouza.blogspot.com/2009/11/neural-network-learning-by-levenberg_18.html (accessed 05.09.2025).

20. Tanzerov A.Kh., Danilov E.A. Modern approaches to signature recognition and authentication: image processing methods. XXI vek: itogi proshlogo i problemy nastoyashchego plyus = XXI Century: the Results of the Past and the Problems of the Present Plus. 2025;14(2):71–76. (In Russ.) EDN SCSZTT