User authentication based on analysis of the length and timing parameters of handwritten signature

This article presents methods for user authentication based on handwritten signature features characterizing its length as a scalar value and as a function of the dependence of the signature part curve length on time. The main emphasis is on methods for extracting static and dynamic features from a handwritten signature, these features are unique to each person and can be used to accept the truth or falsity of a particular user. During the analysis, data on time characteristics are collected, including the time spent writing each symbol and pauses between individual signature elements. The relevance of this study is due to the need to improve the security of user authentication in various systems where a handwritten signature serves as an important authentication element. The results of the study can be useful for creating more reliable authentication systems in such areas as banking, legal procedures, and other areas where a high degree of confidence in the authenticity of documents is required. The presented approaches not only contribute to increasing the level of authorization security, but also expand the horizons for further research in the field of biometric authentication. This, in turn, may lead to wider implementation of these technologies in practical applications in both online and offline systems.

1. Miskevich P.L., Petrovets V.N., Ralovets A.A. Development and Evaluation of Neural Network Methods for Handwritten Signature Verification. In: Komp'yuternye sistemy i seti: sbornik statei 59-i nauchnoi konferentsii aspirantov, magistrantov i studentov, 17–21 April 2023, Minsk, Belarus. Minsk: Belarusian State University of Informatics and Radioelectronics; 2023. P. 365–369. (In Russ.).

2. Xiao W., Wu H. Learning Features for Offline Handwritten Signature Verification Using Spatial Transformer Network. Scientific Reports. 2025;15. https://doi.org/10.1038/s41598-025-92704-3

3. Kozlovskii V.A., Maksimova A.Yu. Algoritm raspoznavaniya, osnovannyi na nechetkom podkhode. Artificial Intelligence. 2008;(4):594–599. (In Russ.).

4. Levinsky A.T. Manual Signature Verification Algorithms Based on Neural Networks. StudNet. 2020;3(3):395–402. (In Russ.).

5. Ivanov Yu.S., Avdeenko A.A. Obzor metoda verifikatsii lichnosti po podpisi i razrabotka programmnogo obespecheniya. Vestnik nauchnogo obshchestva studentov, aspirantov i molodykh uchenykh. 2014;(1):3–8. (In Russ.).

6. Haerova E.I. Using Neural Network Technologies to Identify A Person's Signature. In: Nigmatullin's Readings – 2023: Proceedings of the International Conference, 09–12 October 2023, Kazan, Russia. Kazan: TAS Publishing House; 2023. P. 428–431. (In Russ.).

7. Kadilnikova T.M., Minyuk O.N. Matematicheskoe modelirovanie protsessov verifikatsii v dokumentooborote organizatsii. In: Bankovskaya sistema: ustoichivost' i perspektivy razvitiya: sbornik nauchnykh statei X Mezhdunarodnoi nauchno-prakticheskoi konferentsii po voprosam finansovoi i bankovskoi ekonomiki, posvyashchennoi 75-letiyu bankovskogo obrazovaniya na belorusskom Poles'e, 25 October 2019, Pinsk, Belarus. Pinsk: Polessky State University; 2019. P. 321–326. (In Russ.).

8. Drobintsev P.D., Sergeev D.I., Voinov N.V. Online Signature Verification System for Mobile Devices with Multilevel Pressure Sensor. In: The XX International Conference on Soft Computing and Measurements (SCM'2017): Volume 1, 24–26 May 2017, Saint Petersburg, Russia. Saint Petersburg: Saint Petersburg Electrotechnical University "LETI"; 2017. P. 520–522. (In Russ.).

9. Anisimova E.S., Anikin I.V. Comparative Analysis of Neural Network Models for Handwritten Signature Dynamics Recognition. Electronics, Photonics and Cyber-Physical Systems. 2024;4(3):77–85. (In Russ.).

10. Starovoitov V.V. Should We Normalize Dynamic Signatures Data Before DTW-Based Verification? In: Big Data and Advanced Analytics: sbornik nauchnykh statei X Mezhdunarodnoi nauchno-prakticheskoi konferentsii: Part 2, 13 March 2024, Minsk, Belarus. Minsk: Belarusian State University of Informatics and Radioelectronics; 2024. P. 391–400. (In Russ.).

11. Maergner P., Pondenkandath V., Alberti M., et al. Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks. In: Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop, S+SSPR 2018: Proceedings, 17–19 August 2018, Beijing, China. Cham: Springer; 2018. P. 470–480. https://doi.org/10.1007/978-3-319-97785-0_45

12. Kuznetsov V.V. Ispol'zovanie matritsy uglov dlya povysheniya tochnosti metoda biometricheskoi verifikatsii po dinamicheskoi podpisi. Tekhnika i tekhnologiya: novye perspektivy razvitiya. 2014;(XV):72–75. (In Russ.).