Verification of normalized online signatures without calculating dynamic features
https://doi.org/10.37661/1816-0301-2024-21-4-72-84
Abstract
Objectives. Study of the method of verification of the authenticity of a human signature made on a tablet with a stylus and given three parameters: coordinates X, Y and pressure on the tablet P.
Methods. N genuine dynamic human signatures are given. Data describing different signatures made by one person always have a different number of points. The main variants of normalization of the original signature data are investigated. A model of an individual image of human signatures is built without calculating dynamic features. The method of dynamic time transformation (DTW) is used to compare similar data of different signatures. The results of this transformation are DTW-distances between the data of pairs of signatures. These distances serve as coordinates of a point in the feature space describing the similarity of a pair of signatures. A set of such points represents a model describing the similarity of genuine human signatures. The parameters of the signature being verified are compared with each of the N authentic signatures used to build the model for their proximity to the model. If more than half of these pairs are further from the model than a certain threshold T, the signature is considered fake.
Results. As a result of comparative experiments, a variant of normalization of initial data of dynamic human signatures was found, which allows verification of such signatures without calculating additional features usually calculated from the initial data X, Y, P.
Conclusion. Experiments to generate individual signature models for each of 230 people from the publicly available MCYT dynamic signature database (a subset of the DeepSignDB database) and verify the authenticity of 11,500 signatures made on behalf of these people showed a verification accuracy of 99.82 %. Half of them were genuine, half were fake.
About the Author
V. V. Starovoitov
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Valery V. Starovoitov, D. Sc. (Eng.), Prof.
st. Surganova, 6, Minsk, 220012
References
1. Kaur H., Kumar M. Signature identification and verification techniques: state-of-the-art work. Journal of Ambient Intelligence and Humanized Computing, 2023, vol. 14, no. 2, рр. 1027–1045.
2. Chuprina M. V. Language policy in the Republic of India. Znanie. Ponimanie. Umenie [Knowledge. Understanding. Skill], 2012, no. 2, pp. 293–297 (In Russ.).
3. Starovoitov V. V. Verification of the person’s dynamic signature on a limited number of samples. Informatika [Informatics], 2024, vol. 21, no. 2, pp. 94−106 (In Russ.).
4. Starovoitov V. V. Should we normalize dynamic signatures data before DTW-based verification? BIG DATA i analiz vysokogo urovnja : sbornik nauchnyh statej X Mezhdunarodnoj nauchno-prakticheskoj konferencii, Minsk, 13 marta 2024 goda : v 2 chastjah [BIG DATA and Advanced Analytics : Collection of Scientific Articles of the X International Scientific and Practical Conference, Minsk, 13 March 2024 : in 2 Parts]. Минск, 2024, part 2, рр. 391–400 (In Russ.).
5. Tolosana R., Vera-Rodriguez R., Fierrez J., Ortega-Garcia J. DeepSign: Deep on-line signature verification. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2021, vol. 3, iss. 2, рр. 229–239.
6. Saleem M., Kovari B. Survey of preprocessing techniques and classification approaches in online signature verification. Image Analysis and Recognition. ICIAR 2020. Lecture Notes in Computer Science, 2020, vol. 12131, pp. 253–266. DOI: 10.1007/978-3-030-50347-5_23.
7. Saleem M., Lia Szucs C., Kovari B. Systematic evaluation of pre-processing approaches in online signature verification. Intelligent Decision Technologies, 2023, vol. 17, no. 3, pp. 655–672.
8. Fenton D., Bouchard M., Yeap T. H. Evaluation of features and normalization techniques for signature verification using dynamic timewarping. IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, Toulouse, France, 14–19 May 2006. Toulouse, 2006, vol. 3. Available at: https://ieeexplore.ieee.org/document/1660860/keywords#keywords (accessed 17.08.2024).
9. Xia X., Chen Z., Luan F., Song X. Signature alignment based on GMM for on-line signature verification // Pattern Recognition, 2017, vol. 65, pp. 188–196.
10. Fierrez-Aguilar J., Nanni L., Lopez- eñalba J., Ortega-Garcia J., Maltoni D. An on-line signature verification system based on fusion of local and global information. 5th International Conference Audio- and Video-Based Biometric Person Authentication, Hilton Rye Town, N. Y., USA, 20–22 July 2005. Springer, 2005, рр. 523–532.
11. Xia X., Song X., Luan F., Zheng J., Chen Z., Ma X. Discriminative feature selection for on-line signature verification. Pattern Recognition, 2018, vol. 74, pp. 422–433.
12. Houmani N., Mayoue A., Garcia-Salicetti S., Dorizzi B., Khalil M. I., …, Vivaracho-Pascual C. BioSecure signature evaluation campaign (BSEC'2009): Evaluating online signature algorithms depending on the quality of signatures. Pattern Recognition, 2012, vol. 45, no. 3, рр. 993–1003.
13. Sharma A., Sundaram S. An enhanced contextual DTW based system for online signature verification using vector quantization. Pattern Recognition Letters, 2016, vol. 84, pp. 22–28.
14. Jiang J., Lai S., Jin L., Zhu Y. Dsdtw: Local representation learning with deep soft-dtw for dynamic signature verification. IEEE Transactions on Information Forensics and Security, 2022, vol. 17, pp. 2198–2212.
15. Wu X., Kimura A., Uchida S., Kashino K. Prewarping Siamese network: Learning local representations for online signature verification. IEEE International Conference on Acoustics, Speech and Signal Processing, Brighton, UK, 2–17 May 2019. Brighton, 2019, рр. 2467–2471.
Review
For citations:
Starovoitov V.V. Verification of normalized online signatures without calculating dynamic features. Informatics. 2024;21(4):72-84. (In Russ.) https://doi.org/10.37661/1816-0301-2024-21-4-72-84
Views: 130
Email this article 