REVIEW OF MACHINE LEARNING ALGORITHMS FOR HANDWRITTEN SIGNATURE RECOGNITION

This review examines biometric technologies used in security systems for identity recognition based on physiological and behavioral traits, with a focus on signature verification. Signature is an important biometric trait widely used in legal, financial, and administrative fields. The article describes two types of biometric systems: verification and identification. In the verification process, the system confirms the authenticity of signatures, distinguishing between random, simple, and qualified forgeries. Special attention is given to the classification of signature verification systems, including online (dynamic) and offline (static) methods, as well as recent advancements in the use of deep learning and machine methods to improve verification accuracy. The article covers key stages in signature processing and analysis, such as feature extraction, normalization, and alignment of data. Methods for predicting the authenticity of signatures using machine learning, including hidden Markov models, support vector machines, and neural networks, are also discussed. The author identifies current issues, such as the lack of data for training and difficulties in detecting fakes, as well as prospects for future research in hybrid methods and improving data collection technologies. The article emphasizes the importance of adopting modern devices, such as plane-table and smart pens, to enhance the accuracy of signature verification systems.

Handwritten signature verification, literature review, biometrics, neural networks, deep learning, support vector machines, ensemble classifiers.

1. Abdul Salam Shah, M.N.A. Khan, Asadullah Shah. Evaluation of Offline Signature Verification Methods // International Journal of Modern Education and Computer Science. – 2015. – Vol. 4. – pp. 67–75.

2. Anil K. Jain, Arun Ross, Salil Prabhakar. Introduction to Biometric Recognition // IEEE Transactions on Video Technology. – 2004. – Vol. 14, No. 1. – pp. 4–20.

3. Bertolini D., Sabourin R., Oliveira L.S. Ensemble Methods Using Graphometric Features for Writer-Independent Offline Signature Verification // International Journal of Pattern Recognition and Artificial Intelligence. – 2013. – Vol. 27, No. 6. – pp. 1345–1361.

4. Dominique Rivard, Eric Granger, Robert Sabourin. Multi-Feature Extraction and Selection in Writer-Independent Offline Signature Verification // International Journal on Document Analysis and Recognition. – 2013. – Vol. 16, No. 1.

5. Donato Impedovo, Giuseppe Pirlo. Automatic Signature Verification: The State of the Art // IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews. – 2008. – Vol. 38, No. 5. – pp. 609–635.

6. Donato Impedovo, Giuseppe Pirlo, Rejean Plamondon. Handwritten Signature Verification: New Advances and Open Issues // Proceedings of the International Conference on Frontiers in Handwriting Recognition. – IEEE, 2012.

7. J.-P. Drouard, Robert Sabourin, Mario Godbout. Neural Network Approach to Writer-Independent Offline Signature Verification Using Oriented PDFs // Pattern Recognition. – 1996. – Vol. 29, No. 3. – pp. 415–424.

8. Edson Justino, Luiz S. Oliveira, Batista L.F. Offline Signature Verification System Using Hidden Markov Models and Cross-Validation // IEEE International Joint Conference on Neural Networks Proceedings. – 2000. – Vol. 6. – pp. 2534–2539.

9. Gerbhay D., McCoy J., Kim D. Signature Classification Using One-Class SVM // Journal of Machine Learning. – 2002. – Vol. 42, No. 1. – pp. 261–272.

10. G.S. Eskander, R. Sabourin, E. Granger. Hybrid Writer-Dependent Offline Signature Verification System // IET Biometrics. – 2013. – Vol. 2, No. 4. – pp. 169–181.

11. J.F. Vargas, M.A. Ferrer, S.M. Travieso, J.B. Alonso. GPDS-960 Corpus for Offline Handwritten Signature Verification // Proceedings of the Ninth International Conference on Document Analysis and Recognition. – 2007. – Vol. 2. – pp. 764–768.

12. J.F. Vargas, M.A. Ferrer, S.M. Travieso, J.B. Alonso. Off-Line Signature Verification Based on Gray Level Information Using Texture Features // Pattern Recognition. – 2011. – Vol. 44, No. 2. – pp. 375–385.

13. Donato Impedovo, Giuseppe Pirlo. Automatic Signature Verification: The State of the Art // IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews. – 2008. – Vol. 38, No. 5. – pp. 609–635.

14. J.-P. Drouard, Robert Sabourin, Mario Godbout. Neural Network Approach to Writer-Independent Offline Signature Verification Using Oriented PDFs // Pattern Recognition. – 1996. – Vol. 29, No. 3. – pp. 415–424.

15. Edson Justino, Luiz S. Oliveira, Batista L.F. Offline Signature Verification System Using Hidden Markov Models and Cross-Validation // IEEE International Joint Conference on Neural Networks Proceedings. – 2000. – Vol. 6. – pp. 2534–2539.

16. Kai Huang, Hong Yan. Offline Signature Verification Using Geometric Features and Neural Network Classification // Pattern Recognition. – 1997. – Vol. 30, No. 1. – pp. 9–17.

17. Luis G. Hafemann, Robert Sabourin, Luiz S. Oliveira. Learning Features for Offline Handwritten Signature Verification Using Deep Convolutional Neural Networks // Pattern Recognition. – 2017. – Vol. 70. – pp. 163–176.

18. Luiz S. Oliveira, Edson Justino, Cynthia Freitas, Robert Sabourin. Graphology in Signature Verification // Proceedings of the 12th Conference of the International Graphonomics Society. – 2005. – pp. 286–290.

19. Mustafa Berkay Yilmaz, Berrin Yanikoglu. Score-Level Fusion of Classifiers in Offline Signature Verification // Information Fusion. – 2016. – Vol. 32, Part B. – pp. 109–119.

20. Réjean Plamondon, Guy Lorette. Automatic Signature Verification and Writer Identification – The State of the Art // Pattern Recognition. – 1989. – Vol. 22, No. 2. – pp. 107–131.

21. Réjean Plamondon, Sargur N. Srihari. Online and Offline Handwriting Recognition: A Comprehensive Survey // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2000. – Vol. 22, No. 1. – pp. 63–84.

22. Frank Leclerc, Réjean Plamondon. Automatic Signature Verification: The State of the Art 1989–1993 // International Journal of Pattern Recognition and Artificial Intelligence. –1994. –  Vol. 8, No. 3. – pp. 643–660.

23. H. Ranch, H. Yan, K. Meinel. Signature Embedding: Writer-Independent Offline Signature Verification Using Metric Learning // Advances in Visual Computing. – Springer, 2016.

24. Huang H., Yan H. Offline Signature Verification Based on Geometric Feature Extraction and Neural Network Classification // Pattern Recognition. – 1997. – Vol. 30, No. 1. – pp. 9–17.

25. Huang Hu, Yubin Chen. Offline Signature Verification Using Adaboost Classifier and Pseudo-Dynamic Features // Proceedings of the 12th International Conference on Document Analysis and Recognition. – 2013. – pp. 1345–1349.

2026-03-26