About handwritten signature verification
Some methods for the online verification of handwritten signatures are presented. The methods are based on the KNN algorithm, a Range Classifier algorithm, a hidden Markov model, and the simplest per-ceptron neural network. The features of these methods are studied in the course of their implementing and testing with the purpose of the further modifications and the development of the most effective ones for all parameters of the verification procedure.
Download file
Counter downloads: 179
Keywords
верификация собственноручной подписи, скрытые модели Маркова, нейронные сети, verification of handwritten signature, hidden Markov model, neural networkAuthors
| Name | Organization | |
| Epishkina A. V. | National Research Nuclear University "MEPhI" | avepishkina@mephi.ru |
| Beresneva A. V. | National Research Nuclear University "MEPhI" | anastasiya3161@gmail.com |
| Babkin S. S. | National Research Nuclear University "MEPhI" | ssbbkn@ya.ru |
| Kurnev A. S. | National Research Nuclear University "MEPhI" | simpleman383@gmail.com |
| Lermontov V. Yu. | National Research Nuclear University "MEPhI" | 0rhast0@gmail.com |
References
Kashi R. S., Hu J., Nelson W. L., and Turin W. On-line handwritten signature verification using hidden Markov model features // IEEE Proc. 4th Intern. Conf. Document Analysis and Recognition, Ulm, Germany, 1997. P. 253-257.
Beatrice D. and Thomas H. On-line Handwritten Signature Verification using Machine Learning Techniques with a Deep Learning Approach. Master's Theses in Math. Sciences, Lund University, 2015. 90 p.
McCabeA., Trevathan J., and Read W. Neural network-based handwritten signature verification // J. Computers. 2008. V.3. No. 8. P. 9-22.
