Generate QR code
Open Access
Subscription Access
Methods of Preprocessing of Digitized Handwritten Documents
https://doi.org/10.17586/0021-3454-2025-68-6-494-499
Abstract
The problem of automating the analysis of handwritten documents is solved. It is shown that artificial neural networks capable of recognizing images after training on the original data set are used to solve such problems. At the same time, the quality of recognizing new images largely depends on the stage of pre-processing of digitized handwritten documents. A particular preprocessing problem is considered - removing cell lines from an image of a notebook sheet. Four methods of image filtering are analyzed using the OpenCV library of the Python language. A neural network of convolutional architecture is trained to recognize handwritten characters. The work of the trained neural network on documents preprocessed by different algorithms is demonstrated.
About the Authors
T. M. Tatarnikova
St. Petersburg State University of Aerospace Instrumentation
Russian Federation
Russian Federation
Tatyana M. Tatarnikova — Dr. Sci., Professor; Department of Applied Informatics,
St. Petersburg.
A. A. Shihotov
St. Petersburg State University of Aerospace Instrumentation
Russian Federation
Russian Federation
Aleksey A. Shihotov — M.Sc.; Department of Applied Informatics,
St. Petersburg.
References
1. Krivosheev A.V. Vestnik of Ryazan State Radio Engineering University, 2024, no. 87, pp. 54–61, DOI: 10.21667/1995-4565-2024-87-54-61. (in Russ.)
2. Ferrer M.A., Diaz M., Carmona-Duarte C., Morales A. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, no. 6(39), pp. 1041–1053.
3. Kalko A.I. BIG DATA and Advanced Analytics. BIG DATA i analiz vysokogo urovnya (BIG DATA and Advanced Analytics. BIG DATA and High-Level Analysis), Ninth International Scientific and Practical Conference, Minsk, Republic of Belarus, May 17–18, 2023, рр. 276–284. (in Russ.)
4. Kuchuganov A.V., Lapinskaya G.V. Raspoznavaniye rukopisnykh tekstov (Handwritten Text Recognition), Izhevsk, 2006, 514 р. (in Russ.)
5. Shapiro L., Stockman G. Computer Vision, Prentice Hall, 2001, 617 p.
6. Breusova E.I. Bulletin of the Chelyabinsk State Pedagogical University, 2017, no. 1, pp. 88–92. (in Russ.)
7. Akhundzhanov U.Yu., Starovoytov V.V. System analysis, 2022, no. 2, pp. 4–9, DOI: 10.21122/2309-4923-2022-2-4-9. (in Russ.)
8. OpenCV library, O’Reilly Media Inc, 2008, 6 p.
9. Goritov A.N. Proceedings of the TUSUR University, 2018, no. 4-1(21), pp. 53–58. (in Russ.)
10. Semenov A.N. Science and Education: Scientific Publication of Bauman MSTU, 2014, no. 12, pp. 619–632, DOI: 10.7463/1214.0738733. (in Russ.)
11. Wu B., Wan A., Yue X. and Keutzer K. 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia, 2018, рр. 1887–1893, DOI: 10.1109/ICRA.2018.8462926.
12. Skripnikov A.V., Denisenko V.V., Khitrov E.G., Evteeva K.S., Savchenko I.I. Modern science-intensive technologies, 2021, no. 6-1, pp. 91–95, https://doi.org/10.17513/snt.38703. (in Russ.)
13. Makridakis S., Spiliotis E., Assimakopoulos V. PloS one, 2018, vol. 13, рр. 1–20.
14. Taherdoost H., Sahibuddin S., Jalaliyoon N. Advances in applied and pure mathematics, 2022, vol. 27, рр. 375–382.
15. He K., Zhang X., Ren S. and Sun J. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27–30, 2016, рр. 770–778, DOI: 10.1109/CVPR33180.2016.
16. Tatarnikova T.M., Bimbetov F., Bogdanov P.Yu. Izvestiya SPbGETU LETI, 2021, no. 4, pp. 36–41. (in Russ.)
17. Suprun A., Tatarnikova T., Sikarev I., Shmeleva A. Lecture Notes in Networks and Systems, 2022, vol. 387, рр. 31– 38, DOI: 10.1007/978-3-030-93872-7_3.
Review
For citations:
Tatarnikova T.M., Shihotov A.A. Methods of Preprocessing of Digitized Handwritten Documents. Journal of Instrument Engineering. 2025;68(6):494-499. (In Russ.) https://doi.org/10.17586/0021-3454-2025-68-6-494-499
Views:
20
Email this article 