Control Systems and Computers, N1, 2024, Article 5
https://doi.org/10.15407/csc.2024.01.050
Control Systems and Computers, 2024, Issue 1 (305), pp. 50-56
UDC 004.032.26
M.D. SNITKO, Student, National Technical University of Ukraine “Igor Sikorsky Kyiv
Polytechnic Institute”, Peremohy Ave, 37, Kyiv, 03056, Ukraine,
e-mail
IA.V. KHITSKO, PhD, Senior Lecturer, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Peremohy Ave 37, Kyiv, 03056, Ukraine, ORCID: https://orcid.org0000-0002-6455-8498/,
khitsko@pzks.fpm.kpi.ua
N.A. RYBACHOK, PhD, Asoc. Professor, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Peremohy Ave 37, Kyiv, 03056, Ukraine, ORCID: https://orcid.org/0000-0002-8133-1148,
rybachok@pzks.fpm.kpi.ua
RECOGNITION OF HANDWRITTEN TEXTS ON IMAGES USING
DEEP MACHINE LEARNING
The article is devoted to the aspects of using deep machine learning to recognize handwritten text containing letters of the Latin alphabet and numbers. Software has been developed that recognizes handwritten text. A convolutional neural network consisting of 13 layers was trained for 50 epochs on images of 814255 characters taken from the EMNIST dataset. The prediction accuracy was 0.9468, the response rate was 0,9673, the F1-index reached 0,9429, and the average processing time of one image was 1,15 seconds.
Download full text! (On English)
Keywords: neural network, deep machine learning, handwriting recognition, OCR, CNN.
- LeCun, Y., Cortes, C., Burges, C.J.C. “The MNIST Database of Handwritten Digits” [online]. Available at: <http://yann.lecun.com/exdb/mnist/> [Accessed 06 Dec. 2023].
- Digital Image Processing / Rafael C. González; Richard Eugene Woods (ed.). Prentice Hall, 2007, pp. 85, ISBN 978-0-13-168728-8.
- Chauhan, S., Sharma, E., Doegar, A. (2016). “Binarization Techniques for Degraded Document Images. A Review”. 5th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO).
- Krizhevsky, A., Sutskever, I., Hinton, G.E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25 (NIPS 2012), pp. 1097-1105.
- Mouton, C., Myburgh, J.C., & Davel, M.H. (2020). “Stride and Translation Invariance in CNNS”. In Southern African Conference for Artificial Intelligence Research, Vol. 1342, Cham: Springer International Publishing, pp. 267-281.
https://doi.org/10.1007/978-3-030-66151-9_17 - Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Rabinovich, A. (2015). “Going deeper with convolutions”. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1−9.
https://doi.org/10.1109/CVPR.2015.7298594 - Nikitha, A., Geetha, J., JayaLakshmi, D.S. (2020). “Handwritten text recognition using deep learning”. Int. Conf. on Recent Trends on Electronics, Information, Communication & Technology (RTEICT). pp. 388-392.
https://doi.org/10.1109/RTEICT49044.2020.9315679 - Nurseitov, D., Bostanbekov, K., Kanatov, M., Alimova A., Abdallah, A., Abdimanap, G. (2020). “Classification of handwritten names of cities and Handwritten text recognition using various deep learn”. Advances in Science, Technology and Engineering Systems Journal. Vol. 5, No. 2, XX-YY, https://doi.org/10.25046/aj0505114
- Khitsko, Ya.V., Snitko, M.D. (2023). “Sposib ta prohramne zabezpechennya dlya rozpiznavannya tekstu na zobrazhennyakh”. Zbirnyk tez XVI konferentsiyi molodykh vchenykh «Prykladna matematyka ta komp’yutynh», Kyiv, pp. 627−631 (In Ukrainian).
- Powers, D.M.W. (2011). “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation”. Journal of Machine Learning Technologies, 2 (1), pp. 37-63.
- Manokhyn, A.V., Rybachok, N.A. (2021). “English Accent Recognition Using Deep Machine Learning”. Control Systems and Computers. № 4. pp. 52−59. https://doi.org/10.15407/csc.2021.04.028
Received 15.02.2024
