Solving the handwriting recognition problem using convolutional neural networks

Natalya A. Ivanova; Olesya V. Kubanskikh; Vera A. Bednage; Natalya M. Makhinaа; Olga V. Karbanovich

doi:10.1117/12.2669089

5 January 2023 Solving the handwriting recognition problem using convolutional neural networks

Natalya A. Ivanova, Olesya V. Kubanskikh, Vera A. Bednage, Natalya M. Makhinaа, Olga V. Karbanovich

Proceedings Volume 12564, 2nd International Conference on Computer Applications for Management and Sustainable Development of Production and Industry (CMSD-II-2022); 1256409 (2023) https://doi.org/10.1117/12.2669089
Event: Computer Applications for Management and Sustainable Development of Production and Industry (CMSD2022), 2022, Dushanbe, Tajikistan

Abstract

The article proposes a solution to the problem of handwriting recognition using the capabilities of convolutional neural networks. The architecture of the created ConvNet is described. The main stages of the neural network design process are listed. The created neural network allows to recognize the numbers and letters of the Russian and English alphabets received at the input using various input devices (mouse, graphics tablet, touchpad, etc.). This algorithm can be applied to the analysis of handwriting calligraphy and its correction. Examples of the use in practice of a digital tool created by the authors are given.

Citation Download Citation

Natalya A. Ivanova, Olesya V. Kubanskikh, Vera A. Bednage, Natalya M. Makhinaа, and Olga V. Karbanovich "Solving the handwriting recognition problem using convolutional neural networks", Proc. SPIE 12564, 2nd International Conference on Computer Applications for Management and Sustainable Development of Production and Industry (CMSD-II-2022), 1256409 (5 January 2023); https://doi.org/10.1117/12.2669089

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available