Program and algorithm for segmentation and recognition of hand-printed characters using convolutional neural networks

E. S. Popova, V. G. Spitsyn, Yu A. Bolotova

Research output: Contribution to conferencePaper

Abstract

The article is devoted to the development of the algorithm for segmentation and recognition of hand-printed symbols on images. A generalized algorithm for the operation of the text recognition system is presented. The paper describes the methods of segmentation of text documents. The application of a neural network approach based on the architecture of convolutional neural networks is proposed to solve the problem of recognizing hand-printed characters. Results of numerical experiments on the recognition of USE forms on the basis of the proposed approach showed a recognition accuracy of 94.1%, which exceeds the recognition accuracy of 82% obtained with the help of ABBYY FineReader.

Original languageEnglish
Pages230-233
Number of pages4
Publication statusPublished - 2018
Event28th International Conference on Computer Graphics and Vision, GraphiCon 2018 - Tomsk, Russian Federation
Duration: 24 Sep 201827 Sep 2018

Conference

Conference28th International Conference on Computer Graphics and Vision, GraphiCon 2018
CountryRussian Federation
CityTomsk
Period24.9.1827.9.18

Keywords

  • Computer vision
  • Convolutional neural networks
  • Pattern recognition
  • Segmentation of text images

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Program and algorithm for segmentation and recognition of hand-printed characters using convolutional neural networks'. Together they form a unique fingerprint.

  • Cite this

    Popova, E. S., Spitsyn, V. G., & Bolotova, Y. A. (2018). Program and algorithm for segmentation and recognition of hand-printed characters using convolutional neural networks. 230-233. Paper presented at 28th International Conference on Computer Graphics and Vision, GraphiCon 2018, Tomsk, Russian Federation.