Использование нейронных сетей для распознавания графических образов

Authors

  • Н. И. Безменов
  • С. В. Коваленко
  • М. А. Ткачев

DOI:

https://doi.org/10.20998/%25x

Abstract

Предлагается использовать нейронные сети на основе базисно радиальных функций в качестве метода для распознавания графических образов. Продемонстрирована работоспособность сети на примере распознавания цифр.

Author Biographies

Н. И. Безменов

канд. техн. наук, профессор НТУ "ХПИ"

С. В. Коваленко

старший преподаватель НТУ "ХПИ"

М. А. Ткачев

магистрант НТУ "ХПИ"

References

Ватолин Д.С. Алгоритмы сжатия изображений. – МГУ, 2002. – С. 30- 32.

Micchelli С.А. "Interpolation of scattered data: Distance matrices and conditionally positive definite functions" // Constructive Approximation, 1986, vоl. 2, р. 11-22.

Powell M.J.D. "Radial basis functions for multivariable interpolation: А review" // IMA Conference оn Algorithms for the Approximation of Functions and Data, 1985, р. 143-167, RМCS, Shrivenham, England.

Downloads

Published

2009-12-25

How to Cite

Безменов, Н. И., Коваленко, С. В., & Ткачев, М. А. (2009). Использование нейронных сетей для распознавания графических образов. Bulletin of National Technical University "KhPI". Series: System Analysis, Control and Information Technologies, (9), 126–130. https://doi.org/10.20998/%x

Issue

No. 9 (2010)

Section

SYSTEM ANALYSIS AND DECISION-MAKING THEORY

License

Copyright (c) 2015 Вестник Национального технического университета "ХПИ". Серия: Системный анализ, управление и информационные технологии

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).