Paper · 2002

Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne

Émilie Poisson Caillault, Christian Viard-Gaudin, Pierre-Michel Lallican

HAL, 315–324 · Published 21 October 2002

View at the publisherCite this paper

In brief

“Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne” is a 2002 paper by Émilie Poisson Caillault and 2 co-authors, published in HAL. OpenAlex counts 0 citations as of 15 November 2026. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
0
Authors
3

Abstract

In this paper, we study the techniques and coupling of convolutional neural networks for online isolated handwritten character recognition. Three architectures are investigated, a TDNN that processes online features, a SDNN that relies on the offline bitmaps of the character and an hybrid architecture called SDTDNN coupling the dynamic information and the static one. We… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Caillault, É. P., Viard-Gaudin, C., & Lallican, P.-M. (2002). Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne. HAL, 315–324. https://hal.science/hal-04287796

MLA 9

Caillault, Émilie Poisson, et al. “Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne.” HAL, 2002, pp. 315–324. https://hal.science/hal-04287796.

Chicago

Caillault, Émilie Poisson, Christian Viard-Gaudin, and Pierre-Michel Lallican. 2002. “Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne.” HAL: 315–324. https://hal.science/hal-04287796.

Harvard

Caillault, É. P., Viard-Gaudin, C. and Lallican, P.-M. (2002) ‘Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne’, HAL, pp. 315–324. Available at: https://hal.science/hal-04287796.

IEEE

É. P. Caillault, C. Viard-Gaudin, and P.-M. Lallican, “Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne,” HAL, pp. 315–324, 2002.

BibTeX

@article{caillault2002combinaison,
  title     = {{Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne}},
  author    = {Caillault, Émilie Poisson and Viard-Gaudin, Christian and Lallican, Pierre-Michel},
  journal   = {HAL},
  year      = {2002},
  pages     = {315--324},
  url       = {https://hal.science/hal-04287796}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques

  • online handwritten character recognition
  • isolated handwritten characters
  • convolutional neural networks
  • time-delay neural networks
  • SDNN
  • MNIST

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Caillault, É. P., Viard-Gaudin, C., & Lallican, P.-M. (2002). Combinaison de réseaux de neurones à convolution pour la reconnaissance de caractères manuscrits en-ligne. HAL, 315–324. https://hal.science/hal-04287796

How many times has this paper been cited?

0 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Émilie Poisson Caillault, Christian Viard-Gaudin, Pierre-Michel Lallican.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.