Form Analysis by Neural Classification of Cells - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 1998

Form Analysis by Neural Classification of Cells

Yolande Belaïd
Jean Luc Panchèvre
  • Function : Author
Abdel Belaïd
  • Function : Author

Abstract

Our aim in this paper is to present a methodology for linearly combining multi neural classifier for cell analysis of forms. Features used for the classification are relative to the text orientation and to its character morphology. Eight classes are extracted among numeric, alphabetic, vertical, horizontal, capitals, etc. Classifiers are multi-layered perceptrons considering firstly global features and refining the classification at each step by looking for more precise features. The recognition rate of the classifiers for 3. 500 cells issued from 19 forms is about 91 %.
Fichier principal
Vignette du fichier
article_das_1998_version_auteur.pdf (186.73 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00098513 , version 1 (27-02-2007)

Identifiers

  • HAL Id : inria-00098513 , version 1

Cite

Yolande Belaïd, Jean Luc Panchèvre, Abdel Belaïd. Form Analysis by Neural Classification of Cells. Third IAPR Workshop on Document Analysis Systems, Y. Nakano, 1998, Nagano, Japan. ⟨inria-00098513⟩
65 View
71 Download

Share

Gmail Facebook Twitter LinkedIn More