Character Rotation Absorption Using a Dynamic Neural Network Topology: Comparison With Invariant Features

Christophe Choisy 1 Hubert Cecotti 1 Abdel Belaïd 1
1 READ - READ
LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper treats on rotation absorption in neural networks for multi-oriented character recognition. Classical approaches are based on several rotation invariant features. Here, we propose to use a dynamic neural network topology to absorb the rotation phenomenon. The basic idea is to preserve as most as possible the graphical information, that contains all the information. The proposal is to dynamically modify the neural network architecture, in order to take into account the rotation variation of the analysed pattern.We use too a specific topology that carry out a polar transformation inside the network. The interest of such a transformation is to transform the rotation problem from a problem to a problem, that is easier to treat. These proposals are applied on a synthetic and on a real EDF1 base of multi-oriented characters. A comparison is made with Fourier and Fourier-Mellin invariants.
Mots-clés : reconnaissance de caractères invariant extraction character recognition neural network dynamic topology réseaux de neurones topologie dynamique recherche d'invariants
Type de document :
Communication dans un congrès
6th International Conference on Enterprise Information Systems - ICEIS'2004, Jun 2004, Porto, Portugal, 8 p, 2004
Liste complète des métadonnées
https://hal.inria.fr/inria-00099934
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 10:11:28
Dernière modification le : mardi 24 avril 2018 - 13:34:54
Document(s) archivé(s) le : mercredi 29 mars 2017 - 13:02:58

Fichiers

A04-R-508.pdf

Identifiants

  • HAL Id : inria-00099934, version 1

Collections

INRIA | LORIA | UNIV-LORRAINE

Citation

Christophe Choisy, Hubert Cecotti, Abdel Belaïd. Character Rotation Absorption Using a Dynamic Neural Network Topology: Comparison With Invariant Features. 6th International Conference on Enterprise Information Systems - ICEIS'2004, Jun 2004, Porto, Portugal, 8 p, 2004. 〈inria-00099934〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

136

Téléchargements de fichiers

37

Contact


archive-ouverte@inria.fr