Character Rotation Absorption Using a Dynamic Neural Network Topology: Comparison With Invariant Features - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

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

Christophe Choisy
  • Function : Author
  • PersonId : 836386
Hubert Cecotti
  • Function : Author
  • PersonId : 830534
Abdel Belaïd
  • Function : Author
  • PersonId : 830137

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.
Fichier principal
Vignette du fichier
A04-R-508.pdf (323.5 Ko) Télécharger le fichier

Dates and versions

inria-00099934 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00099934 , version 1

Cite

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. ⟨inria-00099934⟩
78 View
65 Download

Share

Gmail Facebook Twitter LinkedIn More