Recognition of handwritten digits by image processing and neural network - Université de Bretagne Occidentale
Communication Dans Un Congrès Année : 1992

Recognition of handwritten digits by image processing and neural network

Résumé

Recognition of handwritten digits has been one of the first applications of neural networks. Efficient methods have already been proposed to solve this task. We propose an intermediate approach between classical methods, which are based on extraction of a small set of parameters, and pure neural methods,in which the neural network is fed with raw image data. Complexity and learning time are reduced with still good performances. On a data base of 2589 digits coming from 30 people, we provide experimental results and comparisons of various parameters and classifiers.
Fichier principal
Vignette du fichier
1992_06_ijcnn_chiffres.pdf (351.77 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Copyright (Tous droits réservés)

Dates et versions

hal-03221757 , version 1 (17-03-2023)

Licence

Copyright (Tous droits réservés)

Identifiants

Citer

Gilles Burel, Isabelle Pottier, Jean-Yves Catros. Recognition of handwritten digits by image processing and neural network. IJCNN International Joint Conference on Neural Networks, Jun 1992, Baltimore, United States. pp.666-671, ⟨10.1109/IJCNN.1992.227098⟩. ⟨hal-03221757⟩

Collections

UNIV-BREST
34 Consultations
25 Téléchargements

Altmetric

Partager

More