Recognition of handwritten digits by image processing and neural network - Université de Bretagne Occidentale
Conference Papers Year : 1992

Recognition of handwritten digits by image processing and neural network

Abstract

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
Origin Files produced by the author(s)
Licence
Copyright

Dates and versions

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

Licence

Copyright

Identifiers

Cite

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 View
23 Download

Altmetric

Share

More