Training and evaluation of the models for isolated character recognition

Szilárd Vajda 1
1 READ - READ
LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : In this report we describe a special multi-layer perceptron wich was trained on the image database in order to obtain the classification of the test database. We used the same database to train for each class an SVM and after that we used a normalization process in order to be able to compare the different results given by the SVMs on the test database, as they are not n-class classifiers. As the results obtained were not enough satisfactory for our industrial partner, we proposed a combination scheme, in order to interact the different decisions given by the different classifiers and to obtain a high recognition score.
Type de document :
Rapport
[Contract] A02-R-481 || vajda02b, 2002
Liste complète des métadonnées

https://hal.inria.fr/inria-00107623
Contributeur : Publications Loria <>
Soumis le : jeudi 19 octobre 2006 - 09:03:16
Dernière modification le : mardi 24 avril 2018 - 13:36:26
Document(s) archivé(s) le : vendredi 25 novembre 2016 - 13:05:55

Identifiants

  • HAL Id : inria-00107623, version 1

Collections

Citation

Szilárd Vajda. Training and evaluation of the models for isolated character recognition. [Contract] A02-R-481 || vajda02b, 2002. 〈inria-00107623〉

Partager

Métriques

Consultations de la notice

105

Téléchargements de fichiers

39