Boosting bonsai trees for handwritten/printed text discrimination

Yann Ricquebourg 1 Christian Raymond 2 Baptiste Poirriez 1 Aurélie Lemaitre 1 Bertrand Coüasnon 1
1 IntuiDoc - intuitive user interaction for document
IRISA-D6 - MEDIA ET INTERACTIONS
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Boosting over decision-stumps proved its e ciency in Natural Language Processing essentially with symbolic features, and its good properties (fast, few and not critical parameters, not sensitive to overfitting) could be of great interest in the numeric world of pixel images. In this article we investigated the use of boosting over small decision trees, in image classification processing, for the discrimination of handwritten/printed text. Then, we conducted experiments to compare it to usual SVM-based classification revealing convincing results with very close performance, but with faster predictions and behaving far less as a black-box. Those promising results tend to make use of this classifier in more complex recognition tasks like multiclass problems.
Type de document :
Communication dans un congrès
Document Recognition and Retrieval (DRR), Feb 2014, San Francisco, United States. 2014
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00910718
Contributeur : Christian Raymond <>
Soumis le : jeudi 28 novembre 2013 - 10:37:21
Dernière modification le : mercredi 16 mai 2018 - 11:23:35
Document(s) archivé(s) le : lundi 3 mars 2014 - 17:20:40

Fichier

drr2014.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00910718, version 1

Citation

Yann Ricquebourg, Christian Raymond, Baptiste Poirriez, Aurélie Lemaitre, Bertrand Coüasnon. Boosting bonsai trees for handwritten/printed text discrimination. Document Recognition and Retrieval (DRR), Feb 2014, San Francisco, United States. 2014. 〈hal-00910718〉

Partager

Métriques

Consultations de la notice

620

Téléchargements de fichiers

358