DOCUMENT IMAGE AND ZONE CLASSIFICATION THROUGH INCREMENTAL LEARNING

Mohamed-Rafik Bouguelia 1 Yolande Belaïd 1 Abdel Belaïd 1
1 READ - Recognition of writing and analysis of documents
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : We present an incremental learning method for document image and zone classification. We consider an industrial context where the system faces a large variability of digitized administrative documents that become available progressively over time. Each new incoming document is segmented into physical regions (zones) which are classified according to a zone-model. We represent the document by means of its classified zones and we classify the document according to a document-model. The classification relies on a reject utility in order to reject ambiguous zones or documents. Models are updated by incrementally learning each new document and its extracted zones. We validate the method on real administrative document images and we achieve a recognition rate of more than 92%.
Type de document :
Communication dans un congrès
International Conference on Image Processing (ICIP), Sep 2013, Melbourne, Australia. IEEE, pp.4230-4234, 2013
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00865765
Contributeur : Yolande Belaid <>
Soumis le : mercredi 25 septembre 2013 - 10:02:43
Dernière modification le : mardi 24 avril 2018 - 13:16:28
Document(s) archivé(s) le : vendredi 7 avril 2017 - 02:33:39

Fichier

ICIP_version_editeur.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00865765, version 1

Collections

Citation

Mohamed-Rafik Bouguelia, Yolande Belaïd, Abdel Belaïd. DOCUMENT IMAGE AND ZONE CLASSIFICATION THROUGH INCREMENTAL LEARNING. International Conference on Image Processing (ICIP), Sep 2013, Melbourne, Australia. IEEE, pp.4230-4234, 2013. 〈hal-00865765〉

Partager

Métriques

Consultations de la notice

427

Téléchargements de fichiers

370