Hybred: An OCR Document Representation for Classification Tasks - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Journal Articles International Journal of Computer Science Issues Year : 2011

Hybred: An OCR Document Representation for Classification Tasks

Abstract

The classification of digital documents is a complex task in a document analysis flow. The amount of documents resulting from the OCR retro-conversion (optical character recognition) makes the classification task harder. In the literature, different features are used to improve the classification quality. In this paper, we evaluate various features on OCRed and non OCRed documents. Thanks to this evaluation, we propose the HYBRED (HYBrid REpresentation of Documents) approach which combines different features in a single relevant representation. The experiments conducted on real data show the interest of this approach.
Fichier principal
Vignette du fichier
IJCSI-8-3-2-1.pdf (115.78 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive
Loading...

Dates and versions

lirmm-00723581 , version 1 (10-08-2012)

Identifiers

  • HAL Id : lirmm-00723581 , version 1

Cite

Sami Laroum, Nicolas Béchet, Hatem Hamza, Mathieu Roche. Hybred: An OCR Document Representation for Classification Tasks. International Journal of Computer Science Issues, 2011, 8 (3), pp.1-8. ⟨lirmm-00723581⟩
342 View
1137 Download

Share

More