Morphological filters for OCR: a performance comparison

Abstract : In this article is compared the ability of several morphological operators to improve OCR performance when used as preprocessing filters. An experiment on binary and greyscale images using the Tesseract OCR engine and morphological filters acting in complex, graph and vertex spaces has thus been performed and results in a good overall performance of complex and area filters. MSE measures have also been performed to evaluate the denoising ability of these filters, which again shows the good performance of both complex and area filters on this aspect.
Liste complète des métadonnées
Contributeur : Laurent Mennillo <>
Soumis le : vendredi 7 décembre 2012 - 15:16:38
Dernière modification le : vendredi 16 septembre 2016 - 15:17:36
Document(s) archivé(s) le : lundi 11 mars 2013 - 11:40:33


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00762631, version 1


Laurent Mennillo, Jean Cousty, Laurent Najman. Morphological filters for OCR: a performance comparison. 2012. <hal-00762631>



Consultations de
la notice


Téléchargements du document