A Comparison of Some Morphological Filters for Improving OCR Performance

Abstract : Studying discrete space representations has recently lead to the development of novel morphological operators. To date, there has been no study evaluating the performances of those novel operators with respect to a specific application. This article compares the capability of several morphological operators, both old and new, to improve OCR performance when used as preprocessing filters. We design an experiment using the Tesseract OCR engine on binary images degraded with a realistic document-dedicated noise model. We assess the performances of some morphological filters acting in complex, graph and vertex spaces, including the area filters. This experiment reveals the good overall performance of complex and graph filters. MSE measures have also been performed to evaluate the denoising capability of these filters, which again confirms the performances of both complex and graph filtering on this aspect.
Liste complète des métadonnées

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01168641
Contributor : Laurent Najman <>
Submitted on : Friday, June 26, 2015 - 11:59:40 AM
Last modification on : Sunday, December 2, 2018 - 4:00:03 PM
Document(s) archivé(s) le : Friday, October 9, 2015 - 6:20:48 PM

File

Report.pdf
Files produced by the author(s)

Identifiers

Citation

Laurent Mennillo, Jean Cousty, Laurent Najman. A Comparison of Some Morphological Filters for Improving OCR Performance. Mathematical Morphology and Its Applications to Signal and Image Processing, Benediktsson, J.A.; Chanussot, J.; Najman, L.; Talbot, H., May 2015, Reykjavik, Iceland. ⟨10.1007/978-3-319-18720-4_12⟩. ⟨hal-01168641⟩

Share

Metrics

Record views

423

Files downloads

341