A Comparison of Some Morphological Filters for Improving OCR Performance
International audience 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...
Main Authors: | , , |
---|---|
Other Authors: | , , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2015
|
Subjects: | |
Online Access: | https://hal.science/hal-01168641 https://hal.science/hal-01168641/document https://hal.science/hal-01168641/file/Report.pdf https://doi.org/10.1007/978-3-319-18720-4_12 |
id |
ftecoleponts:oai:HAL:hal-01168641v1 |
---|---|
record_format |
openpolar |
spelling |
ftecoleponts:oai:HAL:hal-01168641v1 2024-06-09T07:47:10+00:00 A Comparison of Some Morphological Filters for Improving OCR Performance Mennillo, Laurent Cousty, Jean Najman, Laurent Institut Pascal (IP) SIGMA Clermont (SIGMA Clermont)-Université Clermont Auvergne 2017-2020 (UCA 2017-2020 )-Centre National de la Recherche Scientifique (CNRS) Laboratoire d'Informatique Gaspard-Monge (LIGM) École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel Benediktsson, J.A. Chanussot, J. Najman, L. Talbot, H. Reykjavik, Iceland 2015-05-27 https://hal.science/hal-01168641 https://hal.science/hal-01168641/document https://hal.science/hal-01168641/file/Report.pdf https://doi.org/10.1007/978-3-319-18720-4_12 en eng HAL CCSD info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-18720-4_12 hal-01168641 https://hal.science/hal-01168641 https://hal.science/hal-01168641/document https://hal.science/hal-01168641/file/Report.pdf doi:10.1007/978-3-319-18720-4_12 info:eu-repo/semantics/OpenAccess Mathematical Morphology and Its Applications to Signal and Image Processing https://hal.science/hal-01168641 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⟩ https://link-springer-com.extranet.enpc.fr/chapter/10.1007/978-3-319-18720-4_12 Character recognition Morphological filtering Vertex Graphs Simplicial complexes [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing info:eu-repo/semantics/conferenceObject Conference papers 2015 ftecoleponts https://doi.org/10.1007/978-3-319-18720-4_12 2024-05-16T13:30:26Z International audience 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. Conference Object Iceland École des Ponts ParisTech: HAL 134 145 |
institution |
Open Polar |
collection |
École des Ponts ParisTech: HAL |
op_collection_id |
ftecoleponts |
language |
English |
topic |
Character recognition Morphological filtering Vertex Graphs Simplicial complexes [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing |
spellingShingle |
Character recognition Morphological filtering Vertex Graphs Simplicial complexes [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing Mennillo, Laurent Cousty, Jean Najman, Laurent A Comparison of Some Morphological Filters for Improving OCR Performance |
topic_facet |
Character recognition Morphological filtering Vertex Graphs Simplicial complexes [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing |
description |
International audience 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. |
author2 |
Institut Pascal (IP) SIGMA Clermont (SIGMA Clermont)-Université Clermont Auvergne 2017-2020 (UCA 2017-2020 )-Centre National de la Recherche Scientifique (CNRS) Laboratoire d'Informatique Gaspard-Monge (LIGM) École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel Benediktsson, J.A. Chanussot, J. Najman, L. Talbot, H. |
format |
Conference Object |
author |
Mennillo, Laurent Cousty, Jean Najman, Laurent |
author_facet |
Mennillo, Laurent Cousty, Jean Najman, Laurent |
author_sort |
Mennillo, Laurent |
title |
A Comparison of Some Morphological Filters for Improving OCR Performance |
title_short |
A Comparison of Some Morphological Filters for Improving OCR Performance |
title_full |
A Comparison of Some Morphological Filters for Improving OCR Performance |
title_fullStr |
A Comparison of Some Morphological Filters for Improving OCR Performance |
title_full_unstemmed |
A Comparison of Some Morphological Filters for Improving OCR Performance |
title_sort |
comparison of some morphological filters for improving ocr performance |
publisher |
HAL CCSD |
publishDate |
2015 |
url |
https://hal.science/hal-01168641 https://hal.science/hal-01168641/document https://hal.science/hal-01168641/file/Report.pdf https://doi.org/10.1007/978-3-319-18720-4_12 |
op_coverage |
Reykjavik, Iceland |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
Mathematical Morphology and Its Applications to Signal and Image Processing https://hal.science/hal-01168641 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⟩ https://link-springer-com.extranet.enpc.fr/chapter/10.1007/978-3-319-18720-4_12 |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-18720-4_12 hal-01168641 https://hal.science/hal-01168641 https://hal.science/hal-01168641/document https://hal.science/hal-01168641/file/Report.pdf doi:10.1007/978-3-319-18720-4_12 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1007/978-3-319-18720-4_12 |
container_start_page |
134 |
op_container_end_page |
145 |
_version_ |
1801378100065337344 |