Other Open Access

OCR models for Occitan (standard spelling)

Marianne Vergez-Couret

Citation Style Language JSON Export

  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.2533877", 
  "title": "OCR models for Occitan (standard spelling)", 
  "issued": {
    "date-parts": [
  "abstract": "<p>This dataset provides trained Tesseract (<a href=\"https://github.com/tesseract-ocr/tesseract\">https://github.com/tesseract-ocr/tesseract</a>) and Jochre (<a href=\"https://github.com/urieli/jochre\">https://github.com/urieli/jochre</a>) OCR models for Occitan ( for the standard spelling and two dialects, Gascon and Lengadocian). These models were developed in the context of the RESTAURE project, funded by the French ANR.&nbsp;</p>\n\n<p>Two models are provided. They were presented in the following article <a href=\"http://hal.archives-ouvertes.fr/hal-01252241\">https://hal.archives-ouvertes.fr/hal-01252241</a> and also re-evaluated for the creation of another corpus in <a href=\"https://www.openscience.fr/Constitution-et-annotation-d-un-corpus-ecrit-de-contes-et-recits-en-occitan\">https://www.openscience.fr/Constitution-et-annotation-d-un-corpus-ecrit-de-contes-et-recits-en-occitan</a>.</p>\n\n<p>The first model for Jochre, JOCHRE_2015, has been trained for Jochre 1.1.2b. The training images and corresponding texts were manually annotated using a Jochre online platform (excerpts from 7 different printed works, totalling about 20,000 words)</p>\n\n<p>The second model for Tesseract, TESS_2015, was trained using the jTessBoxEditor tool (<a href=\"http://vietocr.sourceforge.net/training.html\">http://vietocr.sourceforge.net/training.html</a>), Version 1.4 (2 May 2015), based on images automatically generated from the training texts (the one used for Jochre). The generation of the images used a 36pt font size, and two fonts were used (Arial and Times New Roman), with their normal and italic variants. The Tesseract model can be used with Tesseract 3.0x.</p>\n\n<p>List of words was also used for those two trainings. We conflated Occitan words found in several lexicons, dictionaries and corpora for the two dialects, Gascon and Lengadocian:</p>\n\n<ul>\n\t<li>Lexicon extracted from 60 literary works (from 29 different authors) gathered in the BaTel&Ograve;c project.</li>\n\t<li>Dictonary entries from <em>Dictionnaire Fran&ccedil;ais/Occitan Gascon Toulousain</em> de Nicolau Rei B&egrave;thv&eacute;der, 2004, IEO Edicions</li>\n\t<li>Dictonary entries from <em>Dictionnaire Fran&ccedil;ais/Occitan</em> de Cristian Laus, 2004, IEO/IDECO</li>\n\t<li>Dictonary entries from <em>Dictionnaire Fran&ccedil;ais/Occitan (Gascon)</em> de Miqu&egrave;u Grosclaude, Gilab&egrave;rt Nari&ograve;o e Patric Guilhemjoan, 2007, Per Noste Edicions</li>\n\t<li>Conjugated forms from Verb&rsquo;&Ograve;c (designed by the <em>Congr&egrave;s permanent de la lenga occitana</em> (<a href=\"http://www.locongres.org\">http://www.locongres.org</a>))</li>\n\t<li>List of proper nouns extracted from the Apertium (free/open-source machine translation platform) Occitan lexicon.</li>\n</ul>\n\n<p>The jochre model can be used with the Jochre software (<a href=\"https://github.com/urieli/jochre\">https://github.com/urieli/jochre</a>). See also Jochre wiki (https://github.com/urieli/jochre/wiki).</p>\n\n<p>The Tesseract models can be used&nbsp; for instance using the gImageReader tool (<a href=\"https://github.com/manisandro/gImageReader\">https://github.com/manisandro/gImageReader</a>), which provides a graphical user interface for the Tesseract tool.&nbsp;</p>\n\n<p>When evaluated against the same test corpus (four extracts from four different authors from two dialects, Gascon and Lengadocian), the Jochre model achieves better performance levels.</p>\n\n<p>&nbsp;</p>", 
  "author": [
      "family": "Marianne Vergez-Couret"
  "version": "1", 
  "type": "article", 
  "id": "2533877"
All versions This version
Views 145145
Downloads 2221
Data volume 90.5 MB85.4 MB
Unique views 136136
Unique downloads 2019


Cite as