eScriptorium

<h2 id="details">Details</h2>

The software is an <a href="/facts/Open_source/7X9rCdz4">open source</a> software developed at the <a href="/facts/Paris_Sciences_et_Lettres_University/RU5csCTS">Paris Sciences et Lettres University</a> as part of the projects Scripta<a class="footnote-ref" id="fnref:1" href="#fn:1">1</a> and RESILIENCE<a class="footnote-ref" id="fnref:2" href="#fn:2">2</a> with contributions from other institutions, partly funded by the EU's <a href="/facts/Horizon_2020/Udy5lUQ7">Horizon 2020</a> funding program and a grant from the <a href="/facts/Andrew_W._Mellon_Foundation/HvCLbQXq">Andrew W. Mellon Foundation</a>.
Scanned pages from manuscripts and prints can be imported into eScriptorium and exported as text in various formats (text, <a href="/facts/Analyzed_Layout_and_Text_Object/2fX7Pb0n">ALTO</a> or <a href="/facts/Page_Analysis_and_Ground_Truth_Elements/ASsBrJ0l">PAGE XML</a>, <a href="/facts/Text_Encoding_Initiative/fWz7YYv9">TEI</a>). The text areas with text lines in the images are first recognized manually or automatically (segmentation). The text lines are then transcribed manually or automatically.<a class="footnote-ref" id="fnref:3" href="#fn:3">3</a>
Both automatic segmentation and text recognition can be trained using manually created or corrected examples (<a href="/facts/Ground_truth/KNNr8X1G">ground truth</a>). The new models created in this way can be shared with others and can therefore be easily reused.<a class="footnote-ref" id="fnref:4" href="#fn:4">4</a>
eScriptorium is built on top of the <a href="/facts/Free_software/IaoVtJXn">free</a> OCR software Kraken by Benjamin Kiessling, a derivative of the OCR software <a href="/facts/OCRopus/ovqXb2gW">OCRopus</a>, which is suitable for handwritten and printed texts and also supports scripts such as Hebrew and Arabic, which are written from right to left.<a class="footnote-ref" id="fnref:5" href="#fn:5">5</a>
Comparable programs that offer similar functions to eScriptorium are OCR4All<a class="footnote-ref" id="fnref:6" href="#fn:6">6</a> and <a href="/facts/Transkribus/Goce2ApU">Transkribus</a>.

<h2 id="individual-references">Individual references</h2>

<h2 id="external-links">External links</h2>

Wikimedia Commons has media related to eScriptorium.

<h2 id="references">References</h2>

<ol>
<li id="fn:1">"Scripta-PSL. History and practices of writing". Retrieved 2022-03-13. <a href="https://www.psl.eu/en/scripta" target="_blank">https://www.psl.eu/en/scripta</a> <a href="#fnref:1" class="footnote-back-ref">↩</a></li>
<li id="fn:2">"RESILIENCE - The Religious Studies Research Infrastructure". Retrieved 2022-03-13. <a href="https://www.resilience-ri.eu/" target="_blank">https://www.resilience-ri.eu/</a> <a href="#fnref:2" class="footnote-back-ref">↩</a></li>
<li id="fn:3">"eScriptorium Documentation". Retrieved 2024-01-21. <a href="https://escriptorium.readthedocs.io/en/latest/" target="_blank">https://escriptorium.readthedocs.io/en/latest/</a> <a href="#fnref:3" class="footnote-back-ref">↩</a></li>
<li id="fn:4">"Export data - eScriptorium Documentation". Retrieved 2024-01-21. <a href="https://escriptorium.readthedocs.io/en/latest/export/" target="_blank">https://escriptorium.readthedocs.io/en/latest/export/</a> <a href="#fnref:4" class="footnote-back-ref">↩</a></li>
<li id="fn:5">"lunch/kraken: OCR engine for all the languages". Retrieved 2022-03-13. <a href="https://github.com/mittagessen/kraken/" target="_blank">https://github.com/mittagessen/kraken/</a> <a href="#fnref:5" class="footnote-back-ref">↩</a></li>
<li id="fn:6">"OCR4all | forTEXT". Retrieved 2023-06-20. <a href="https://fortext.net/tools/tools/ocr4all" target="_blank">https://fortext.net/tools/tools/ocr4all</a> <a href="#fnref:6" class="footnote-back-ref">↩</a></li>
</ol>

eScriptorium open-in-new

eScriptorium