August 12, 2018 Dataset Open Access

Springmann, Uwe; Reul, Christian; Dipper, Stefanie; Baiter, Johannes

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.1344132</identifier>
  <creators>
    <creator>
      <creatorName>Springmann, Uwe</creatorName>
      <givenName>Uwe</givenName>
      <familyName>Springmann</familyName>
      <affiliation>LMU</affiliation>
    </creator>
    <creator>
      <creatorName>Reul, Christian</creatorName>
      <givenName>Christian</givenName>
      <familyName>Reul</familyName>
      <affiliation>Universität Würzburg</affiliation>
    </creator>
    <creator>
      <creatorName>Dipper, Stefanie</creatorName>
      <givenName>Stefanie</givenName>
      <familyName>Dipper</familyName>
      <affiliation>Ruhr-Universität Bochum</affiliation>
    </creator>
    <creator>
      <creatorName>Baiter, Johannes</creatorName>
      <givenName>Johannes</givenName>
      <familyName>Baiter</familyName>
      <affiliation>Bayerische Staatsbibiliothek München</affiliation>
    </creator>
  </creators>
  <titles>
    <title>GT4HistOCR: Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <subjects>
    <subject>OCR, historical documents, digital humanities, Fraktur, Early Modern Latin, Early New High German</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2018-08-12</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/1344132</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.1344131</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;&lt;strong&gt;GT4HistOCR&lt;/strong&gt; contains ground truth for research in Optical Character Recognition (OCR) technology applied to historical printings in German Fraktur and Early Modern Latin.&lt;/p&gt;

&lt;p&gt;The ground truth comes in pairs of images of single printed lines as they appear in book pages (*.png) and their corresponding diplomatic transcriptions (*.gt.txt), which are UTF-8 strings preserving the character forms (glyphs) as much as possible within the UNICODE standard. These pairs of line images and their transcriptions can be directly used to train recognition models with, e.g., the open source OCR engines &lt;em&gt;OCRopy&lt;/em&gt; or &lt;em&gt;Tesseract&lt;/em&gt;. A total of 313,173 ground truth lines are provided.&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Please note that the subcorpora making up this collection used different transcription guidelines, so it is a bad idea to train a recognition model on the total collection! Rather train individual models for each subcorpus.&lt;/strong&gt; Fur further information about the subcorpora, please see the README file and the accompanying publication.&lt;/p&gt;

&lt;p&gt;If these data are useful for you, please cite the accompanying publication:&lt;/p&gt;

&lt;pre&gt;@article{&lt;a href="http://springmann.net/publications.html#springmann2018gt4hist"&gt;springmann2018gt4hist&lt;/a&gt;,
  author = {Uwe Springmann and Christian Reul and Stefanie Dipper and
		  Johannes Baiter},
  title = {{Ground Truth for training {OCR} engines on historical
		  documents in German Fraktur and Early Modern Latin}},
  journal = {J. Lang. Technol. Comput. Linguistics},
  volume = {33},
  number = {1},
  pages = {97--114},
  year = {2018},
  url = {https://jlcl.org/content/2-allissues/1-heft1-2018/jlcl_2018-1_5.pdf}
}&lt;/pre&gt;</description>
  </descriptions>
</resource>