Dataset Open Access

Data set of the paper "Publishing an OCR ground truth data set for reuse in an unclear copyright setting"

David Lassner; Julius Coburger; Clemens Neudecker; Anne Baillot


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.4742068</identifier>
  <creators>
    <creator>
      <creatorName>David Lassner</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-9013-0834</nameIdentifier>
      <affiliation>TU Berlin</affiliation>
    </creator>
    <creator>
      <creatorName>Julius Coburger</creatorName>
      <affiliation>TU Berlin</affiliation>
    </creator>
    <creator>
      <creatorName>Clemens Neudecker</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-5293-8322</nameIdentifier>
      <affiliation>Staatsbibliothek zu Berlin - Preußischer Kulturbesitz</affiliation>
    </creator>
    <creator>
      <creatorName>Anne Baillot</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-4593-059X</nameIdentifier>
      <affiliation>Le Mans Université</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Data set of the paper "Publishing an OCR ground truth data set for reuse in an unclear copyright setting"</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>OCR ground-truth</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2021-05-07</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4742068</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.4742067</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.1</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;The data set consists of a METS file for each of the PDFs that were used for transcription and a directory data/page_xml that contains the transcriptions of the ground truth in PAGE-XML format. In parallel to the data set publication, a data paper will be published that contains a detailed description of the data set. As soon as it is published, we will link to it. The corresponding source code can be found here&amp;nbsp;https://github.com/millawell/ocr-data/tree/1.1&lt;/p&gt;</description>
  </descriptions>
</resource>
35
10
views
downloads
All versions This version
Views 3535
Downloads 1010
Data volume 3.0 MB3.0 MB
Unique views 2828
Unique downloads 77

Share

Cite as