- home
- Advanced Search
Filters
Clear All- DARIAH EU
- 2017-2021
- Open Access
- Publications
- Research data
- HAL-ENS-LYON
- DARIAH EU
- DARIAH EU
- 2017-2021
- Open Access
- Publications
- Research data
- HAL-ENS-LYON
- DARIAH EU
Loading
description Publicationkeyboard_double_arrow_right Article , Data Paper 2021 France GermanPublisher:Zeitschrift für digitale Geisteswissenschaften - ZfdG Authors: Lassner, David; Coburger, Julius; Neudecker, Clemens; Baillot, Anne;Lassner, David; Coburger, Julius; Neudecker, Clemens; Baillot, Anne;doi: 10.17175/sb005_006
In dieser Arbeit stellen wir einen OCR-Trainingsdatensatz für historische Drucke vor und zeigen, wie sich im Vergleich zu unspezifischen Modellen die Erkennungsgenauigkeit verbessert, wenn sie mithilfe dieser Daten weitertrainiert werden. Wir erörtern die Nachnutzbarkeit dieses Datensatzes anhand von zwei Experimenten, die die rechtliche Grundlage zur Veröffentlichung digitalisierter Bilddateien am Beispiel von deutschen und englischen Büchern des 19. Jahrhunderts betrachten. Wir präsentieren ein Framework, mit dem OCR-Trainingsdatensätze veröffentlicht werden können, auch wenn die Bilddateien nicht zur Wiederveröffentlichung freigegeben sind. We present an OCR ground truth data set for historical prints and show improvement of recognition results over baselines with training on this data. We reflect on reusability of the ground truth data set based on two experiments that look into the legal basis for reuse of digitized document images in the case of 19th century English and German books. We propose a framework for publishing ground truth data even when digitized document images cannot be easily redistributed. Fabrikation von Erkenntnis – Experimente in den Digital Humanities. Hg. von Manuel Burghardt, Lisa Dieckmann, Timo Steyer, Peer Trilcke, Niels Walkowski, Joëlle Weis, Ulrike Wuttke. Wolfenbüttel 2021—2022. (= Zeitschrift für digitale Geisteswissenschaften / Sonderbände, 5)
Zeitschrift für digi... arrow_drop_down HAL-ENS-LYONArticle . 2021License: CC BYFull-Text: https://hal.science/hal-03482671/documentData sources: HAL-ENS-LYONadd ClaimPlease grant OpenAIRE to access and update your ORCID works.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.All Research productsarrow_drop_down <script type="text/javascript"> <!-- document.write('<div id="oa_widget"></div>'); document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=10.17175/sb005_006&type=result"></script>'); --> </script>
For further information contact us at helpdesk@openaire.eu0 citations 0 popularity Average influence Average impulse Average Powered by BIP!more_vert Zeitschrift für digi... arrow_drop_down HAL-ENS-LYONArticle . 2021License: CC BYFull-Text: https://hal.science/hal-03482671/documentData sources: HAL-ENS-LYONadd ClaimPlease grant OpenAIRE to access and update your ORCID works.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.All Research productsarrow_drop_down <script type="text/javascript"> <!-- document.write('<div id="oa_widget"></div>'); document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=10.17175/sb005_006&type=result"></script>'); --> </script>
For further information contact us at helpdesk@openaire.eu
Loading
description Publicationkeyboard_double_arrow_right Article , Data Paper 2021 France GermanPublisher:Zeitschrift für digitale Geisteswissenschaften - ZfdG Authors: Lassner, David; Coburger, Julius; Neudecker, Clemens; Baillot, Anne;Lassner, David; Coburger, Julius; Neudecker, Clemens; Baillot, Anne;doi: 10.17175/sb005_006
In dieser Arbeit stellen wir einen OCR-Trainingsdatensatz für historische Drucke vor und zeigen, wie sich im Vergleich zu unspezifischen Modellen die Erkennungsgenauigkeit verbessert, wenn sie mithilfe dieser Daten weitertrainiert werden. Wir erörtern die Nachnutzbarkeit dieses Datensatzes anhand von zwei Experimenten, die die rechtliche Grundlage zur Veröffentlichung digitalisierter Bilddateien am Beispiel von deutschen und englischen Büchern des 19. Jahrhunderts betrachten. Wir präsentieren ein Framework, mit dem OCR-Trainingsdatensätze veröffentlicht werden können, auch wenn die Bilddateien nicht zur Wiederveröffentlichung freigegeben sind. We present an OCR ground truth data set for historical prints and show improvement of recognition results over baselines with training on this data. We reflect on reusability of the ground truth data set based on two experiments that look into the legal basis for reuse of digitized document images in the case of 19th century English and German books. We propose a framework for publishing ground truth data even when digitized document images cannot be easily redistributed. Fabrikation von Erkenntnis – Experimente in den Digital Humanities. Hg. von Manuel Burghardt, Lisa Dieckmann, Timo Steyer, Peer Trilcke, Niels Walkowski, Joëlle Weis, Ulrike Wuttke. Wolfenbüttel 2021—2022. (= Zeitschrift für digitale Geisteswissenschaften / Sonderbände, 5)
Zeitschrift für digi... arrow_drop_down HAL-ENS-LYONArticle . 2021License: CC BYFull-Text: https://hal.science/hal-03482671/documentData sources: HAL-ENS-LYONadd ClaimPlease grant OpenAIRE to access and update your ORCID works.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.All Research productsarrow_drop_down <script type="text/javascript"> <!-- document.write('<div id="oa_widget"></div>'); document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=10.17175/sb005_006&type=result"></script>'); --> </script>
For further information contact us at helpdesk@openaire.eu0 citations 0 popularity Average influence Average impulse Average Powered by BIP!more_vert Zeitschrift für digi... arrow_drop_down HAL-ENS-LYONArticle . 2021License: CC BYFull-Text: https://hal.science/hal-03482671/documentData sources: HAL-ENS-LYONadd ClaimPlease grant OpenAIRE to access and update your ORCID works.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.All Research productsarrow_drop_down <script type="text/javascript"> <!-- document.write('<div id="oa_widget"></div>'); document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=10.17175/sb005_006&type=result"></script>'); --> </script>
For further information contact us at helpdesk@openaire.eu