{{Short description|Software for analysis of historical documents}} {{Infobox software | title = Transkribus | logo = | logo caption = | logo alt = | logo upright = | logo size = | screenshot = Transkribus.jpg | screenshot alt = screenshot showing an old, hand-written document and the OCR-transcribed version | caption = | other_names = | author = | developer = READ-COOP | released = <!-- {{Start date and age|YYYY|MM|DD|df=yes/no}} --> | ver layout = <!-- simple (default) or stacked --> | discontinued = <!-- Set to yes, if software is discontinued, otherwise omit. --> | latest release version = | latest release date = <!-- {{Start date and age|YYYY|MM|DD|df=yes/no}} --> | latest preview version = | latest preview date = <!-- {{Start date and age|YYYY|MM|DD|df=yes/no}} --> | repo = <!-- {{URL|example.org}} --> | qid = | programming language = | middleware = | engine = <!-- or |engines= --> | operating system = | platform = | included with = | replaces = | replaced_by = | service_name = | size = | standard = | language = | language count = <!-- Number only --> | language footnote = | genre = | license = <!-- or |licence= --> | website = {{official URL}} | AsOf = }}
'''Transkribus''' is a platform for the text recognition, image analysis and structure recognition of historical documents.
The platform was created in the context of the two EU projects "tranScriptorium" (2013–2015)<ref>{{cite web |url=http://transkriptorium.com/ |title= TranSkriptorium |website=transkriptorium.com |access-date=24 February 2022}}{{title missing|date=May 2022}}</ref> and "READ" (Recognition and Enrichment of Archival Documents – 2016–2019).<ref>{{cite web |url=https://cordis.europa.eu/project/id/674943 |title=tranScriptorium Project Page |website=cordis.europa.eu |access-date=1 February 2020}}{{title missing|date=May 2022}}</ref> It was developed by the University of Innsbruck. Since July 1, 2019 the platform has been directed and further developed by the READ-COOP, a non-profit cooperative.<ref>{{cite web |url=https://readcoop.eu/ |title= Read-Coop |website=readcoop.eu |access-date=1 February 2020}}{{title missing|date=May 2022}}</ref>
The platform integrates tools developed by research groups throughout Europe, including the ''Pattern Recognition and Human Language Technology'' (PRHLT) group of the Technical University of Valencia and the Computational Intelligence Technology Lab (CITlab) group of University of Rostock.
Comparable programs that offer similar functions are eScriptorium and OCR4All.<ref>{{Cite web |url=https://fortext.net/tools/tools/ocr4all |title=OCR4all {{!}} forTEXT |access-date=2023-06-20}}</ref>
==References== <references />
==Further reading== * {{Cite journal|last=Polomac|first=Vladimir R.|title=Serbian Early Printed Books from Venice: Creating Models for Automatic Text Recognition using Transkribus|journal=Scripta & e-Script|year=2022|volume=22|pages=11–29|url=https://www.academia.edu/85293509}}
==External links== * {{Official website}} * [https://readcoop.eu/ READ-COOP] * [https://transkribus.eu/wikiDe/index.php/Hauptseite Deutschsprachige Benutzeranleitung für die Transkribus-Plattform] * [https://github.com/Transkribus/ Github Repository] * Marc Rothballer: [https://archivalia.hypotheses.org/124394 ''Transkribus – Erfahrungsbericht zu maschinellem Lernen und Handwritten Text Recognition in der Heimat- und Familienforschung''], Besprechung der Software vom 26. Juni 2020 im Archivalia-Blog
Category:Optical character recognition Category:Handwriting recognition Category:Machine learning task