Handwritten Text Recognition and Keyword Spotting

Provided by:
Research area:
Dedicated for:
Research group, Researchers, Research organisations
(0.0 /5) 0 reviews

| Transkribus is a platform for the digitisation, transcription, recognition and searching of historical documents. Transkribus enables users to train specific neural networks on their documents not only for printed, but also for handwritten documents. Transkribus offers a number of tools for the automated processing of documents, such as: a) Handwritten Text Recognition (HTR), b) Layout Analysis, c) Document Understanding, d) Keyword Spotting, e) Optical Character Recognition (OCR) using ABBYY Finereader Engine 11. All documents in Transkribus are private and not shared publicly.  |

Standard Historical documents are recognized and made searchable. Allows scholars to transcribe documents in a highly standardized, flexible and reliable way and get support from automated tools such as Handwritten Text Recognition and Layout Analysis. Allows archivists to involve humanities scholars and volunteers in repository building. Allows scientists in the fields of computer vision, document analysis, pattern recognition, natural language, etc. to access reference data in a well-acknowledged format. 300+ data providers (researchers, scholars, archives, libraries), 20.000+ registered users

Places and languages
  • World
  • English
Service Availability
Service phase
  • Production
  • 1.6.
Last Update
  • 20.09.2020

The EOSC portal is been jointly developed and maintained by the EOSC-hub, eInfraCentral and OpenAIRE-Advance projects funded by the European

Union’s Horizon 2020 research and innovation programme with contribution of the European Commission

2018 EOSC Portal