- 09:00 to 18:00
- Friday 22 November 2024
- Graham Storey Room, Trinity Hall
Workshop Leaders: Dr Rachael Griffiths (EPHE, Paris & Affiliated Researcher at the Faculty of Modern & Medieval Languages & Linguistics) and Dr Marieke Meelen (Theoretical & Applied Linguistics)
This workshop will provide a comprehensive introduction to handwritten text recognition (HTR) with a focus on the Transkribus platform. The workshop will begin with an introduction to the theory behind HTR and best practices for planning and managing HTR workflow, including leveraging existing knowledge and data, ensuring the quality and consistency of training data, and effective data management. Following this, it will cover essential aspects of using Transkribus, its main functions and features, including creating collections of documents, segmenting images, adding metadata, leveraging both existing and custom HTR models, and sharing data. The presented examples will mostly draw on handwritten documents, however the pipeline and steps are also applicable to printed materials.
No previous knowledge of the topic is required, but interest in working with historical/handwritten documents of any kind is useful as participants will have the opportunity for hands-on experience setting up HTR pipelines for their own current or future projects. Sample projects will be provided to participants who don't have access to images of manuscripts.
We invite 25 participants (postgraduate students, postdocs or any other researchers) from any department in Cambridge as well as the University Library and Museums. Participation is free of charge and places will be allocated on a first-come, first-serve basis, operated with a waiting list if necessary. Coffee/tea/lunch as well as a drinks reception for networking are all included since we are aiming to bring together researchers from a variety of backgrounds who are interested in learning and/or collaboration. If there are remaining spaces available, we will open registration to advanced undergraduates and those who collaborate with Cambridge researchers as well.
This workshop is supported by funding from Cambridge Language Sciences.
Interested in joining? Please sign up via our online form: registration is open from 5 October - 5 November. Participants will be notified of confirmed places by 10 November.
For further information, please email Rachael (rachael.griffiths@ephe.psl.eu) or Marieke (mm986@cam.ac.uk).