+ New article on automated transcription and search of seventeenth-century document

The Pattern Recognition and Human Language Technology research group at the Universitat Politècnica de València (one of the READ project partners) have published an article exploring their work processing seventeenth-century botanical documents in the latest issue of Digital Scholarship in the Humanities.

The article explains how the team applied techniques of layout analysis, text line detection and automated transcription to a handwritten book by the Spanish botanist Bernardo de Cienfuegos.

The 1000 page work is now fully transcribed and searchable.  In addition to this impressive result, the article also points that the experiment has generated useful feedback on the interaction between human transcribers and Automated Text Recognition technology.

  • Alejandro H Toselli, Luis A Leiva, Isabel Bordes-Cabrera, Celio Hernández-Tornero, Vicent Bosch, Enrique Vidal, ‘Transcribing a 17th-century botanical manuscript: Longitudinal evaluation of document layout detection and interactive transcription’, Digital Scholarship in the Humanities, 33, 1, April 2018, 173-202 https://doi.org/10.1093/llc/fqw064
SHARE THIS ARTICLE

Recent Posts

June 20, 2022
Transkribus
By Joe Nockels, University of Edinburgh As part of his PhD research at the University of Edinburgh and National Library ...
June 15, 2022
Transkribus, Webinars
We are excited to launch our new “Ask Us Anything” webinar series, where attendees can ask us about anything related ...
June 9, 2022
Uncategorized
The new sharing feature It might be a small button for a screen, but it is a great function for ...