Glossary

Dataset
Pages, line regions and correct transcriptions prepared for HTR training. Under development.

Diplomatic transcription
A transcription preserving the source's form and supporting editorial marks.

Entity
A marked person, place, date or other semantic item in a transcription.

HTR
Automatic handwritten text recognition. Vestigia has a provider interface and Kraken integration.

Multimedia item
An image or other file managed in a project's multimedia node.

Normalised transcription
Text adapted for reading or searching, separate from diplomatic transcription. The user defines editorial rules; verify in the application.

Image block
A manuscript page region recorded as image content and available as a crop.

PAGE XML
An exchange format for page layout, lines and text.

Project
A saved workspace containing the module tree, application data and links.

Text block
A page region containing one or more text lines.

View
A workspace view opened in a tab or a separate subwindow.