This project is work in progress.
The repository contains data used to train Kraken text recognition and segmentation models for medieval Greek minuscule manuscripts within the framework of eScriptorium.
Currently, the repository contains these folders and files:
- README.md: This file
- MssList.md: List of manuscripts which have already been segmented and annotated
- TranscriptionRules.md: Rules applied in transcription
- SegmentationRules.md: Rules for the segmentation
- eScriptorium_helpers
- Greek manuscripts.json: Virtual keyboard for special characters used in transcription
- ontology_escriptorium_grc.json: Ontology for segmentation (adapting SegmOnto)