greekhtr

Greek (grc) Handwritten Text Recognition

https://github.com/patristictextarchive/greekhtr

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 3 DOI reference(s) in README
  • Academic publication links
    Links to: zenodo.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (5.4%) to scientific vocabulary

Keywords

escriptorium grc ground-truth htr
Last synced: 6 months ago · JSON representation ·

Repository

Greek (grc) Handwritten Text Recognition

Basic Info
  • Host: GitHub
  • Owner: PatristicTextArchive
  • Default Branch: main
  • Homepage:
  • Size: 9.77 KB
Statistics
  • Stars: 3
  • Watchers: 4
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
escriptorium grc ground-truth htr
Created about 2 years ago · Last pushed 8 months ago
Metadata Files
Readme Citation

README.md

Handwritten Text Recognition for Greek (grc)

[!TIP] A preview of a recognition model for 9th-12th century minuscule manuscripts (not trained on microfilm images) is published here: DOI.

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.

All images were collected using the IIIF-Services provided by the respective library (copyright may be claimed by the respective library, cf. the linked IIIF manifests in MssList.md). The original transcriptions were taken from Vatican Library Greek Paleography (VAT in MssList.md) and from the Patristic Text Archive. All transcriptions were manually corrected and amended by Annette von Stockhausen.

Currently, the repository contains these folders and files:

Owner

  • Name: Patristic Text Archive
  • Login: PatristicTextArchive
  • Kind: organization
  • Email: annette.von_stockhausen@bbaw.de
  • Location: Berlin

Open access digital archive of ancient Christian texts

Citation (CITATION.cff)

cff-version: 1.2.0
title: >-
  Handwritten Text Recognition for Greek (grc)
message: >-
  If you use this dataset, please cite it using the
  metadata from this file.
type: dataset
authors:
  - given-names: Annette
    name-particle: von
    family-names: Stockhausen
    email: annette.von_stockhausen@bbaw.de
    affiliation: >-
      Berlin-Brandenburgische Akademie der
      Wissenschaften
    orcid: 'https://orcid.org/0000-0001-5382-6322'
license: CC-BY

GitHub Events

Total
  • Watch event: 1
  • Push event: 2
Last Year
  • Watch event: 1
  • Push event: 2