Implementation Project OCR‑D / Kitodo
Erik Sommer
Image Not Showing
Possible Reasons
The image file may be corrupted The server hosting the image is unavailable The image path is incorrect The image format is not supported
Learn More →
Robert Sachunsky
Image Not Showing
Possible Reasons
The image file may be corrupted The server hosting the image is unavailable The image path is incorrect The image format is not supported
Learn More →
Katya Rykhlinskaya
1st OCR-D III developer workshop, 29 Nov 2021
https://hackmd.io/@bertsky/ocrd-workshop1-kitodo
Status and Planning
Development
Kitodo User Survey
0 Quick Recap
→ We want to bring OCR-D into mass digitization.
Project goals:
scalabe and robust OCR-D Web Service
improved Quality Metrics
integration with Kitodo ( .Production / .Presentation )
aligned to the requirements of the Community
1 Status
Commenced 01 Oct, staged entry of core team members:
Katya Rykhlinskaya (Community Outreach): Oct 2021
Robert Sachunsky (DEV OCR-D): Nov 2021
Sven Marcus (DEV Web Service): ~Dec 2021
Markus Weigelt (DEV Kitodo.Production): ~Jan 2022
H. Sidiropoulos (DEV Kitodo.Presentation): ~mid Jan 2022
1 Planning
First Phase – independent Tiers:
Assess User Requirements
Network Implementation (coordinated)
Scaling + robustness (coordinated)
Quality/Error interfaces, Quality Metrics
Fill technological gaps (GT, OLR, Backlog, New Wrappers)
Second Phase – additional, dependent tiers:
UI for Control and Visualization
Kitodo.Production Module
Kitodo.Presentation Interfaces
Experiments on Workflow Optimization
3 User survey
General data
workshop for Kitodo user community
open survey to understand the needs concerning OCR-D integration
33 detailed questions regarding:
type/quantity/quality of data
technical constraints on software
Kitodo versions/migration and servicing
preferences regarding service model
previous/other OCR experience
preferences regarding workflow and monitoring UI
preferences regarding quality vs. speed
required output formats and interface for manual correction
demand for OCR-on-demand functions
24 participants (so far!)
3 User survey
Preliminary results (example)
questions regarding kind of materials to be digitalized, format and language
→ broad spectrum of materials to process (including newspapers and magazines), fonts and languages
3 User survey
Preliminary results (example)
3 User survey
Summary
survey still active → results not fully analysed yet
information will guide Kitodo/OCR-D design and implementation
everyone welcome to participate
Resume presentation
Implementation Project OCR‑D / Kitodo Erik Sommer Robert Sachunsky Katya Rykhlinskaya 1st OCR-D III developer workshop, 29 Nov 2021 https://hackmd.io/@bertsky/ocrd-workshop1-kitodo
{"metaMigratedAt":"2023-06-16T15:17:34.130Z","metaMigratedFrom":"YAML","title":"Implementation Project OCR-D / Kitodo","breaks":true,"description":"1st OCR-D developer workshop, 29 Nov 2021","slideOptions":"{\"theme\":\"white\",\"slideNumber\":true}","contributors":"[{\"id\":\"76c8705c-2d98-4d35-a8a8-eb9cc1cf5377\",\"add\":936,\"del\":661},{\"id\":\"c62f1b15-791a-47e1-8e4c-ab2ed00c04bc\",\"add\":5309,\"del\":722},{\"id\":\"53b50d9e-fdf9-46cf-94f5-b7bee0fa25a8\",\"add\":4113,\"del\":3312}]"}