• Blog
  • Project news
• About OCR‑D
  • Learn more about OCR‑D
• Community
  • Communication channels and participation
• Projects
  • Information about our implementation and module projects in phase III
• Reference Data
  • Ground Truth corpus and special corpora
• Contact
  • Contact us!
• GitHub | Gitter | Twitter

Implementation projects

• Integration of Kitodo and OCR‑D for productive mass digitisation
• OPERANDI: OCR‑D Performance Optimisation and Integration
• OCR4all libraries – full text recognition of historical collections
• ODEM: OCR‑D extension for mass digitization

Module projects

• Workflow for work-specific training based on generic models with OCR‑D and ground truth enhancement
• Font Group Recognition for Improved OCR
• OLA-HD Service - A Generic Service for Long-Term Archiving of Historical Prints

• Setup Guide
  • How to setup/install the OCR‑D stack
• User Guide
  • Instructions how to use OCR‑D components
• Workflows
  • Steps of an OCR‑D-workflow with sample workflows
• Models
  • Overview of models for different OCR-engines
• Glossary
  • Glossary of technical terms used in OCR‑D

• OCR‑D Specifications
  • OCR‑D Specifications for CLI, METS, PAGE etc.
• OCR‑D/core API documentation
  • Python API documentation of core implementation
• OCR‑D development best practices
  • Practical information on distributed development of software and specifications in OCR‑D
• Ground Truth Guidelines
  • Guidelines for Ground Truth
• PAGE-XML format documentation
  • Documentation for the PAGE-XML format

Frequently Asked Questions

Search our Website

• For this feature, we implemented Google Custom Search. If you use it, please note that cookies may be stored and Privacy Policy by Google LLC applies: https://policies.google.com/privacy