Dawsonia

Digitize hAndWritten obServatiONs In weather journAls

Dawsonia is a young project aimed at data-rescue of weather journals. It specializes in digitization of hand-written numeric data in the form of tables. We aim to use a combination of

• image processing

• machine learning

to achieve this. The digitization pipeline is implemented in Python, using well-known open-source scientific libraries.

Contents

• User guide
  • Input data and neural network models
  • Configuration
  • Command line parameters
  • Table formats
  • Command-line interface
• API Reference
  • dawsonia
• Wishlist
  • Table detection and OCR for printed tables without lines
  • Extend training dataset
  • Alternative models for OCR and HTR
  • Dashboard for ML training: MLops
  • Dashboard for digitizing, verification and correction
  • Hyperparameter tuning
  • Pipeline for flagging failed digitizations
  • Deskewing images

Indices and tables

• Index

• Module Index

• Search Page