OCR-D command line tools

Use virtualenv to install dependencies:

• virutalenv -p python3 env-dir
• source env-dir/bin/activate
• pip install -e path/to/dir/containing/setup.py

• Create a new (empty) workspace: ocrd workspace init workspace-dir
• cd into workspace-dir
• Add new file to workspace: ocrd workspace add file -G group -i id -m mimetype

The alignment tool line-aligns multiple file groups. It can be used to align the results of multiple OCRs with their respective ground-truth.

The tool expects a comma-separated list of input file groups, the according output file group and the url of the configuration file:

ocrd-cis-align \
  --input-file-grp 'ocr1,ocr2,gt' \
  --ouput-file-grp 'ocr1 ocr2 gt' \
  --parameter file:///path/to/config.json

• OCR-D
• Github
• Project-page
• Ground-truth