You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Go to file

Gerber, Mike f7b43bbefa ✨ ppn2ocr: Support TIFF in the BEST group		5 years ago
data@dcd3643917	⬆ Update calamari-models URL + path	5 years ago
ocrd-bugs	🐛 ocrd-bugs: Most/All workspaces in bag files don't validate	5 years ago
xsd	Use PAGE 2019	5 years ago
.gitignore	🧹 .gitignore __pychache__/*.pyc	5 years ago
.gitmodules	✨ Run Calamari OCR	5 years ago
.travis.yml	👷 Travis: Hopefully fix deploy on tags	5 years ago
Dockerfile	⁉️ Check dependencies using pipdeptree to triage Travis build fail	5 years ago
README-DEV.md	📝 README-DEV: Fix git push instructions	5 years ago
README.md	📓 README: Reference howto/proxy.md instead of duplicating the proxy settings	5 years ago
build	✅ Travis: Cache Docker builds from previous image	5 years ago
my_ocrd_workflow	✨ Validate before even starting, to find data problems	5 years ago
ocrd_logging.py	🔧 Set up logging level using /etc/ocrd_logging.py instead of "-l"	5 years ago
ppn2ocr	✨ ppn2ocr: Support TIFF in the BEST group	5 years ago
qurator_data_lib.sh	⬆ Update qurator_data_lib.sh to use a silent curl instead of wget	5 years ago
requirements-ppn2ocr.txt	🚧 Add a script that checks FULLTEXT dimensions against BEST dimensions	5 years ago
requirements.txt	🐛 Add tessdata_best Tesseract models again	5 years ago
run	🐛 run: XXX Work around podman vs docker uid behaviour	5 years ago
run-docker-hub	✨ Support --input-file-grp/-I command line parameter	5 years ago
zdb2ocr	🚧 zdb2ocr: Add TODOs from notes.md	5 years ago

README.md

My OCR-D workflow

WIP. Given a OCR-D workspace with document images in the OCR-D-IMG file group, this workflow produces:

Binarized images
Line segmentation
OCR text (using Calamari and Tesseract, both with GT4HistOCR models)
(Given ground truth in OCR-D-GT-PAGE, also an OCR text evaluation report)

If you're interested in the exact processors, versions and parameters, please take a look at the script and possibly the Dockerfile and the requirements.

Goal

Provide a test environment to produce OCR output for historical prints, using OCR-D, especially ocrd_calamari and sbb_textline_detection, including all dependencies in Docker.

How to use

It's easiest to use it as a pre-built container. To run the container on an example workspace:

# Download an example workspace
cd /tmp
wget https://qurator-data.de/examples/actevedef_718448162.first-page.zip
unzip actevedef_718448162.first-page.zip

# Run the workflow on it
cd actevedef_718448162.first-page
~/devel/my_ocrd_workflow/run-docker-hub

Build the container yourself

To build the container yourself using Docker:

cd ~/devel/my_ocrd_workflow
./build

You may then use the script run to use your self-built container, analogous to the example above.

Viewing results

You may then examine the results using PRImA's PAGE Viewer:

java -jar /path/to/JPageViewer.jar --resolve-dir . OCR-D-OCR-CALAMARI/OCR-D-OCR-CALAMARI_00000024.xml

The workflow also produces OCR evaluation reports using dinglehopper, if ground truth was available:

firefox OCR-D-OCR-CALAMARI-EVAL/OCR-D-OCR-CALAMARI-EVAL_00000024.html

ppn2ocr

The ppn2ocr script produces a METS file with the best images for a given document in the State Library Berlin (SBB)'s digitized collection. The document must be specified by its PPN, for example:

pip install -r ~/devel/my_ocrd_workflow/requirements-ppn2ocr.txt
~/devel/my_ocrd_workflow/ppn2ocr PPN77164308X
cd PPN77164308X
~/devel/my_ocrd_workflow/run-docker-hub -I BEST --skip-validation

This produces a workspace directory PPN77164308X with the OCR results in it; the results are viewable as explained above.

ppn2ocr requires a working Docker setup and properly set up environment variables for the proxy configuration. At SBB, this following howto/docker-proxy.md and howto/proxy-settings-for-shell+python.md (in qurator's mono-repo).