A Dockerized test environment for OCR-D processors 🚢
WIP. Given a OCR-D workspace with document images in the OCR-D-IMG file group, the example 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 individual Dockerfiles.
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
ocrd-galley uses Docker to run the OCR-D images. We provide pre-built container images that get downloaded automatically when you run the provided wrappers for the OCR-D processors.
You can then install the wrappers into a Python venv:
cd ~/devel/ocrd-galley/wrapper pip install .
To download models, you need to use the
-a flag of
ocrd resmgr download -a ocrd-calamari-recognize default
You may then use the script
my_ocrd_workflow to use your self-built
containers 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/ocrd-galley/my_ocrd_workflow
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 example workflow also produces OCR evaluation reports using dinglehopper, if ground truth was available:
ppn2ocr script produces a workspace and METS file with the best images for
a given document in the Berlin State Library (SBB)'s digitized collection.
Install it with an up-to-date pip (otherwise this will fail due to a opencv-python-headless build failure):
pip install -r ~/devel/ocrd-galley/requirements-ppn2ocr.txt
The document must be specified by its PPN, for example:
~/devel/ocrd-galley/ppn2ocr PPN77164308X cd PPN77164308X ~/devel/ocrd-galley/my_ocrd_workflow -I MAX --skip-validation
This produces a workspace directory
PPN77164308X with the OCR results in it;
the results are viewable as explained above.
ppn2ocr requires properly set up environment variables for the proxy
configuration. At SBB, please read
howto/proxy-settings-for-shell+python.md (in qurator's mono-repo).
ocrd-workspace-from-images script produces a OCR-D workspace (incl. METS)
for the given images.
~/devel/ocrd-galley/ocrd-workspace-from-images 0005.png cd workspace-xxxxx # output by the last command ~/devel/ocrd-galley/my_ocrd_workflow
This produces a workspace from the files and then runs the OCR workflow on it.
Build the containers yourself
To build the containers yourself using Docker:
cd ~/devel/ocrd-galley/ ./build