No description
Find a file
2020-02-21 13:22:06 +01:00
data@dcd3643917 ⬆ Update calamari-models URL + path 2020-01-16 15:46:43 +01:00
ocrd-bugs 🐛 ocrd-bugs: Most/All workspaces in bag files don't validate 2019-10-09 13:36:54 +02:00
xsd Use PAGE 2019 2019-08-02 11:59:16 +02:00
.gitmodules Run Calamari OCR 2019-08-21 11:54:01 +02:00
.travis.yml 🎨 Nudge build+download towards the standard qurator_data_lib.sh 2020-02-10 19:23:17 +01:00
build 🎨 Nudge build+download towards the standard qurator_data_lib.sh 2020-02-10 19:23:17 +01:00
Dockerfile 🧹 Remove half-ass GPU support to fix Travis build 2020-02-10 17:04:12 +01:00
my_ocrd_workflow Include glyph output 2020-02-13 16:13:24 +01:00
ocrd_logging.py 🔧 Set up logging level using /etc/ocrd_logging.py instead of "-l" 2020-02-07 17:51:53 +01:00
qurator_data_lib.sh ⬆ Update qurator_data_lib.sh (Fixes GH-5) 2020-02-13 19:02:57 +01:00
README.md 📝 README: Include example workspace + reference PAGE Viewer and dinglehopper 2020-02-21 13:22:06 +01:00
requirements.txt ⬆ Update ocrd_tesserocr to fix glyph bug (OCR-D/ocrd_tesserocr#112) 2020-02-17 18:52:44 +01:00
run 🎨 Improve structure and documentation of run 2020-02-11 15:51:56 +01:00

My OCR-D workflow

Build Status

WIP.

It's easiest to use it as a container. To build the container using Docker:

cd ~/devel/my_ocrd_workflow
./build

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

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 in a OCR-D-GT-PAGE file group:

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