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 c416e0c253 Revert "🐛 Use the documented package name for TensorFlow 1.15.x" This reverts commit `739f43e9da`.		5 years ago
.circleci	🐛 CircleCI: Try upgrading pip	5 years ago
.idea	🔧 Add PyCharm project files	5 years ago
ocrd_calamari	🧹 Clean up trailing whitespace	5 years ago
test	✅ Remove broken __main__ handling (stick to pytest)	5 years ago
.coveragerc	✅ Only do the coverage on our code	5 years ago
.gitignore	✅ Fix tests by 1. binarizing and 2. use the GT4HistOCR model	5 years ago
Dockerfile	Dockerfile	5 years ago
LICENSE	Initial commit	7 years ago
Makefile	circle: set locale to a UTF-8 variant so python doesn't fall back to ascii	5 years ago
README-DEV.md	📝 README-DEV: Document installing test requirements	5 years ago
README.md	🧹 Do not advertise and support untested models	5 years ago
ocrd-tool.json	.	7 years ago
requirements-test.txt	✅ Use GT segmentation to test	5 years ago
requirements.txt	Revert "🐛 Use the documented package name for TensorFlow 1.15.x"	5 years ago
setup.py	📦 v0.0.3 – To fix version inconsistency	5 years ago

ocrd_calamari

Recognize text using Calamari OCR.

Introduction

This offers a OCR-D compliant workspace processor for some of the functionality of Calamari OCR.

This processor only operates on the text line level and so needs a line segmentation (and by extension a binarized image) as its input.

pip install ocrd_calamari

pip install .

Download models trained on GT4HistOCR data:

make gt4histocr-calamari
ls gt4histocr-calamari

ocrd-calamari-recognize -p test-parameters.json -m mets.xml -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI

With test-parameters.json:

{
    "checkpoint": "/path/to/some/trained/models/*.ckpt.json"
}

For information regarding development and testing, please see README-DEV.md.