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 e1f57b2638 🐛 Open our test result with UTF-8 encoding (for Python 3.6?)		5 years ago
.circleci	✅ Use Ubuntu 18.04 LTS again (19.04 is EOL 2020-01)	5 years ago
ocrd_calamari	smoke test, circle ci	5 years ago
test	🐛 Open our test result with UTF-8 encoding (for Python 3.6?)	5 years ago
.coveragerc	✅ Only do the coverage on our code	5 years ago
.gitignore	smoke test, circle ci	5 years ago
Dockerfile	Dockerfile	5 years ago
LICENSE	Initial commit	6 years ago
Makefile	🐛 Fix checking out calamari_models	5 years ago
README-DEV.md	📝 Add README-DEV.md with info how to release	5 years ago
README.md	📦 v0.0.1	5 years ago
ocrd-tool.json	.	6 years ago
requirements-test.txt	✅ Use GT segmentation to test	5 years ago
requirements.txt	🐛 Further tighten dependencies to a known good configuration	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.

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"
}

Support Calamari's "extended prediction data" output
Currently, the processor only supports a prediction using confidence voting of multiple models. While this is superior, it makes sense to support single model prediction, too.