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 ebf0d53640 🚧 Do not hardcode used models		5 years ago
ocrd_calamari	🚧 Do not hardcode used models	5 years ago
.gitignore	.	6 years ago
LICENSE	Initial commit	6 years ago
Makefile	.	6 years ago
README.md	🚧 Do not hardcode used models	5 years ago
ocrd-tool.json	.	6 years ago
requirements.txt	🚧 Update to ocrd >= 1.0.0b11	5 years ago
setup.py	🚧 s/Ocr/Recognize	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"
}