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.
dinglehopper/README.md

50 lines
1.1 KiB
Markdown

dinglehopper
============
dinglehopper is an OCR evaluation tool and reads [ALTO](https://github.com/altoxml), [PAGE](https://github.com/PRImA-Research-Lab/PAGE-XML) and text files.
[![Build Status](https://travis-ci.org/qurator-spk/dinglehopper.svg?branch=master)](https://travis-ci.org/qurator-spk/dinglehopper)
Goals
-----
* Useful
* As a UI tool
* For an automated evaluation
* As a library
* Unicode support
Installation
------------
It's best to use pip, e.g.:
~~~
sudo pip install .
~~~
Usage
-----
~~~
dinglehopper some-document.gt.page.xml some-document.ocr.alto.xml
~~~
This generates `report.html` and `report.json`.
As a OCR-D processor:
~~~
ocrd-dinglehopper -m mets.xml -I OCR-D-GT-PAGE,OCR-D-OCR-TESS -O OCR-D-OCR-TESS-EVAL
~~~
This generates HTML and JSON reports in the `OCR-D-OCR-TESS-EVAL` filegroup.
![dinglehopper displaying metrics and character differences](.screenshots/dinglehopper.png?raw=true)
Testing
-------
Use `pytest` to run the tests in [the tests directory](qurator/dinglehopper/tests):
~~~
virtualenv -p /usr/bin/python3 venv
. venv/bin/activate
pip install -r requirements.txt
pip install pytest
pytest
~~~