qurator-spk
/
sbb_textline_detection
mirror of https://github.com/qurator-spk/sbb_textline_detection.git
1
0
Fork 0
Code Issues Releases Wiki Activity
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.
97 Commits
3 Branches
0 Tags
409 KiB
Python 99.8%
Dockerfile 0.2%
 
 
master
resolve-resources
h5py3
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '3941f2f17d'
${ noResults }
Go to file
b-vr103 3941f2f17d gettin robust and doing sth for verticals 5 years ago
qurator gettin robust and doing sth for verticals 5 years ago
.gitignore Revert "Merge branch 'master' of https://github.com/qurator-spk/sbb_textline_detector" 5 years ago
.gitkeep Update config_params.json 5 years ago
Dockerfile Update config_params.json 5 years ago
LICENSE Revert "Merge branch 'master' of https://github.com/qurator-spk/sbb_textline_detector" 5 years ago
README.md 📝 sbb_textline_detection: Document that this also does printspace and region detection 5 years ago
ocrd-tool.json Update config_params.json 5 years ago
requirements.txt Revert "Merge branch 'master' of https://github.com/qurator-spk/sbb_textline_detector" 5 years ago
setup.py Revert "Merge branch 'master' of https://github.com/qurator-spk/sbb_textline_detector" 5 years ago

README.md

Textline Detection

Introduction

This tool performs printspace, region and textline detection from document image data and returns the results as PAGE-XML.

Installation

pip install .

Models

In order to run this tool you also need trained models. You can download our pre-trained models from here:
https://file.spk-berlin.de:8443/textline_detection/

Usage

sbb_textline_detector -i <image file name> -o <directory to write output xml> -m <directory of models>

Usage with OCR-D

ocrd-example-binarize -I OCR-D-IMG -O OCR-D-IMG-BIN
ocrd-sbb-textline-detector -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE-SBB \
        -p '{ "model": "/path/to/the/models/textline_detection" }'

Segmentation works on raw RGB images, but respects and retains AlternativeImages from binarization steps, so it's a good idea to do binarization first, then perform the textline detection. The used binarization processor must produce an AlternativeImage for the binarized image, not replace the original raw RGB image.