2019-10-10 16:13:07 +02:00
|
|
|
# Textline-Recognition
|
|
|
|
|
|
2019-12-06 00:47:53 +01:00
|
|
|
## Introduction
|
|
|
|
|
This tool performs textline detection from document image data and returns the results as PAGE-XML.
|
2019-10-10 16:13:07 +02:00
|
|
|
|
2019-12-06 00:47:53 +01:00
|
|
|
## Installation
|
2019-12-05 16:30:09 +01:00
|
|
|
|
2019-12-06 00:48:38 +01:00
|
|
|
`pip install .`
|
2019-12-05 16:06:55 +01:00
|
|
|
|
2019-12-06 00:47:53 +01:00
|
|
|
## Models
|
|
|
|
|
In order to run this tool you also need trained models. You can download our pre-trained models from here:
|
2019-12-05 22:06:44 +01:00
|
|
|
https://file.spk-berlin.de:8443/textline_detection/
|
2019-10-10 16:13:07 +02:00
|
|
|
|
2019-12-06 00:47:53 +01:00
|
|
|
## Usage
|
2019-10-10 16:13:07 +02:00
|
|
|
|
2019-12-05 22:06:44 +01:00
|
|
|
`sbb_textline_detector -i <image file name> -o <directory to write output xml> -m <directory of models>`
|
2019-12-05 16:15:07 +01:00
|
|
|
|
2019-12-06 11:42:23 +01:00
|
|
|
## Usage with OCR-D
|
2019-12-06 20:03:51 +01:00
|
|
|
|
2019-12-06 11:42:23 +01:00
|
|
|
~~~
|
|
|
|
|
ocrd-example-binarize -I OCR-D-IMG -O OCR-D-IMG-BIN
|
2019-12-06 12:34:15 +01:00
|
|
|
ocrd_sbb_textline_detector -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE-SBB \
|
|
|
|
|
-p '{ "model": "/path/to/the/models/textline_detection" }'
|
2019-12-06 11:42:23 +01:00
|
|
|
~~~
|
|
|
|
|
|
|
|
|
|
Segmentation works on raw RGB images, but respects and retains
|
|
|
|
|
`AlternativeImage`s 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
|
2019-12-06 20:03:51 +01:00
|
|
|
replace the original raw RGB image.
|
