sbb_binarization

Document Image Binarization using pre-trained models

Examples

Python versions 3.7-3.10 are currently supported.

You can either install via

pip install sbb-binarization

or clone the repository, enter it and install (editable) with

git clone git@github.com:qurator-spk/sbb_binarization.git
cd sbb_binarization; pip install -e .

Pre-trained models can be downloaded from the locations below. We also provide the models and model card on 🤗

Version	Format	Download
2021-03-09	`SavedModel`	https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2021_03_09.zip
2021-03-09	`HDF5`	https://qurator-data.de/sbb_binarization/2021-03-09/models.tar.gz
2020-01-16	`SavedModel`	https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2020_01_16.zip
2020-01-16	`HDF5`	https://qurator-data.de/sbb_binarization/2020-01-16/models.tar.gz

With OCR-D, you can use the Resource Manager to deploy models, e.g.

ocrd resmgr download ocrd-sbb-binarize "*"

sbb_binarize \
  -m <path to directory containing model files> \
  <input image> \
  <output image>

Note: the output image MUST use either .tif or .png as file extension to produce a binary image. Input images can also be JPEG.

Images containing a lot of border noise (black pixels) should be cropped beforehand to improve the quality of results.

sbb_binarize -m /path/to/model/ myimage.tif myimage-bin.tif

To use the OCR-D interface:

ocrd-sbb-binarize -I INPUT_FILE_GRP -O OCR-D-IMG-BIN -P model default

For simple smoke tests, the following will

download models
download test data
run the OCR-D wrapper (on page and region level):
```
  make models
  make test
```