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
Clemens Neudecker fbe2f2302f
Merge pull request #104 from bertsky/reinstate-namespace-pkg
Revert "Merge pull request #97 from qurator-spk/420-namespace-package"
10 hours ago
.circleci Merge branch 'main' into eynollah_light 1 month ago
.github/workflows re-enable Action for Python 3.8 4 weeks ago
qurator Revert "Merge pull request #97 from qurator-spk/420-namespace-package" 11 hours ago
tests allow passing PIL image to Eynollah w/o disk I/O 2 years ago
.gitignore 📦 v0.0.3 2 years ago Update 4 weeks ago
LICENSE extend, add Makefile, gitignore, requirements.txt 3 years ago
Makefile use the SavedModel format 2 months ago improve links to GT guidelines 4 weeks ago
ocrd-tool.json OCR-D CLI 2 years ago
requirements-test.txt 🎨 reformat with black 3 years ago
requirements.txt Update requirements.txt 2 months ago Revert "Merge pull request #97 from qurator-spk/420-namespace-package" 11 hours ago


Document Layout Analysis (segmentation) using pre-trained models and heuristics

PyPI Version CircleCI Build Status GH Actions Test License: ASL


  • Support for up to 10 segmentation classes:
  • Support for various image optimization operations:
    • cropping (border detection), binarization, deskewing, dewarping, scaling, enhancing, resizing
  • Text line segmentation to bounding boxes or polygons (contours) including for curved lines and vertical text
  • Detection of reading order
  • Output in PAGE-XML
  • OCR-D interface


Python versions 3.7-3.10 with Tensorflow >=2.4 are currently supported.

For (limited) GPU support the matching CUDA toolkit >=10.1 needs to be installed.

You can either install via

pip install eynollah

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

git clone
cd eynollah; pip install -e .

Alternatively, you can run make install or make install-dev for editable installation.


Pre-trained models can be downloaded from

In case you want to train your own model to use with Eynollah, have a look at sbb_pixelwise_segmentation.


The command-line interface can be called like this:

eynollah \
  -i <image file> \
  -o <output directory> \
  -m <path to directory containing model files> \

The following options can be used to further configure the processing:

option description
-fl full layout analysis including all steps and segmentation classes
-light lighter and faster but simpler method for main region detection and deskewing
-tab apply table detection
-ae apply enhancement (the resulting image is saved to the output directory)
-as apply scaling
-cl apply countour detection for curved text lines instead of bounding boxes
-ib apply binarization (the resulting image is saved to the output directory)
-ep enable plotting (MUST always be used with -sl, -sd, -sa, -si or -ae)
-ho ignore headers for reading order dectection
-di <directory> process all images in a directory in batch mode
-si <directory> save image regions detected to this directory
-sd <directory> save deskewed image to this directory
-sl <directory> save layout prediction as plot to this directory
-sp <directory> save cropped page image to this directory
-sa <directory> save all (plot, enhanced/binary image, layout) to this directory

If no option is set, the tool will perform layout detection of main regions (background, text, images, separators and marginals). The tool produces better quality output when RGB images are used as input than greyscale or binarized images.

Use as OCR-D processor

Eynollah ships with a CLI interface to be used as OCR-D processor.

In this case, the source image file group with (preferably) RGB images should be used as input like this:

ocrd-eynollah-segment -I OCR-D-IMG -O SEG-LINE -P models

Any image referenced by @imageFilename in PAGE-XML is passed on directly to Eynollah as a processor, so that e.g.

ocrd-eynollah-segment -I OCR-D-IMG-BIN -O SEG-LINE -P models

uses the original (RGB) image despite any binarization that may have occured in previous OCR-D processing steps