https://github.com/mittagessen/kraken

OCR engine for all the languages
https://github.com/mittagessen/kraken

alto-xml handwritten-text-recognition hocr htr layout-analysis neural-networks ocr optical-character-recognition page-xml

Last synced: about 2 months ago
JSON representation

OCR engine for all the languages

• Host: GitHub
• URL: https://github.com/mittagessen/kraken
• Owner: mittagessen
• License: apache-2.0
• Created: 2015-05-19T09:24:38.000Z (almost 10 years ago)
• Default Branch: main
• Last Pushed: 2024-10-21T10:26:04.000Z (7 months ago)
• Last Synced: 2024-10-21T15:10:44.440Z (7 months ago)
• Topics: alto-xml, handwritten-text-recognition, hocr, htr, layout-analysis, neural-networks, ocr, optical-character-recognition, page-xml
• Language: Python
• Homepage: http://kraken.re
• Size: 28.9 MB
• Stars: 734
• Watchers: 27
• Forks: 130
• Open Issues: 28
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE
  • Citation: CITATION.cff

Awesome Lists containing this project

• awesome-ocr - kraken - Ocropus fork with sane defaults (Software / OCR engines)

README

        
Description

===========

.. image:: https://github.com/mittagessen/kraken/actions/workflows/test.yml/badge.svg

    :target: https://github.com/mittagessen/kraken/actions/workflows/test.yml

kraken is a turn-key OCR system optimized for historical and non-Latin script

material.

kraken's main features are:

  - Fully trainable layout analysis, reading order, and character recognition

  - `Right-to-Left `_, `BiDi

    `_, and Top-to-Bottom

    script support

  - `ALTO `_, PageXML, abbyyXML, and hOCR

    output

  - Word bounding boxes and character cuts

  - Multi-script recognition support

  - `Public repository `_ of model files

  - Variable recognition network architecture

Installation

============

kraken only runs on **Linux or Mac OS X**. Windows is not supported.

The latest stable releases can be installed from `PyPi `_:

::

  $ pip install kraken

If you want direct PDF and multi-image TIFF/JPEG2000 support it is necessary to

install the `pdf` extras package for PyPi:

::

  $ pip install kraken[pdf]

or install `pyvips` manually with pip:

::

  $ pip install pyvips

Conda environment files are provided for the seamless installation of the main

branch as well:

::

  $ git clone https://github.com/mittagessen/kraken.git

  $ cd kraken

  $ conda env create -f environment.yml

or:

::

  $ git clone https://github.com/mittagessen/kraken.git

  $ cd kraken

  $ conda env create -f environment_cuda.yml

for CUDA acceleration with the appropriate hardware.

Finally you'll have to scrounge up a model to do the actual recognition of

characters. To download the default model for printed French text and place it

in the kraken directory for the current user:

::

  $ kraken get 10.5281/zenodo.10592716

A list of libre models available in the central repository can be retrieved by

running:

::

  $ kraken list

Quickstart

==========

Recognizing text on an image using the default parameters including the

prerequisite steps of binarization and page segmentation:

::

  $ kraken -i image.tif image.txt binarize segment ocr

To binarize a single image using the nlbin algorithm:

::

  $ kraken -i image.tif bw.png binarize

To segment an image (binarized or not) with the new baseline segmenter:

::

  $ kraken -i image.tif lines.json segment -bl

To segment and OCR an image using the default model(s):

::

  $ kraken -i image.tif image.txt segment -bl ocr -m catmus-print-fondue-large.mlmodel

All subcommands and options are documented. Use the ``help`` option to get more

information.

Documentation

=============

Have a look at the `docs `_.

Related Software

================

These days kraken is quite closely linked to the `eScriptorium

`_ project developed in the same eScripta research

group. eScriptorium provides a user-friendly interface for annotating data,

training models, and inference (but also much more). There is a `gitter channel

`_ that is mostly intended for

coordinating technical development but is also a spot to find people with

experience on applying kraken on a wide variety of material.

Funding

=======

kraken is developed at the `École Pratique des Hautes Études `_, `Université PSL `_.

.. container:: twocol

   .. container::

        .. image:: https://raw.githubusercontent.com/mittagessen/kraken/main/docs/_static/normal-reproduction-low-resolution.jpg

          :width: 100

          :alt: Co-financed by the European Union

   .. container::

        This project was funded in part by the European Union. (ERC, MiDRASH,

        project number 101071829).

.. container:: twocol

   .. container::

        .. image:: https://raw.githubusercontent.com/mittagessen/kraken/main/docs/_static/normal-reproduction-low-resolution.jpg

          :width: 100

          :alt: Co-financed by the European Union

   .. container::

        This project was partially funded through the RESILIENCE project, funded from

        the European Union’s Horizon 2020 Framework Programme for Research and

        Innovation.

.. container:: twocol

   .. container::

      .. image:: https://projet.biblissima.fr/sites/default/files/2021-11/biblissima-baseline-sombre-ia.png

         :width: 400

         :alt: Received funding from the Programme d’investissements d’Avenir

   .. container::

        Ce travail a bénéficié d’une aide de l’État gérée par l’Agence Nationale de la

        Recherche au titre du Programme d’Investissements d’Avenir portant la référence

        ANR-21-ESRE-0005 (Biblissima+).