https://github.com/dhlab-epfl/dhSegment

Generic framework for historical document processing
https://github.com/dhlab-epfl/dhSegment

document-processing historical-data python3 segmentation tensorflow

Last synced: 3 months ago
JSON representation

Generic framework for historical document processing

• Host: GitHub
• URL: https://github.com/dhlab-epfl/dhSegment
• Owner: dhlab-epfl
• License: gpl-3.0
• Created: 2017-07-13T14:08:24.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2021-07-09T16:14:24.000Z (almost 3 years ago)
• Last Synced: 2024-01-16T02:48:10.583Z (5 months ago)
• Topics: document-processing, historical-data, python3, segmentation, tensorflow
• Language: Python
• Homepage: https://dhlab-epfl.github.com/dhSegment
• Size: 5.89 MB
• Stars: 360
• Watchers: 29
• Forks: 114
• Open Issues: 13
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-digitization - GitHub src
• awesome-ocr - dhlab-epfl/dhSegment - Generic framework for historical document processing (11. <a name='OpticalCharacterRecognitionEnginesandFrameworks'></a>Optical Character Recognition Engines and Frameworks / 8.1. <a name='GroundTruth'></a>Ground Truth)
• awesome-historical-newspaper-analysis - dhSegment
• awesome-ocr - dhlab-epfl/dhSegment - Generic framework for historical document processing (Optical Character Recognition Engines and Frameworks / CTPN [paper:2016](https://arxiv.org/pdf/1609.03605.pdf))

README

        
# dhSegment

[![Documentation Status](https://readthedocs.org/projects/dhsegment/badge/?version=latest)](https://dhsegment.readthedocs.io/en/latest/?badge=latest)

**dhSegment** is a tool for Historical Document Processing. Its generic approach allows to segment regions and

extract content from different type of documents. See 

[some examples here](https://dhsegment.readthedocs.io/en/latest/intro/intro.html#use-cases).

The complete description of the system can be found in the corresponding [paper](https://arxiv.org/abs/1804.10371).

It was created by [Benoit Seguin](https://twitter.com/Seguin_Be) and Sofia Ares Oliveira at DHLAB, EPFL.

## Installation and usage

The [installation procedure](https://dhsegment.readthedocs.io/en/latest/start/install.html) 

and examples of usage can be found in the documentation (see section below).

## Demo

Have a try at the [demo](https://dhsegment.readthedocs.io/en/latest/start/demo.html) to train (optional) and apply dhSegment in page extraction using the `demo.py` script.

## Documentation

The documentation is available on [readthedocs](https://dhsegment.readthedocs.io/).

##

If you are using this code for your research, you can cite the corresponding paper as :

```

@inproceedings{oliveiraseguinkaplan2018dhsegment,

  title={dhSegment: A generic deep-learning approach for document segmentation},

  author={Ares Oliveira, Sofia and Seguin, Benoit and Kaplan, Frederic},

  booktitle={Frontiers in Handwriting Recognition (ICFHR), 2018 16th International Conference on},

  pages={7--12},

  year={2018},

  organization={IEEE}

}

```