This repository is a concise collection of well known deep learning based document binarization models. The various models and the links to the original repositories are as shown below:
| Model | Link |
|---|---|
| Two-Stage-GAN | https://github.com/opensuh/DocumentBinarization |
| DeepOtsu | https://www.ai.rug.nl/~sheng/DeepOtsu.html |
| DE-GAN | https://github.com/dali92002/DE-GAN |
| DP-LinkNet | https://github.com/beargolden/DP-LinkNet |
| Sauvola-Net | https://github.com/Leedeng/SauvolaNet |
| Selectional AutoEncoder | https://github.com/ajgallego/document-image-binarization |
| Robin UNet | https://github.com/masyagin1998/robin |
Each project folder contains instructions regarding how to run the model as well as a requirements.txt file to create the python environment.
The model weights can be downloaded via: https://www.dropbox.com/s/vrlcbdhfbvn82pi/model_weights.zip?dl=0
The models were trained on the DIBCO2009, DIBCO2010, DIBCO2011, DIBCO2012, DIBCO2014 and DIBCO2016 datasets.
| Dataset | Link |
|---|---|
| DIBCO 2009 | http://users.iit.demokritos.gr/~bgat/DIBCO2009/benchmark/ |
| DIBCO 2010 | http://users.iit.demokritos.gr/~bgat/H-DIBCO2010/benchmark/ |
| DIBCO 2011 | http://utopia.duth.gr/~ipratika/DIBCO2011/benchmark/ |
| DIBCO 2012 | http://utopia.duth.gr/~ipratika/HDIBCO2012/benchmark/ |
| DIBCO 2013 | http://utopia.duth.gr/~ipratika/DIBCO2013/benchmark/ |
| DIBCO 2014 | http://users.iit.demokritos.gr/~bgat/HDIBCO2014/benchmark/ |
| DIBCO 2016 | http://vc.ee.duth.gr/h-dibco2016/benchmark/ |
| DIBCO 2017 | https://vc.ee.duth.gr/dibco2017/benchmark/ |
| DIBCO 2018 | http://vc.ee.duth.gr/h-dibco2018/benchmark/ |
| DIBCO 2019 | https://vc.ee.duth.gr/dibco2019/ |