# **The Augraphy Project**


Augraphy is a Python library that creates multiple copies of original documents through an augmentation pipeline that randomly distorts each copy – degrading the clean version into dirty and realistic copies rendered through synthetic paper printing, faxing, scanning, and copy machine processes.

The dataset created for the Denoising Shabby Pages competition was generated using Augraphy pipelines to create realistic old and noisy documents from “born digital” sources. This simulation of realistic paper-oriented process distortions creates large amounts of training data for AI/ML processes to learn how to remove those distortions.

Fork and star [Augraphy](https://github.com/sparkfish/augraphy) on GitHub to help the team and improve the project!

[![GitHub forks](https://img.shields.io/github/forks/sparkfish/augraphy.svg?style=social&label=Fork&maxAge=2592000)](https://GitHub.com/sparkfish/augraphy/network/)
[![GitHub stars](https://img.shields.io/github/stars/sparkfish/augraphy.svg?style=social&label=Star&maxAge=2592000)](https://GitHub.com/sparkfish/augraphy)

![The Augraphy Project](https://raw.githubusercontent.com/sparkfish/augraphy/dev/images/logo/augraphy.png)

The ShabbyPages dataset is compiled through the Augraphy pipeline. If you would like to run your own documents through the pipeline to create your own training/testing data, we encourage you to do so! [You can access the pipeline here.](https://github.com/sparkfish/shabby-pages/blob/dev/shabbypipeline.py)

[You can use these clean documents to run through the pipeline.](https://drive.google.com/drive/folders/1NJhrxo5wyQnyPUKuRkIMOmcW7Zkd2J_0?usp=sharing)