# **Your Challenge**
Your task is to denoise “shabby” documents, reversing the effects imposed on them by [Augraphy](https://github.com/sparkfish/augraphy). There are several paths one might take to accomplish this goal, so feel free to experiment and find which leads to doom and which leads to glory.

![](https://miro.medium.com/max/1400/1*-Gif4QqHRoUotVE_AVvv6A.png)
### The task is simple: denoise shabby documents, like the right image, to make them look as clean as possible, like the left image.

# **Historical Significance**
Documents are exposed to harsh conditions once scribed and enter the world. Most of human history is captured in paper form, some going back thousands of years -- yet the knowledge they hold often degrades very quickly. Even in the modern world, as those documents are scanned, faxed, copied, and printed, there are many distortions that get introduced that obscure their original form. Those distortions, or "noise", prevent them from being captured in a more immortal, digital form. That is the problem we intend to solve, with your help.

Depart with us on the hero's journey, to chart the uncharted path that restores luster to that which was once lost.

# **Due Date**
The competition is set to end based on the accuracy of the top denoising model. The winner of the competition will be the first person with a denoising model with an RMSE value of less than 0.05. To train models with this accuracy, look at how you can create more data under the Data tab.

# **Rules**
All code submissions must be written in Python, but any library can be used
No online solutions-as-a-service may be used
Groups of up to 3 people are allowed

# **Augraphy Workshop**
Unlike most competitions, this one will feature a workshop that describes how Augraphy works and how you can use it to supercharge your submissions to improve your odds of winning. Once the competition receives more interest, we'll poll competitors on Slack and determine a date and time for the workshop. Check back here or in the Slack channel for the announcement!

# **Communication**
All official communication will be done through Slack.
[Join in the discussion](https://join.slack.com/t/denoisingshabby/shared_invite/zt-160i3x0c7-3mGB81~5M0mt2t0zcq2N_Q) happening right now on Slack to see how others are approaching a solution and to access other opportunities to learn!

# **Prizes**
The grand prize offered by our sponsors are [detailed separately…](https://denoising-shabby.com/prizes/)
We are awarding the author of the best write-up and code documentation with the chance to meet and collaborate with the Augraphy Team on the Augraphy paper, which will be submitted to global AI conferences.
We are also awarding 20 Augraphy T-shirts! 10 for the highest-scoring submissions on the leaderboard, and 10 for the most active participants in the Kaggle competition discussion.

# **Website**
All of this information and more is accessible at [https://denoising-shabby.com/](https://denoising-shabby.com/).

# **Shabby Pages**
The full Shabby Pages dataset is under active development, and you can help by participating in this competition! We'll release the full set later, but for now, you can grab the cropped set available on the Data page of this competition, or you can grab that and the full-size set from [here](https://drive.google.com/drive/folders/12TtuZHgtTeFyJEhV3DECBXYFlYt4tGUC?usp=sharing).