{ "fetched_at": "2026-10-19T14:05:33Z", "source_url": "https://www.kaggle.com/competitions/denoising-dirty-documents/data", "pages": [ { "name": "data-description", "content": "

You are provided two sets of images, train and test. These images contain various styles of text, to which synthetic noise has been added to simulate real-world, messy artifacts. The training set includes the test without the noise (train_cleaned). You must create an algorithm to clean the images in the test set.

\r\n

\"\"

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "
\r\n

Optical Character Recognition (OCR) is the process of getting type or handwritten documents into a digitized format. If you've read a classic novel on a digital reading device or had your doctor pull up old healthcare records via the hospital computer system, you've probably benefited from OCR.

\r\n

OCR makes previously static content editable, searchable, and much easier to share. But, a lot of documents eager for digitization are being held back. Coffee stains, faded sun spots, dog-eared pages, and lot of wrinkles are keeping some printed documents offline and in the past. 

\r\n

This competition challenges you to give these documents a machine learning makeover. Given a dataset of images of scanned text that has seen better days, you're challenged to remove the noise. Improving the ease of document enhancement will help us get that rare mathematics book on our e-reader before the next beach vacation.

\r\n

We've kicked off the fun with a few handy scripts to get you started on the dataset.

\r\n

Acknowledgements

\r\n

Kaggle is hosting this competition for the machine learning community to use for fun and practice. This dataset was created by RM.J. Castro-Bleda, S. España-Boquera, J. Pastor-Pellicer, F. Zamora-Martinez. We also thank the UCI machine learning repository for hosting the dataset. If you use the problem in publication, please cite:

\r\n

Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository. Irvine, CA: University of California, School of Information and Computer Science

\r\n
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "

Submissions are evaluated on the root mean squared error between the cleaned pixel intensities and the actual grayscale pixel intensities.

\r\n

Submission File

\r\n

Form the submission file by melting each images into a set of pixels, assigning each pixel an id of image_row_col (e.g. 1_2_1 is image 1, row 2, column 1). Intensity values range from 0 (black) to 1 (white). The file should contain a header and have the following format:

\r\n
id,value
1_1_1,1
1_2_1,1
1_3_1,1
etc.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n\t\r\n

One account per participant

\r\n

You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.

\r\n

No private sharing outside teams

\r\n

\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n

\r\n

Team Mergers

\r\n

\r\n Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.
\r\n

\r\n\r\n

Team Limits

\r\n

There is no maximum team size.

\r\n

Submission Limits

\r\n

You may submit a maximum of 5 entries per day.

\r\n

You may select up to 2 final submissions for judging.

\r\n

Competition Timeline

\r\n

Start Date: 6/1/2015 5:27 PM UTC

\r\n

Merger Deadline: None

\r\n

Entry Deadline: None

\r\n

End Date: 10/5/2015 11:59 PM UTC

\r\n\t\r\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "\r\n

All deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The organizers reserve the right to update the contest timeline if they deem it necessary.

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "

Scripts for Swag

\r\n

The authors of the 3 most up-voted scripts for this competition will get their choice of an official Kaggle hoodie, t-shirt, or mug!

\r\n

Your position on the leaderboard does not factor into winning Scripts for Swag.

", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }