dali92002/DocEnTR

DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022

47
/ 100
Emerging

This project helps anyone working with scanned documents by cleaning up poor-quality images. It takes in degraded document images, such as those with smudges, low contrast, or faded text, and outputs crisp, binarized versions where text is clearly separated from the background. Document archivists, data entry specialists, or researchers digitizing old texts would find this useful.

186 stars. No commits in the last 6 months.

Use this if you need to transform hard-to-read scanned documents into clean, black-and-white images for better readability or further processing.

Not ideal if you're looking for a tool to enhance photographs or other types of images that aren't primarily document-based.

document-digitization ocr-preprocessing records-management archiving historical-document-restoration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

186

Forks

39

Language

Jupyter Notebook

License

Last pushed

Jan 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dali92002/DocEnTR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.