dali92002/SSL-OCR

Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement - AAAI 2023

40
/ 100
Emerging

This project helps you to improve the readability and extract text from difficult-to-read document images. It takes degraded or unclear text images, such as historical documents or photos of text, and outputs enhanced images and the recognized text. This is designed for researchers or practitioners working with challenging text recognition tasks.

No commits in the last 6 months.

Use this if you need to extract accurate text from scanned documents, historical archives, or images where the text is blurry, distorted, or suffers from various degradations.

Not ideal if you are looking for a simple, out-of-the-box solution for perfectly clear, machine-printed text recognition.

document-enhancement historical-document-analysis optical-character-recognition image-processing text-extraction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

28

Forks

8

Language

Python

License

MIT

Last pushed

Jul 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dali92002/SSL-OCR"

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