Yuliang-Liu/Curve-Text-Detector

This repository provides train&test code, dataset, det.&rec. annotation, evaluation script, annotation tool, and ranking.

43
/ 100
Emerging

This provides a collection of images and their corresponding annotations for training and evaluating systems that detect curved text. It helps researchers and engineers build better algorithms for recognizing text that isn't straight, like on product labels or street signs. You input a raw image and the output is the identified curved text regions and characters.

652 stars. No commits in the last 6 months.

Use this if you are developing or testing algorithms specifically designed to detect and recognize text that appears in curved or arbitrary shapes within images.

Not ideal if you are looking for a maintained project or a complete, out-of-the-box solution for general text recognition, especially for Chinese text.

optical-character-recognition image-processing computer-vision-research document-analysis deep-learning-datasets
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 25 / 25

How are scores calculated?

Stars

652

Forks

157

Language

Jupyter Notebook

License

Last pushed

Jul 20, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Yuliang-Liu/Curve-Text-Detector"

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