argman/EAST

A tensorflow implementation of EAST text detector

51
/ 100
Established

This project helps quickly identify and locate text within images, a crucial step for digitizing documents, analyzing visual content, or making images searchable. You input an image containing text, and it outputs precise bounding boxes around each text instance. It's designed for anyone needing to automatically extract text regions from photos or scanned documents.

3,060 stars. No commits in the last 6 months.

Use this if you need to accurately detect and localize text in various real-world images, such as street signs, product labels, or document scans.

Not ideal if you only need to recognize characters (OCR) without first detecting the text regions, or if you require a solution for non-Latin scripts.

document-digitization image-analysis visual-search content-extraction data-entry-automation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

3,060

Forks

1,047

Language

C++

License

GPL-3.0

Last pushed

Nov 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/argman/EAST"

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