juvian/Manga-Text-Segmentation

Segmentation of text in manga images

42
/ 100
Emerging

This project helps scan manga pages to precisely identify and isolate all text bubbles and sound effects. You input a raw manga page image, and it outputs an identical image with the text areas clearly highlighted. This is useful for translators, digital comics archivists, or researchers analyzing visual novel layouts.

138 stars. No commits in the last 6 months.

Use this if you need to automatically distinguish and extract text regions from the intricate artwork of Japanese manga.

Not ideal if you need to detect text in typical photographs, documents, or Western comics.

manga-translation digital-comics image-segmentation comics-archiving visual-novel-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

138

Forks

18

Language

Jupyter Notebook

License

MIT

Category

latex-ocr-tools

Last pushed

Feb 06, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/juvian/Manga-Text-Segmentation"

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