Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] can you recommend the detec and reg model for Chinese OCR. #1979

Open
wahahaer opened this issue Sep 3, 2023 · 0 comments
Open
Assignees

Comments

@wahahaer
Copy link

wahahaer commented Sep 3, 2023

What is the feature?

MMOCR has supplied so many models including detec and reg models,
such as:
[det]: DBNet / DBNetpp / DRRG / FCENet / Mask R-CNN
[rec]: ABINet / ASTER / CRNN / MASTER / NRTR / RobustScanner

but for our common users, I only want to know which model can be better in my scene during to so many users' experience.
So, you are appreciated if u can tell me which models can be better for such Chinese ocr scenes:

Horizontal Simplified Chinese
Vertical Traditional Chinese, such as ancient Chinese texts
I think MMOCR comes from a Chinese AI/CV company, it shall be more advanced in Chinese ocr.
Am I right?
I don't want to train with my own data.Thanks very much!!!

Any other context?

No response

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants