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

Super Resolution for Text Recognition #309

Open
jkcg-learning opened this issue Jun 21, 2021 · 2 comments
Open

Super Resolution for Text Recognition #309

jkcg-learning opened this issue Jun 21, 2021 · 2 comments

Comments

@jkcg-learning
Copy link

jkcg-learning commented Jun 21, 2021

Implement Super Resolution for Low Resolution Images

Motivation
Improving the resolution of low resolution images could help in better Detection and thereby Recognition of text in the image.
https://arxiv.org/pdf/1909.07113.pdf (TextSR)
https://arxiv.org/pdf/2005.03341v3.pdf
https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600154.pdf
https://arxiv.org/pdf/1811.10449v1.pdf
https://github.com/JasonBoy1/TextZoom

Related resources
https://paperswithcode.com/task/super-resolution

Some Algorithms, but not sure if this performs good with respect to STR usecases.

EDSR, ESPCN, FSRCNN, LapSRN

@usamaamjad7
Copy link

Hey bro , How to create a pipeline using Custom dataset in text Recognition ?

@innerlee
Copy link
Contributor

Hi @usamaamjad7, please open a new issue for new questions :)

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

No branches or pull requests

3 participants