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

Recognize more fonts and train tesseract for different meme formats #2

Open
kevinchr opened this issue Jun 16, 2018 · 3 comments
Open

Comments

@kevinchr
Copy link

Hi there,

I was wondering if it is possible for your wonderful script to recognize more fonts? I'm having the most problems with the font impact and was wondering if i can add more fonts for tesseract to recognize? Also can i train tesseract for different meme formats? And if so, how could i do this?

Hoping you can help me out,

Kind regards,

kevin

@aryaminus
Copy link
Owner

By different meme format you mean on image text meme, It does not render as I am taking white background rendering using OpenCV to separate meme and image. We could use other fonts though but it should be installed in the system, thus used Arial as it comes builtin

@kevinchr
Copy link
Author

Yes, with different meme formats i mean for example like this one
image

Is it possible to train the OpenCv in your script? Or does it require some hardcoding?

And thank you for clarifying my issue with different font types on memes :)

@aryaminus
Copy link
Owner

I would have to hard code it to look for White Background. I would have to look into it.

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