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

Accounting\currency version #9

Open
oldominion opened this issue Jun 3, 2019 · 4 comments
Open

Accounting\currency version #9

oldominion opened this issue Jun 3, 2019 · 4 comments

Comments

@oldominion
Copy link

Could you possibly add a traindata file specialized for accounting purposes?
1-9, dot, comma, various currency symbols such as '$£€', dash, colon/semicolon, etc

€ is the main problem for me, it's invariably detected as a 6 or an 8 instead of being ignored, and since I'm looking for digits only, I have no way of correcting the output via post processing.

@Shreeshrii
Copy link
Owner

Please see tesseract-ocr/tessdata#120

@oldominion
Copy link
Author

oldominion commented Jun 4, 2019

Thanks! Sadly that one doesn't include currency symbols, so it's no use at avoiding the frequent misclassification of € for example.

@Shreeshrii
Copy link
Owner

If you can make a training text with the kind of symbols you need, I can run the training.

See samples of training text used for other traineddata:

https://github.com/Shreeshrii/tessdata_shreetest/blob/master/eng.digits.training_text
https://github.com/Shreeshrii/tessdata_shreetest/blob/master/engrestrict.training_text

@samrood121
Copy link

@Shreeshrii is there any way that you can help me make a traineddata for single image (it is basically a check box) for my project

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

3 participants