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

Adding segmentation as way to save ton of time #120

Open
maximka1812 opened this issue Nov 17, 2022 · 0 comments
Open

Adding segmentation as way to save ton of time #120

maximka1812 opened this issue Nov 17, 2022 · 0 comments

Comments

@maximka1812
Copy link

One option is to use Tesseract OCR API, see https://github.com/maximka1812/Segmentation-Demo-Using-Tesseract-API
Note that you can use Tesseract API also for automatic page turning on initial stage, they have feature to determinate angle (90, 180, 270).

This can be also all be done via external call and just use JSON or similar way to return information to ST.

Another huge help is to be able to use image regions data for mixed output mode, as presently ST automatic mode frequently make errors or miss stuff.

Another option is to have tool that changes ScanTailor project file adding all information, here saved Finereader project files can be also used, they have regions data in binary (and their segmentation quality is better!)

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

1 participant