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

[WIP] Customizable vertical separators #138

Open
wants to merge 2 commits into
base: master
Choose a base branch
from

Conversation

kba
Copy link
Collaborator

@kba kba commented Nov 4, 2016

This branch contains the pertinent commits from #68 for now

Comments from that PR:

#68 (comment):

I work a lot with bordered tables and observed damaged characters near the left and right cell borders. I think the vertical separators are expanded too much.

#68 (comment):

That looks useful, but could you please make these values into command line parameters? I'm reluctant to change them because it would require extensive testing to figure out how that affects other page segmentation (since I currently don't have a setup for testing this easily on large datasets).

Something like:

d1 = int(max(5,args.separator_multiplier_h * scale)) + args.sepwiden
seps = minimum(thresh,maximum_filter(grad,(int(args.septhresh_multiplier_h*scale),int(5*scale))))
The defaults should just be 1.0

Eventually, this code will get replaced by trainable 2D LSTM models.

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

Successfully merging this pull request may close these issues.

3 participants