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

segment-region: use BlockPolygon #57

Merged
merged 6 commits into from
Jul 18, 2019
Merged

Conversation

bertsky
Copy link
Collaborator

@bertsky bertsky commented Jul 17, 2019

Now that sirfz/tesserocr#185 is merged, we can annotate Tesseract's polygon results instead of just the bounding box. Still not making crop_polygons true by default, because I believe these things cannot be trusted.

I have linked with tesserocr requirement from Github instead of the PyPI pkg, because a new release will likely not arrive before Tesseract 5.

@bertsky bertsky requested review from kba and wrznr July 17, 2019 15:00
@bertsky bertsky force-pushed the use-blockpolygon branch 2 times, most recently from 4f2edd4 to 83b4eef Compare July 17, 2019 15:06
@bertsky
Copy link
Collaborator Author

bertsky commented Jul 17, 2019

Sorry about the force-pushing noise: having a hard time getting used to RST.

@kba
Copy link
Member

kba commented Jul 17, 2019

You can also use Markdown for the README if you prefer that, just have to change the setup.py so it's correctly displayed on PyPI.

Copy link
Member

@kba kba left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

requirements.txt Outdated Show resolved Hide resolved
Copy link
Contributor

@wrznr wrznr left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Minor comments. Thanks for the excellent documentation!

README.rst Outdated Show resolved Hide resolved
README.rst Outdated Show resolved Hide resolved
@@ -125,12 +125,12 @@ def process(self):
bin_bbox = image.getbbox()
if not bin_bbox:
# this does happen!
LOG.debug("Ignoring region '%s' because its binarization is empty", ID)
LOG.info("Ignoring region '%s' because its binarization is empty", ID)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So, you decided to take the more-verbose road. We have to see if this is feasible in the long run.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry, then I misunderstood you. So you want this to stay in DEBUG here, and downgrade similar statements in segment-region to DEBUG as well?

ocrd_tesserocr/segment_region.py Show resolved Hide resolved
@bertsky
Copy link
Collaborator Author

bertsky commented Jul 18, 2019

Sorry, I should have made the last 3 on a separate branch/PR. Just sneaking by your approval!

@bertsky bertsky merged commit 7c669ff into OCR-D:master Jul 18, 2019
@bertsky bertsky deleted the use-blockpolygon branch July 18, 2019 16:18
@kba
Copy link
Member

kba commented Jul 18, 2019

Sneaky sneaky 😁

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

Successfully merging this pull request may close these issues.

None yet

3 participants