Skip to content

Find block text without marginal notes#17

Open
zuphilip wants to merge 1 commit intomasterfrom
block
Open

Find block text without marginal notes#17
zuphilip wants to merge 1 commit intomasterfrom
block

Conversation

@zuphilip
Copy link
Copy Markdown
Member

This is work in progress and the PR here is just that we can discuss the attempt/code and maybe someone can continue.

I focused on the length of the text line because the vertical coordinates are in real pictures not aligned nicely (i.e. one would need to perform a rotation first). Moreover, the order of the textboxes is not easily determined and e.g. tesseract produces strange boxes on the margins. However, I am open for alternatives, if you have any ideas that work well. Here is an example 417576986_0463 where the current code works (and I have problems to think of any alternatives):

417576986_0463 block

@stweil
Copy link
Copy Markdown
Member

stweil commented Sep 1, 2016

I rebased this PR (fixes merge conflicts caused by changes in README.md).

@zuphilip
Copy link
Copy Markdown
Member Author

zuphilip commented Sep 1, 2016

Thank you.

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.

2 participants