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.

Sign up for GitHub

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

Jump to bottom

Figure - Table detection challenges #215

Open
egork520 opened this issue Mar 28, 2023 · 3 comments
Open

Figure - Table detection challenges #215

egork520 opened this issue Mar 28, 2023 · 3 comments
Assignees
@egork520

Comments

@egork520
Copy link
Contributor

In this issue I am collecting some of the examples where LayoutParser predictions or Villa predictions are incorrect.
@egork520
Copy link
Contributor Author

sha = 1dd66e46a7a92fa2936e7f8ec3d727acf5260697
Using recipes to make (box) annotations, layoutparser predictions are seem to be pretty noise. Here is an example of items in box_groups predicitons: Red = equation, Green = Figure, Yellow = Table, Pink = Text
Screenshot 2023-03-28 at 9 47 39 AM
Screenshot 2023-03-28 at 9 50 15 AM
Screenshot 2023-03-28 at 9 53 19 AM

@kyleclo
Copy link
Collaborator

kyleclo commented Mar 29, 2023

@comorado can you include the commands you need to reproduce these predictions?

@egork520
Copy link
Contributor Author

Hello @kyleclo here is a link to a code which reproduces the above predicted boxes

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@egork520 egork520

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@egork520 @kyleclo