docling-project / docling-project/docling

Multicolumn text recognition breaks in image

Open
#1,396 0 comments 0 reactions 1 assignee Claimed by @nikos-livathinos View on GitHub
bug layout
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Bug

...
"The original file is shown in Figure 1, and the Docling parsing result in HTML is shown in Figure 2. The two parts marked in red in Figure 2 belong to two columns on the page, but the layout analysis results classify these two parts as the same type of block, so they should be merged together."
Figure 1:
![Image](https://github.com/user-attachments/assets/479024d6-e562-49c1-83d6-9bfc0dd73739)

Figure 2:
![Image](https://github.com/user-attachments/assets/a82e2063-f5ce-470c-a078-0685373ffdc9)

### Steps to reproduce

...

### Docling version

...

### Python version

...

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.