NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Correct scaling of debug visualizations, tune OCR (#700)

Browse Source 
* fix: Correct scaling of debug visualizations, tune OCR

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* chore: remove unused imports

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* chore: Update docling-core

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-01-08 12:26:44 +01:00
committed by GitHub
parent ead396ab40
commit 5cb4cf6f19
5 changed files with 766 additions and 839 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docling/models/table_structure_model.py
View File

@@ -66,23 +66,43 @@ class TableStructureModel(BasePageModel):
show: bool = False,
):
assert page._backend is not None
assert page.size is not None
image = (
page._backend.get_page_image()
) # make new image to avoid drawing on the saved ones
scale_x = image.width / page.size.width
scale_y = image.height / page.size.height
draw = ImageDraw.Draw(image)
for table_element in tbl_list:
x0, y0, x1, y1 = table_element.cluster.bbox.as_tuple()
y0 *= scale_x
y1 *= scale_y
x0 *= scale_x
x1 *= scale_x
draw.rectangle([(x0, y0), (x1, y1)], outline="red")
for cell in table_element.cluster.cells:
x0, y0, x1, y1 = cell.bbox.as_tuple()
x0 *= scale_x
x1 *= scale_x
y0 *= scale_x
y1 *= scale_y
draw.rectangle([(x0, y0), (x1, y1)], outline="green")
for tc in table_element.table_cells:
if tc.bbox is not None:
x0, y0, x1, y1 = tc.bbox.as_tuple()
x0 *= scale_x
x1 *= scale_x
y0 *= scale_x
y1 *= scale_y
if tc.column_header:
width = 3
else: