qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2026-06-16 09:59:13 +02:00
Code Issues Projects Releases Wiki Activity

extracting ocr textline images and text: vertical lines threshold has changed to 1.4

Browse source
This commit is contained in:
vahidrezanezhad 2026-02-10 14:32:23 +01:00 • committed by kba
parent 4776ea9fc4
commit d0b3bb419f
1 changed files with 10 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/eynollah/training/extract_line_gt.py
View file

@ -50,6 +50,12 @@ from ..utils import is_image_filename
is_flag=True, is_flag=True,
help="if this parameter set to true, cropped textline images will not be masked with textline contour.", help="if this parameter set to true, cropped textline images will not be masked with textline contour.",
) )
@click.option(
"--exclude_vertical_lines",
"-exv",
is_flag=True,
help="if this parameter set to true, vertical textline images will be excluded.",
)
def linegt_cli( def linegt_cli(
image, image,
dir_in, dir_in,
@ -57,6 +63,7 @@ def linegt_cli(
dir_out, dir_out,
pref_of_dataset, pref_of_dataset,
do_not_mask_with_textline_contour, do_not_mask_with_textline_contour,
exclude_vertical_lines,
): ):
assert bool(dir_in) ^ bool(image), "Set --dir-in or --image-filename, not both" assert bool(dir_in) ^ bool(image), "Set --dir-in or --image-filename, not both"
if dir_in: if dir_in:
@ -100,6 +107,9 @@ def linegt_cli(
x, y, w, h = cv2.boundingRect(textline_coords) x, y, w, h = cv2.boundingRect(textline_coords)
if exclude_vertical_lines and h > 2 * w:
continue
total_bb_coordinates.append([x, y, w, h]) total_bb_coordinates.append([x, y, w, h])
img_poly_on_img = np.copy(img) img_poly_on_img = np.copy(img)