qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-08-29 03:49:54 +02:00
Code Issues Projects Releases Wiki Activity

check_any_text_region_in_model_one_is_main_or_header_light: return original instead of resampled contours

Browse source
This commit is contained in:
Robert Sachunsky 2025-08-21 01:05:15 +02:00
parent 3d53070b90
commit b610fe07a6
1 changed files with 6 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/eynollah/utils/__init__.py
View file

@ -955,11 +955,11 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
regions_model_full = cv2.resize(regions_model_full, (regions_model_full.shape[1] // zoom,
regions_model_full.shape[0] // zoom),
interpolation=cv2.INTER_NEAREST)
contours_only_text_parent = [(i / zoom).astype(int) for i in contours_only_text_parent]
contours_only_text_parent_z = [(cnt / zoom).astype(int) for cnt in contours_only_text_parent]
###
cx_main, cy_main, x_min_main, x_max_main, y_min_main, y_max_main, y_corr_x_min_from_argmin = \
find_new_features_of_contours(contours_only_text_parent)
find_new_features_of_contours(contours_only_text_parent_z)
length_con=x_max_main-x_min_main
height_con=y_max_main-y_min_main
@ -982,8 +982,7 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
contours_only_text_parent_main_d=[]
contours_only_text_parent_head_d=[]
for ii in range(len(contours_only_text_parent)):
con=contours_only_text_parent[ii]
for ii, con in enumerate(contours_only_text_parent_z):
img=np.zeros((regions_model_1.shape[0], regions_model_1.shape[1], 3))
img = cv2.fillPoly(img, pts=[con], color=(255, 255, 255))
@ -994,23 +993,22 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
if (pixels_header/float(pixels_main)>=0.3) and ( (length_con[ii]/float(height_con[ii]) )>=1.3 ):
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img[:,:,0]==255) ]=2
contours_only_text_parent_head.append(con)
contours_only_text_parent_head.append(contours_only_text_parent[ii])
conf_contours_head.append(None) # why not conf_contours[ii], too?
if contours_only_text_parent_d_ordered is not None:
contours_only_text_parent_head_d.append(contours_only_text_parent_d_ordered[ii])
all_box_coord_head.append(all_box_coord[ii])
slopes_head.append(slopes[ii])
all_found_textline_polygons_head.append(all_found_textline_polygons[ii])
conf_contours_head.append(None)
else:
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img[:,:,0]==255) ]=1
contours_only_text_parent_main.append(con)
contours_only_text_parent_main.append(contours_only_text_parent[ii])
conf_contours_main.append(conf_contours[ii])
if contours_only_text_parent_d_ordered is not None:
contours_only_text_parent_main_d.append(contours_only_text_parent_d_ordered[ii])
all_box_coord_main.append(all_box_coord[ii])
slopes_main.append(slopes[ii])
all_found_textline_polygons_main.append(all_found_textline_polygons[ii])
#print(all_pixels,pixels_main,pixels_header)
### to make it faster
@ -1018,8 +1016,6 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
# regions_model_full = cv2.resize(img, (regions_model_full.shape[1] // zoom,
# regions_model_full.shape[0] // zoom),
# interpolation=cv2.INTER_NEAREST)
contours_only_text_parent_head = [(i * zoom).astype(int) for i in contours_only_text_parent_head]
contours_only_text_parent_main = [(i * zoom).astype(int) for i in contours_only_text_parent_main]
###
return (regions_model_1,