qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-10-15 19:09:58 +02:00
Code Issues Projects Releases Wiki Activity

no more need to rm from contours_only_text_parent_d_ordered now

Browse source
This commit is contained in:
Robert Sachunsky 2025-10-07 22:47:34 +02:00
parent fd43e78442
commit 02a347a48a
2 changed files with 6 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/eynollah/eynollah.py
View file

@ -4437,6 +4437,8 @@ class Eynollah:
###min_con_area = 0.000005 ###min_con_area = 0.000005
contours_only_text, hir_on_text = return_contours_of_image(text_only) contours_only_text, hir_on_text = return_contours_of_image(text_only)
contours_only_text_parent = return_parent_contours(contours_only_text, hir_on_text) contours_only_text_parent = return_parent_contours(contours_only_text, hir_on_text)
contours_only_text_parent_d_ordered = []
contours_only_text_parent_d = []
if len(contours_only_text_parent) > 0: if len(contours_only_text_parent) > 0:
areas_tot_text = np.prod(text_only.shape) areas_tot_text = np.prod(text_only.shape)
areas_cnt_text = np.array([cv2.contourArea(c) for c in contours_only_text_parent]) areas_cnt_text = np.array([cv2.contourArea(c) for c in contours_only_text_parent])
@ -4558,15 +4560,6 @@ class Eynollah:
# plt.subplot(2, 2, 2, title="result contours") # plt.subplot(2, 2, 2, title="result contours")
# plt.imshow(img4) # plt.imshow(img4)
# plt.show() # plt.show()
else:
contours_only_text_parent_d_ordered = []
contours_only_text_parent_d = []
contours_only_text_parent = []
else:
contours_only_text_parent_d_ordered = []
contours_only_text_parent_d = []
#contours_only_text_parent = []
if not len(contours_only_text_parent): if not len(contours_only_text_parent):
# stop early # stop early
@ -4684,11 +4677,6 @@ class Eynollah:
slopes_marginals, mid_point_of_page_width) slopes_marginals, mid_point_of_page_width)
#print(len(polygons_of_marginals), len(ordered_left_marginals), len(ordered_right_marginals), 'marginals ordred') #print(len(polygons_of_marginals), len(ordered_left_marginals), len(ordered_right_marginals), 'marginals ordred')
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
contours_only_text_parent_d_ordered = self.return_list_of_contours_with_desired_order(
contours_only_text_parent_d_ordered, index_by_text_par_con)
else:
contours_only_text_parent_d_ordered = None
if self.full_layout: if self.full_layout:
if self.light_version: if self.light_version:

8
src/eynollah/utils/__init__.py
View file

@ -938,7 +938,7 @@ def check_any_text_region_in_model_one_is_main_or_header(
if (pixels_header>=pixels_main) and ( (length_con[ii]/float(height_con[ii]) )>=1.3 ): if (pixels_header>=pixels_main) and ( (length_con[ii]/float(height_con[ii]) )>=1.3 ):
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ]=2 regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ]=2
contours_only_text_parent_head.append(con) contours_only_text_parent_head.append(con)
if contours_only_text_parent_d_ordered is not None: if len(contours_only_text_parent_d_ordered):
contours_only_text_parent_head_d.append(contours_only_text_parent_d_ordered[ii]) contours_only_text_parent_head_d.append(contours_only_text_parent_d_ordered[ii])
all_box_coord_head.append(all_box_coord[ii]) all_box_coord_head.append(all_box_coord[ii])
slopes_head.append(slopes[ii]) slopes_head.append(slopes[ii])
@ -948,7 +948,7 @@ def check_any_text_region_in_model_one_is_main_or_header(
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ]=1 regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ]=1
contours_only_text_parent_main.append(con) contours_only_text_parent_main.append(con)
conf_contours_main.append(conf_contours[ii]) conf_contours_main.append(conf_contours[ii])
if contours_only_text_parent_d_ordered is not None: if len(contours_only_text_parent_d_ordered):
contours_only_text_parent_main_d.append(contours_only_text_parent_d_ordered[ii]) contours_only_text_parent_main_d.append(contours_only_text_parent_d_ordered[ii])
all_box_coord_main.append(all_box_coord[ii]) all_box_coord_main.append(all_box_coord[ii])
slopes_main.append(slopes[ii]) slopes_main.append(slopes[ii])
@ -1033,7 +1033,7 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ] = 2 regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ] = 2
contours_only_text_parent_head.append(contours_only_text_parent[ii]) contours_only_text_parent_head.append(contours_only_text_parent[ii])
conf_contours_head.append(None) # why not conf_contours[ii], too? conf_contours_head.append(None) # why not conf_contours[ii], too?
if contours_only_text_parent_d_ordered is not None: if len(contours_only_text_parent_d_ordered):
contours_only_text_parent_head_d.append(contours_only_text_parent_d_ordered[ii]) contours_only_text_parent_head_d.append(contours_only_text_parent_d_ordered[ii])
all_box_coord_head.append(all_box_coord[ii]) all_box_coord_head.append(all_box_coord[ii])
slopes_head.append(slopes[ii]) slopes_head.append(slopes[ii])
@ -1043,7 +1043,7 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ] = 1 regions_model_1[:,:][(regions_model_1[:,:]==1) & (img == 255) ] = 1
contours_only_text_parent_main.append(contours_only_text_parent[ii]) contours_only_text_parent_main.append(contours_only_text_parent[ii])
conf_contours_main.append(conf_contours[ii]) conf_contours_main.append(conf_contours[ii])
if contours_only_text_parent_d_ordered is not None: if len(contours_only_text_parent_d_ordered):
contours_only_text_parent_main_d.append(contours_only_text_parent_d_ordered[ii]) contours_only_text_parent_main_d.append(contours_only_text_parent_d_ordered[ii])
all_box_coord_main.append(all_box_coord[ii]) all_box_coord_main.append(all_box_coord[ii])
slopes_main.append(slopes[ii]) slopes_main.append(slopes[ii])