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

return_contours_of_interested_region*: rm unused variants

Browse source
This commit is contained in:
Robert Sachunsky 2025-10-08 19:21:07 +02:00
parent 8a2d682e12
commit b3d29bef89
2 changed files with 7 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

15
src/eynollah/eynollah.py
View file

@ -79,7 +79,6 @@ from .utils.contour import (
get_textregion_contours_in_org_image_light,
return_contours_of_image,
return_contours_of_interested_region,
return_contours_of_interested_region_by_min_size,
return_contours_of_interested_textline,
return_parent_contours,
dilate_textregion_contours,
@ -4242,13 +4241,10 @@ class Eynollah:
all_found_textline_polygons = filter_contours_area_of_image(
textline_mask_tot_ea, cnt_clean_rot_raw, hir_on_cnt_clean_rot, max_area=1, min_area=0.00001)
M_main_tot = [cv2.moments(all_found_textline_polygons[j])
for j in range(len(all_found_textline_polygons))]
w_h_textlines = [cv2.boundingRect(all_found_textline_polygons[j])[2:]
for j in range(len(all_found_textline_polygons))]
w_h_textlines = [w_h_textlines[j][0] / float(w_h_textlines[j][1]) for j in range(len(w_h_textlines))]
cx_main_tot = [(M_main_tot[j]["m10"] / (M_main_tot[j]["m00"] + 1e-32)) for j in range(len(M_main_tot))]
cy_main_tot = [(M_main_tot[j]["m01"] / (M_main_tot[j]["m00"] + 1e-32)) for j in range(len(M_main_tot))]
cx_main_tot, cy_main_tot = find_center_of_contours(all_found_textline_polygons)
w_h_textlines = [cv2.boundingRect(polygon)[2:]
for polygon in all_found_textline_polygons]
w_h_textlines = [w / float(h) for w, h in w_h_textlines]
all_found_textline_polygons = self.get_textlines_of_a_textregion_sorted(
#all_found_textline_polygons[::-1]
@ -4677,7 +4673,8 @@ class Eynollah:
self.plotter.save_plot_of_layout_all(text_regions_p, image_page)
label_img = 4
polygons_of_drop_capitals = return_contours_of_interested_region_by_min_size(text_regions_p, label_img)
polygons_of_drop_capitals = return_contours_of_interested_region(text_regions_p, label_img,
min_area=0.00003)
##all_found_textline_polygons = adhere_drop_capital_region_into_corresponding_textline(
##text_regions_p, polygons_of_drop_capitals, contours_only_text_parent, contours_only_text_parent_h,
##all_box_coord, all_box_coord_h, all_found_textline_polygons, all_found_textline_polygons_h,

33
src/eynollah/utils/contour.py
View file

@ -253,39 +253,6 @@ def return_contours_of_image(image):
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
return contours, hierarchy
def return_contours_of_interested_region_by_min_size(region_pre_p, label, min_size=0.00003):
# pixels of images are identified by 5
if region_pre_p.ndim == 3:
cnts_images = (region_pre_p[:, :, 0] == label) * 1
else:
cnts_images = (region_pre_p[:, :] == label) * 1
_, thresh = cv2.threshold(cnts_images.astype(np.uint8), 0, 255, 0)
contours_imgs, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_imgs = return_parent_contours(contours_imgs, hierarchy)
contours_imgs = filter_contours_area_of_image_tables(
thresh, contours_imgs, hierarchy, max_area=1, min_area=min_size)
return contours_imgs
def return_contours_of_interested_region_by_size(region_pre_p, label, min_area, max_area):
# pixels of images are identified by 5
if region_pre_p.ndim == 3:
cnts_images = (region_pre_p[:, :, 0] == label) * 1
else:
cnts_images = (region_pre_p[:, :] == label) * 1
_, thresh = cv2.threshold(cnts_images.astype(np.uint8), 0, 255, 0)
contours_imgs, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_imgs = return_parent_contours(contours_imgs, hierarchy)
contours_imgs = filter_contours_area_of_image_tables(
thresh, contours_imgs, hierarchy, max_area=max_area, min_area=min_area)
img_ret = np.zeros((region_pre_p.shape[0], region_pre_p.shape[1]))
img_ret = cv2.fillPoly(img_ret, pts=contours_imgs, color=1)
return img_ret
def dilate_textline_contours(all_found_textline_polygons):
return [[polygon2contour(contour2polygon(contour, dilate=6))
for contour in region]