qurator-spk
/
eynollah
mirror of https://github.com/qurator-spk/eynollah.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

textlines of drop capitals are connected to corresponding textline if possible otherwise they are inserted in corresponding textregion

Browse Source
pull/142/merge
vahidrezanezhad 1 month ago
parent 22b0b07a73
commit f43c49c508
3 changed files with 66 additions and 31 deletions
Show Stats Download Patch File Download Diff File

2
src/eynollah/eynollah.py
Unescape Escape View File

@ -5176,7 +5176,7 @@ class Eynollah:
pixel_img = 4
polygons_of_drop_capitals = return_contours_of_interested_region_by_min_size(text_regions_p, pixel_img)
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, kernel=KERNEL, curved_line=self.curved_line)
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, kernel=KERNEL, curved_line=self.curved_line, textline_light=self.textline_light)
pixel_lines = 6
if not self.reading_order_machine_based:

77
src/eynollah/utils/drop_capitals.py
Unescape Escape View File

@ -4,6 +4,7 @@ from .contour import (
find_new_features_of_contours,
return_contours_of_image,
return_parent_contours,
return_contours_of_interested_region,
)
def adhere_drop_capital_region_into_corresponding_textline(
@ -17,6 +18,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
all_found_textline_polygons_h,
kernel=None,
curved_line=False,
textline_light=False,
):
# print(np.shape(all_found_textline_polygons),np.shape(all_found_textline_polygons[3]),'all_found_textline_polygonsshape')
# print(all_found_textline_polygons[3])
@ -76,7 +78,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
# region_with_intersected_drop=region_with_intersected_drop/3
region_with_intersected_drop = region_with_intersected_drop.astype(np.uint8)
# print(np.unique(img_con_all_copy[:,:,0]))
if curved_line:
if curved_line or textline_light:
if len(region_with_intersected_drop) > 1:
sum_pixels_of_intersection = []
@ -114,12 +116,17 @@ def adhere_drop_capital_region_into_corresponding_textline(
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_combined = return_contours_of_interested_region(img_textlines, 255, 0)
#plt.imshow(img_textlines)
#plt.show()
#imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
#ret, thresh = cv2.threshold(imgray, 0, 255, 0)
#contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
contours_biggest = contours_combined[np.argmax(areas_cnt_text)]
@ -131,7 +138,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
# contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
if len(contours_combined)==1:
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
elif len(contours_combined)==2:
all_found_textline_polygons[int(region_final)].insert(arg_min, polygons_of_drop_capitals[i_drop] )
else:
pass
except:
# print('gordun1')
@ -167,14 +179,13 @@ def adhere_drop_capital_region_into_corresponding_textline(
img_textlines = img_textlines.astype(np.uint8)
# plt.imshow(img_textlines)
# plt.show()
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_combined = return_contours_of_interested_region(img_textlines, 255, 0)
##imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
##ret, thresh = cv2.threshold(imgray, 0, 255, 0)
##contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
contours_biggest = contours_combined[np.argmax(areas_cnt_text)]
@ -186,7 +197,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
# print(np.shape(contours_biggest),'contours_biggest')
# print(np.shape(all_found_textline_polygons[int(region_final)][arg_min]))
##contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
if len(contours_combined)==1:
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
elif len(contours_combined)==2:
all_found_textline_polygons[int(region_final)].insert(arg_min, polygons_of_drop_capitals[i_drop] )
else:
pass
except:
pass
@ -215,10 +231,11 @@ def adhere_drop_capital_region_into_corresponding_textline(
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined = return_contours_of_interested_region(img_textlines, 255, 0)
#imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
#ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -231,7 +248,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
contours_biggest[:, 0, 1] = contours_biggest[:, 0, 1] # -all_box_coord[int(region_final)][0]
##contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
if len(contours_combined)==1:
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
elif len(contours_combined)==2:
all_found_textline_polygons[int(region_final)].insert(arg_min, polygons_of_drop_capitals[i_drop] )
else:
pass
# all_found_textline_polygons[int(region_final)][arg_min]=contours_biggest
except:
@ -320,10 +342,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined = return_contours_of_interested_region(img_textlines, 255, 0)
#imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
#ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -336,8 +360,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
contours_biggest[:, 0, 1] = contours_biggest[:, 0, 1] - all_box_coord[int(region_final)][0]
contours_biggest = contours_biggest.reshape(np.shape(contours_biggest)[0], np.shape(contours_biggest)[2])
if len(contours_combined)==1:
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
elif len(contours_combined)==2:
all_found_textline_polygons[int(region_final)].insert(arg_min, polygons_of_drop_capitals[i_drop] )
else:
pass
except:
# print('gordun1')
@ -375,10 +403,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined = return_contours_of_interested_region(img_textlines, 255, 0)
#imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
#ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -391,7 +421,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
contours_biggest[:, 0, 1] = contours_biggest[:, 0, 1] - all_box_coord[int(region_final)][0]
contours_biggest = contours_biggest.reshape(np.shape(contours_biggest)[0], np.shape(contours_biggest)[2])
if len(contours_combined)==1:
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
elif len(contours_combined)==2:
all_found_textline_polygons[int(region_final)].insert(arg_min, polygons_of_drop_capitals[i_drop] )
else:
pass
# all_found_textline_polygons[int(region_final)][arg_min]=contours_biggest
except:

6
src/eynollah/writer.py
Unescape Escape View File

@ -285,9 +285,9 @@ class EynollahXmlWriter():
dropcapital = TextRegionType(id=counter.next_region_id, type_='drop-capital',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_drop_capitals[mm], page_coord)))
page.add_TextRegion(dropcapital)
all_box_coord_drop = None
slopes_drop = None
self.serialize_lines_in_dropcapital(dropcapital, [found_polygons_drop_capitals[mm]], mm, page_coord, all_box_coord_drop, slopes_drop, counter, ocr_all_textlines_textregion=None)
###all_box_coord_drop = None
###slopes_drop = None
###self.serialize_lines_in_dropcapital(dropcapital, [found_polygons_drop_capitals[mm]], mm, page_coord, all_box_coord_drop, slopes_drop, counter, ocr_all_textlines_textregion=None)
for mm in range(len(found_polygons_text_region_img)):
page.add_ImageRegion(ImageRegionType(id=counter.next_region_id, Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region_img[mm], page_coord))))

Write Preview
Loading…
Cancel
Save