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

eynollah, drop_capitals: simplify

Browse source 
- use new `find_center_of_contours`
This commit is contained in:
Robert Sachunsky 2025-10-02 21:36:22 +02:00
parent 3f3353ec3a
commit 415b2cbad8
2 changed files with 22 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

21
src/eynollah/eynollah.py
View file

@ -70,6 +70,7 @@ from .utils.contour import (
filter_contours_area_of_image, filter_contours_area_of_image,
filter_contours_area_of_image_tables, filter_contours_area_of_image_tables,
find_contours_mean_y_diff, find_contours_mean_y_diff,
find_center_of_contours,
find_new_features_of_contours, find_new_features_of_contours,
find_features_of_contours, find_features_of_contours,
get_text_region_boxes_by_given_contours, get_text_region_boxes_by_given_contours,
@ -1859,14 +1860,10 @@ class Eynollah:
def get_slopes_and_deskew_new_light2(self, contours, contours_par, textline_mask_tot, boxes, slope_deskew): def get_slopes_and_deskew_new_light2(self, contours, contours_par, textline_mask_tot, boxes, slope_deskew):
polygons_of_textlines = return_contours_of_interested_region(textline_mask_tot,1,0.00001) polygons_of_textlines = return_contours_of_interested_region(textline_mask_tot,1,0.00001)
M_main_tot = [cv2.moments(polygons_of_textlines[j]) cx_main_tot, cy_main_tot = find_center_of_contours(polygons_of_textlines)
for j in range(len(polygons_of_textlines))] w_h_textlines = [cv2.boundingRect(polygon)[2:] for polygon in polygons_of_textlines]
w_h_textlines = [cv2.boundingRect(polygons_of_textlines[i])[2:] for i in range(len(polygons_of_textlines))] args_textlines = np.arange(len(polygons_of_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))]
args_textlines = np.array(range(len(polygons_of_textlines)))
all_found_textline_polygons = [] all_found_textline_polygons = []
slopes = [] slopes = []
all_box_coord =[] all_box_coord =[]
@ -4809,8 +4806,8 @@ class Eynollah:
areas_cnt_text_parent = self.return_list_of_contours_with_desired_order( areas_cnt_text_parent = self.return_list_of_contours_with_desired_order(
areas_cnt_text_parent, index_con_parents) areas_cnt_text_parent, index_con_parents)
cx_bigest_big, cy_biggest_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest]) cx_bigest_big, cy_biggest_big = find_center_of_contours([contours_biggest])
cx_bigest, cy_biggest, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent) cx_bigest, cy_biggest = find_center_of_contours(contours_only_text_parent)
if np.abs(slope_deskew) >= SLOPE_THRESHOLD: if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
contours_only_text_d, hir_on_text_d = return_contours_of_image(text_only_d) contours_only_text_d, hir_on_text_d = return_contours_of_image(text_only_d)
@ -4834,10 +4831,8 @@ class Eynollah:
areas_cnt_text_d = self.return_list_of_contours_with_desired_order( areas_cnt_text_d = self.return_list_of_contours_with_desired_order(
areas_cnt_text_d, index_con_parents_d) areas_cnt_text_d, index_con_parents_d)
cx_bigest_d_big, cy_biggest_d_big, _, _, _, _, _ = \ cx_bigest_d_big, cy_biggest_d_big = find_center_of_contours([contours_biggest_d])
find_new_features_of_contours([contours_biggest_d]) cx_bigest_d, cy_biggest_d = find_center_of_contours(contours_only_text_parent_d)
cx_bigest_d, cy_biggest_d, _, _, _, _, _ = \
find_new_features_of_contours(contours_only_text_parent_d)
try: try:
if len(cx_bigest_d) >= 5: if len(cx_bigest_d) >= 5:
cx_bigest_d_last5 = cx_bigest_d[-5:] cx_bigest_d_last5 = cx_bigest_d[-5:]

27
src/eynollah/utils/drop_capitals.py
View file

@ -1,6 +1,7 @@
import numpy as np import numpy as np
import cv2 import cv2
from .contour import ( from .contour import (
find_center_of_contours,
find_new_features_of_contours, find_new_features_of_contours,
return_contours_of_image, return_contours_of_image,
return_parent_contours, return_parent_contours,
@ -22,8 +23,8 @@ def adhere_drop_capital_region_into_corresponding_textline(
): ):
# print(np.shape(all_found_textline_polygons),np.shape(all_found_textline_polygons[3]),'all_found_textline_polygonsshape') # print(np.shape(all_found_textline_polygons),np.shape(all_found_textline_polygons[3]),'all_found_textline_polygonsshape')
# print(all_found_textline_polygons[3]) # print(all_found_textline_polygons[3])
cx_m, cy_m, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent) cx_m, cy_m = find_center_of_contours(contours_only_text_parent)
cx_h, cy_h, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent_h) cx_h, cy_h = find_center_of_contours(contours_only_text_parent_h)
cx_d, cy_d, _, _, y_min_d, y_max_d, _ = find_new_features_of_contours(polygons_of_drop_capitals) cx_d, cy_d, _, _, y_min_d, y_max_d, _ = find_new_features_of_contours(polygons_of_drop_capitals)
img_con_all = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3)) img_con_all = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
@ -89,9 +90,9 @@ def adhere_drop_capital_region_into_corresponding_textline(
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1 region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final') # print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) # cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
try: try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -153,9 +154,9 @@ def adhere_drop_capital_region_into_corresponding_textline(
# areas_main=np.array([cv2.contourArea(all_found_textline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_textline_polygons[int(region_final)]))]) # areas_main=np.array([cv2.contourArea(all_found_textline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_textline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) # cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
try: try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -208,7 +209,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
try: try:
# print(all_found_textline_polygons[j_cont][0]) # print(all_found_textline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -261,7 +262,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
else: else:
pass pass
##cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) ##cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
###print(all_box_coord[j_cont]) ###print(all_box_coord[j_cont])
###print(cx_t) ###print(cx_t)
###print(cy_t) ###print(cy_t)
@ -315,9 +316,9 @@ def adhere_drop_capital_region_into_corresponding_textline(
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1 region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final') # print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) # cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
try: try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -375,12 +376,12 @@ def adhere_drop_capital_region_into_corresponding_textline(
# areas_main=np.array([cv2.contourArea(all_found_textline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_textline_polygons[int(region_final)]))]) # areas_main=np.array([cv2.contourArea(all_found_textline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_textline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) # cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
# print(cx_t,'print') # print(cx_t,'print')
try: try:
# print(all_found_textline_polygons[j_cont][0]) # print(all_found_textline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)]) cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont]) # print(all_box_coord[j_cont])
# print(cx_t) # print(cx_t)
# print(cy_t) # print(cy_t)
@ -453,7 +454,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
#####try: #####try:
#####if len(contours_new_parent)==1: #####if len(contours_new_parent)==1:
######print(all_found_textline_polygons[j_cont][0]) ######print(all_found_textline_polygons[j_cont][0])
#####cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[j_cont]) #####cx_t, cy_t = find_center_of_contours(all_found_textline_polygons[j_cont])
######print(all_box_coord[j_cont]) ######print(all_box_coord[j_cont])
######print(cx_t) ######print(cx_t)
######print(cy_t) ######print(cy_t)