qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-09 20:29:55 +02:00
Code Issues Projects Releases Wiki Activity

typo: s,hierachy,hierarchy,

Browse source
This commit is contained in:
Konstantin Baierer 2021-03-01 17:53:47 +01:00
parent 6036478889
commit ec9939c3c7
5 changed files with 28 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

12
qurator/eynollah/eynollah.py
View file

@ -833,8 +833,8 @@ class Eynollah:
slope_for_all = [slope_deskew][0] slope_for_all = [slope_deskew][0]
else: else:
try: try:
textline_con, hierachy = return_contours_of_image(img_int_p) textline_con, hierarchy = return_contours_of_image(img_int_p)
textline_con_fil = filter_contours_area_of_image(img_int_p, textline_con, hierachy, max_area=1, min_area=0.0008) textline_con_fil = filter_contours_area_of_image(img_int_p, textline_con, hierarchy, max_area=1, min_area=0.0008)
y_diff_mean = find_contours_mean_y_diff(textline_con_fil) y_diff_mean = find_contours_mean_y_diff(textline_con_fil)
sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0))) sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0)))
@ -944,8 +944,8 @@ class Eynollah:
bounding_box_of_textregion_per_each_subprocess.append(boxes_text[mv]) bounding_box_of_textregion_per_each_subprocess.append(boxes_text[mv])
else: else:
try: try:
textline_con, hierachy = return_contours_of_image(img_int_p) textline_con, hierarchy = return_contours_of_image(img_int_p)
textline_con_fil = filter_contours_area_of_image(img_int_p, textline_con, hierachy, max_area=1, min_area=0.00008) textline_con_fil = filter_contours_area_of_image(img_int_p, textline_con, hierarchy, max_area=1, min_area=0.00008)
y_diff_mean = find_contours_mean_y_diff(textline_con_fil) y_diff_mean = find_contours_mean_y_diff(textline_con_fil)
sigma_des = int(y_diff_mean * (4.0 / 40.0)) sigma_des = int(y_diff_mean * (4.0 / 40.0))
if sigma_des < 1: if sigma_des < 1:
@ -1018,8 +1018,8 @@ class Eynollah:
crop_img = crop_img[:, :, 0] crop_img = crop_img[:, :, 0]
crop_img = cv2.erode(crop_img, KERNEL, iterations=2) crop_img = cv2.erode(crop_img, KERNEL, iterations=2)
try: try:
textline_con, hierachy = return_contours_of_image(crop_img) textline_con, hierarchy = return_contours_of_image(crop_img)
textline_con_fil = filter_contours_area_of_image(crop_img, textline_con, hierachy, max_area=1, min_area=0.0008) textline_con_fil = filter_contours_area_of_image(crop_img, textline_con, hierarchy, max_area=1, min_area=0.0008)
y_diff_mean = find_contours_mean_y_diff(textline_con_fil) y_diff_mean = find_contours_mean_y_diff(textline_con_fil)
sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0))) sigma_des = max(1, int(y_diff_mean * (4.0 / 40.0)))
crop_img[crop_img > 0] = 1 crop_img[crop_img > 0] = 1

12
qurator/eynollah/utils/__init__.py
View file

@ -957,7 +957,7 @@ def small_textlines_to_parent_adherence2(textlines_con, textline_iamge, num_col)
img_text2 = img_text2.astype(np.uint8) img_text2 = img_text2.astype(np.uint8)
imgray = cv2.cvtColor(img_text2, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_text2, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont, hierachy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) cont, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(cont[0],type(cont)) # print(cont[0],type(cont))
@ -1187,7 +1187,7 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(im
imgray = cv2.cvtColor(img_p_in_ver, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_p_in_ver, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_lines_ver,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) contours_lines_ver,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
slope_lines_ver,dist_x_ver, x_min_main_ver ,x_max_main_ver ,cy_main_ver,slope_lines_org_ver,y_min_main_ver, y_max_main_ver, cx_main_ver=find_features_of_lines(contours_lines_ver) slope_lines_ver,dist_x_ver, x_min_main_ver ,x_max_main_ver ,cy_main_ver,slope_lines_org_ver,y_min_main_ver, y_max_main_ver, cx_main_ver=find_features_of_lines(contours_lines_ver)
@ -1201,7 +1201,7 @@ def combine_hor_lines_and_delete_cross_points_and_get_lines_features_back_new(im
imgray = cv2.cvtColor(img_in_hor, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_in_hor, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_lines_hor,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) contours_lines_hor,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
slope_lines_hor,dist_x_hor, x_min_main_hor ,x_max_main_hor ,cy_main_hor,slope_lines_org_hor,y_min_main_hor, y_max_main_hor, cx_main_hor=find_features_of_lines(contours_lines_hor) slope_lines_hor,dist_x_hor, x_min_main_hor ,x_max_main_hor ,cy_main_hor,slope_lines_org_hor,y_min_main_hor, y_max_main_hor, cx_main_hor=find_features_of_lines(contours_lines_hor)
@ -1335,7 +1335,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
ret_e, thresh_e = cv2.threshold(imgray_e, 0, 255, 0) ret_e, thresh_e = cv2.threshold(imgray_e, 0, 255, 0)
#print('burda3') #print('burda3')
contours_line_e,hierachy_e=cv2.findContours(thresh_e,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) contours_line_e,hierarchy_e=cv2.findContours(thresh_e,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
#slope_lines_e,dist_x_e, x_min_main_e ,x_max_main_e ,cy_main_e,slope_lines_org_e,y_min_main_e, y_max_main_e, cx_main_e=self.find_features_of_lines(contours_line_e) #slope_lines_e,dist_x_e, x_min_main_e ,x_max_main_e ,cy_main_e,slope_lines_org_e,y_min_main_e, y_max_main_e, cx_main_e=self.find_features_of_lines(contours_line_e)
@ -1442,7 +1442,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
imgray = cv2.cvtColor(vertical, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(vertical, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_line_vers,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) contours_line_vers,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
slope_lines,dist_x, x_min_main ,x_max_main ,cy_main,slope_lines_org,y_min_main, y_max_main, cx_main=find_features_of_lines(contours_line_vers) slope_lines,dist_x, x_min_main ,x_max_main ,cy_main,slope_lines_org,y_min_main, y_max_main, cx_main=find_features_of_lines(contours_line_vers)
#print(slope_lines,'vertical') #print(slope_lines,'vertical')
args=np.array( range(len(slope_lines) )) args=np.array( range(len(slope_lines) ))
@ -1465,7 +1465,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, pixel_l
imgray = cv2.cvtColor(horizontal, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(horizontal, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_line_hors,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) contours_line_hors,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
slope_lines,dist_x, x_min_main ,x_max_main ,cy_main,slope_lines_org,y_min_main, y_max_main, cx_main=find_features_of_lines(contours_line_hors) slope_lines,dist_x, x_min_main ,x_max_main ,cy_main,slope_lines_org,y_min_main, y_max_main, cx_main=find_features_of_lines(contours_line_hors)
slope_lines_org_hor=slope_lines_org[slope_lines==0] slope_lines_org_hor=slope_lines_org[slope_lines==0]

4
qurator/eynollah/utils/contour.py
View file

@ -194,8 +194,8 @@ def return_contours_of_image(image):
image = image.astype(np.uint8) image = image.astype(np.uint8)
imgray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours, hierachy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
return contours, hierachy return contours, hierarchy
def return_contours_of_interested_region_by_min_size(region_pre_p, pixel, min_size=0.00003): def return_contours_of_interested_region_by_min_size(region_pre_p, pixel, min_size=0.00003):

16
qurator/eynollah/utils/drop_capitals.py
View file

@ -117,7 +117,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierachy = 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') # print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))]) areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -172,7 +172,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierachy = 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') # print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))]) areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -217,7 +217,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierachy = 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') # print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))]) areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -267,7 +267,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
##imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY) ##imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
##ret, thresh = cv2.threshold(imgray, 0, 255, 0) ##ret, thresh = cv2.threshold(imgray, 0, 255, 0)
##contours_combined,hierachy=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') ##print(len(contours_combined),'len textlines mixed')
##areas_cnt_text=np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))]) ##areas_cnt_text=np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -322,7 +322,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierachy = 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') # print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))]) areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -377,7 +377,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY) imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0) ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierachy = 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') # print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))]) areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
@ -408,7 +408,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
######imgray = cv2.cvtColor(img_con, cv2.COLOR_BGR2GRAY) ######imgray = cv2.cvtColor(img_con, cv2.COLOR_BGR2GRAY)
######ret, thresh = cv2.threshold(imgray, 0, 255, 0) ######ret, thresh = cv2.threshold(imgray, 0, 255, 0)
######contours_new,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) ######contours_new,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
#####contours_new,hir_new=return_contours_of_image(img_con) #####contours_new,hir_new=return_contours_of_image(img_con)
#####contours_new_parent=return_parent_contours( contours_new,hir_new) #####contours_new_parent=return_parent_contours( contours_new,hir_new)
@ -442,7 +442,7 @@ def adhere_drop_capital_region_into_corresponding_textline(
#####imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY) #####imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
#####ret, thresh = cv2.threshold(imgray, 0, 255, 0) #####ret, thresh = cv2.threshold(imgray, 0, 255, 0)
#####contours_combined,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE) #####contours_combined,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
#####areas_cnt_text=np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))]) #####areas_cnt_text=np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])

12
qurator/eynollah/utils/separate_lines.py
View file

@ -102,8 +102,8 @@ def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
else: else:
peaks_new_tot = peaks_e[:] peaks_new_tot = peaks_e[:]
textline_con, hierachy = return_contours_of_image(img_patch) textline_con, hierarchy = return_contours_of_image(img_patch)
textline_con_fil = filter_contours_area_of_image(img_patch, textline_con, hierachy, max_area=1, min_area=0.0008) textline_con_fil = filter_contours_area_of_image(img_patch, textline_con, hierarchy, max_area=1, min_area=0.0008)
y_diff_mean = np.mean(np.diff(peaks_new_tot)) # self.find_contours_mean_y_diff(textline_con_fil) y_diff_mean = np.mean(np.diff(peaks_new_tot)) # self.find_contours_mean_y_diff(textline_con_fil)
sigma_gaus = int(y_diff_mean * (7.0 / 40.0)) sigma_gaus = int(y_diff_mean * (7.0 / 40.0))
@ -219,8 +219,8 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
peaks_new_tot=peaks_e[:] peaks_new_tot=peaks_e[:]
textline_con,hierachy=return_contours_of_image(img_patch) textline_con,hierarchy=return_contours_of_image(img_patch)
textline_con_fil=filter_contours_area_of_image(img_patch,textline_con,hierachy,max_area=1,min_area=0.0008) textline_con_fil=filter_contours_area_of_image(img_patch,textline_con,hierarchy,max_area=1,min_area=0.0008)
y_diff_mean=np.mean(np.diff(peaks_new_tot))#self.find_contours_mean_y_diff(textline_con_fil) y_diff_mean=np.mean(np.diff(peaks_new_tot))#self.find_contours_mean_y_diff(textline_con_fil)
sigma_gaus=int( y_diff_mean * (7./40.0) ) sigma_gaus=int( y_diff_mean * (7./40.0) )
@ -1054,8 +1054,8 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
else: else:
peaks_new_tot = peaks_e[:] peaks_new_tot = peaks_e[:]
textline_con, hierachy = return_contours_of_image(img_patch) textline_con, hierarchy = return_contours_of_image(img_patch)
textline_con_fil = filter_contours_area_of_image(img_patch, textline_con, hierachy, max_area=1, min_area=0.0008) textline_con_fil = filter_contours_area_of_image(img_patch, textline_con, hierarchy, max_area=1, min_area=0.0008)
y_diff_mean = np.mean(np.diff(peaks_new_tot)) # self.find_contours_mean_y_diff(textline_con_fil) y_diff_mean = np.mean(np.diff(peaks_new_tot)) # self.find_contours_mean_y_diff(textline_con_fil)
sigma_gaus = int(y_diff_mean * (7.0 / 40.0)) sigma_gaus = int(y_diff_mean * (7.0 / 40.0))