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

factor more methods out of utils

Browse Source
pull/8/head
Konstantin Baierer 4 years ago
parent 8c72f8bc03
commit fb247dafc2
9 changed files with 3086 additions and 3027 deletions
Show Stats Download Patch File Download Diff File

493
sbb_newspapers_org_image/eynollah.py
Unescape Escape View File

@ -39,6 +39,7 @@ from .utils.contour import (
contours_in_same_horizon, contours_in_same_horizon,
filter_contours_area_of_image_interiors, filter_contours_area_of_image_interiors,
filter_contours_area_of_image_tables, filter_contours_area_of_image_tables,
filter_contours_area_of_image,
find_contours_mean_y_diff, find_contours_mean_y_diff,
find_features_of_contours, find_features_of_contours,
find_new_features_of_contoures, find_new_features_of_contoures,
@ -74,10 +75,14 @@ from .utils.separate_lines import (
seperate_lines_vertical_cont, seperate_lines_vertical_cont,
) )
from .utils.drop_capitals import (
adhere_drop_capital_region_into_cprresponding_textline,
filter_small_drop_capitals_from_no_patch_layout
)
from .utils import ( from .utils import (
boosting_headers_by_longshot_region_segmentation, boosting_headers_by_longshot_region_segmentation,
crop_image_inside_box, crop_image_inside_box,
filter_small_drop_capitals_from_no_patch_layout,
find_features_of_lines, find_features_of_lines,
find_num_col, find_num_col,
find_num_col_by_vertical_lines, find_num_col_by_vertical_lines,
@ -2788,10 +2793,10 @@ class eynollah:
median_blur=False median_blur=False
img= self.resize_image(img_org, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x)) img= resize_image(img_org, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x))
if binary: if binary:
img = self.otsu_copy_binary(img)#self.otsu_copy(img) img = otsu_copy_binary(img)#self.otsu_copy(img)
img = img.astype(np.uint16) img = img.astype(np.uint16)
if median_blur: if median_blur:
@ -2801,7 +2806,7 @@ class eynollah:
img = img.astype(np.uint16) img = img.astype(np.uint16)
prediction_regions_org_y=self.do_prediction(patches,img,model_region) prediction_regions_org_y=self.do_prediction(patches,img,model_region)
prediction_regions_org_y=self.resize_image(prediction_regions_org_y, img_height_h, img_width_h ) prediction_regions_org_y = resize_image(prediction_regions_org_y, img_height_h, img_width_h )
#plt.imshow(prediction_regions_org_y[:,:,0]) #plt.imshow(prediction_regions_org_y[:,:,0])
#plt.show() #plt.show()
@ -2823,10 +2828,10 @@ class eynollah:
ratio_y=1 ratio_y=1
median_blur=False median_blur=False
img= self.resize_image(img_org, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x)) img= resize_image(img_org, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x))
if binary: if binary:
img = self.otsu_copy_binary(img)#self.otsu_copy(img) img = otsu_copy_binary(img)#self.otsu_copy(img)
img = img.astype(np.uint16) img = img.astype(np.uint16)
if median_blur: if median_blur:
@ -2836,7 +2841,7 @@ class eynollah:
img = img.astype(np.uint16) img = img.astype(np.uint16)
prediction_regions_org=self.do_prediction(patches,img,model_region) prediction_regions_org=self.do_prediction(patches,img,model_region)
prediction_regions_org=self.resize_image(prediction_regions_org, img_height_h, img_width_h ) prediction_regions_org=resize_image(prediction_regions_org, img_height_h, img_width_h )
##plt.imshow(prediction_regions_org[:,:,0]) ##plt.imshow(prediction_regions_org[:,:,0])
##plt.show() ##plt.show()
@ -2863,10 +2868,10 @@ class eynollah:
ratio_y=1 ratio_y=1
median_blur=False median_blur=False
img= self.resize_image(img_org, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x)) img= resize_image(img_org, int(img_org.shape[0]*ratio_y), int(img_org.shape[1]*ratio_x))
if binary: if binary:
img = self.otsu_copy_binary(img)#self.otsu_copy(img) img = otsu_copy_binary(img)#self.otsu_copy(img)
img = img.astype(np.uint16) img = img.astype(np.uint16)
if median_blur: if median_blur:
@ -2878,7 +2883,7 @@ class eynollah:
marginal_patch=0.2 marginal_patch=0.2
prediction_regions_org2=self.do_prediction(patches,img,model_region,marginal_patch) prediction_regions_org2=self.do_prediction(patches,img,model_region,marginal_patch)
prediction_regions_org2=self.resize_image(prediction_regions_org2, img_height_h, img_width_h ) prediction_regions_org2=resize_image(prediction_regions_org2, img_height_h, img_width_h )
#plt.imshow(prediction_regions_org2[:,:,0]) #plt.imshow(prediction_regions_org2[:,:,0])
#plt.show() #plt.show()
@ -2998,11 +3003,11 @@ class eynollah:
pixel_img=1 pixel_img=1
min_area_text=0.00001 min_area_text=0.00001
polygons_of_only_texts=self.return_contours_of_interested_region(mask_texts_only,pixel_img,min_area_text) polygons_of_only_texts=return_contours_of_interested_region(mask_texts_only,pixel_img,min_area_text)
polygons_of_only_images=self.return_contours_of_interested_region(mask_images_only,pixel_img) polygons_of_only_images=return_contours_of_interested_region(mask_images_only,pixel_img)
polygons_of_only_lines=self.return_contours_of_interested_region(mask_lines_only,pixel_img,min_area_text) polygons_of_only_lines=return_contours_of_interested_region(mask_lines_only,pixel_img,min_area_text)
text_regions_p_true=np.zeros(prediction_regions_org.shape) text_regions_p_true=np.zeros(prediction_regions_org.shape)
@ -3065,13 +3070,13 @@ class eynollah:
if text_with_lines.shape[0]<=1500: if text_with_lines.shape[0]<=1500:
pass pass
elif text_with_lines.shape[0]>1500 and text_with_lines.shape[0]<=1800: elif text_with_lines.shape[0]>1500 and text_with_lines.shape[0]<=1800:
text_with_lines=self.resize_image(text_with_lines,int(text_with_lines.shape[0]*1.5),text_with_lines.shape[1]) text_with_lines=resize_image(text_with_lines,int(text_with_lines.shape[0]*1.5),text_with_lines.shape[1])
text_with_lines=cv2.erode(text_with_lines,self.kernel,iterations=5) text_with_lines=cv2.erode(text_with_lines,self.kernel,iterations=5)
text_with_lines=self.resize_image(text_with_lines,text_with_lines_eroded.shape[0],text_with_lines_eroded.shape[1]) text_with_lines=resize_image(text_with_lines,text_with_lines_eroded.shape[0],text_with_lines_eroded.shape[1])
else: else:
text_with_lines=self.resize_image(text_with_lines,int(text_with_lines.shape[0]*1.8),text_with_lines.shape[1]) text_with_lines=resize_image(text_with_lines,int(text_with_lines.shape[0]*1.8),text_with_lines.shape[1])
text_with_lines=cv2.erode(text_with_lines,self.kernel,iterations=7) text_with_lines=cv2.erode(text_with_lines,self.kernel,iterations=7)
text_with_lines=self.resize_image(text_with_lines,text_with_lines_eroded.shape[0],text_with_lines_eroded.shape[1]) text_with_lines=resize_image(text_with_lines,text_with_lines_eroded.shape[0],text_with_lines_eroded.shape[1])
text_with_lines_y=text_with_lines.sum(axis=0) text_with_lines_y=text_with_lines.sum(axis=0)
@ -3193,7 +3198,7 @@ class eynollah:
mask_marginals[:,:]=1 mask_marginals[:,:]=1
#print(mask_marginals.shape,point_left,point_right,'nadosh') #print(mask_marginals.shape,point_left,point_right,'nadosh')
mask_marginals_rotated=self.rotate_image(mask_marginals,-slope_deskew) mask_marginals_rotated=rotate_image(mask_marginals,-slope_deskew)
#print(mask_marginals_rotated.shape,'nadosh') #print(mask_marginals_rotated.shape,'nadosh')
mask_marginals_rotated_sum=mask_marginals_rotated.sum(axis=0) mask_marginals_rotated_sum=mask_marginals_rotated.sum(axis=0)
@ -3227,9 +3232,9 @@ class eynollah:
pixel_img=4 pixel_img=4
min_area_text=0.00001 min_area_text=0.00001
polygons_of_marginals=self.return_contours_of_interested_region(text_regions,pixel_img,min_area_text) polygons_of_marginals=return_contours_of_interested_region(text_regions,pixel_img,min_area_text)
cx_text_only,cy_text_only ,x_min_text_only,x_max_text_only, y_min_text_only ,y_max_text_only,y_cor_x_min_main=self.find_new_features_of_contoures(polygons_of_marginals) cx_text_only,cy_text_only ,x_min_text_only,x_max_text_only, y_min_text_only ,y_max_text_only,y_cor_x_min_main=find_new_features_of_contoures(polygons_of_marginals)
text_regions[(text_regions[:,:]==4)]=1 text_regions[(text_regions[:,:]==4)]=1
@ -3578,452 +3583,6 @@ class eynollah:
return order_text_new, id_of_texts_tot return order_text_new, id_of_texts_tot
def adhere_drop_capital_region_into_cprresponding_textline(self, 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_texline_polygons, all_found_texline_polygons_h):
# print(np.shape(all_found_texline_polygons),np.shape(all_found_texline_polygons[3]),'all_found_texline_polygonsshape')
# print(all_found_texline_polygons[3])
cx_m, cy_m, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent)
cx_h, cy_h, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent_h)
cx_d, cy_d, _, _, y_min_d, y_max_d, _ = find_new_features_of_contoures(polygons_of_drop_capitals)
img_con_all = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
for j_cont in range(len(contours_only_text_parent)):
img_con_all[all_box_coord[j_cont][0] : all_box_coord[j_cont][1], all_box_coord[j_cont][2] : all_box_coord[j_cont][3], 0] = (j_cont + 1) * 3
# img_con_all=cv2.fillPoly(img_con_all,pts=[contours_only_text_parent[j_cont]],color=((j_cont+1)*3,(j_cont+1)*3,(j_cont+1)*3))
# plt.imshow(img_con_all[:,:,0])
# plt.show()
# img_con_all=cv2.dilate(img_con_all, self.kernel, iterations=3)
# plt.imshow(img_con_all[:,:,0])
# plt.show()
# print(np.unique(img_con_all[:,:,0]))
for i_drop in range(len(polygons_of_drop_capitals)):
# print(i_drop,'i_drop')
img_con_all_copy = np.copy(img_con_all)
img_con = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_con = cv2.fillPoly(img_con, pts=[polygons_of_drop_capitals[i_drop]], color=(1, 1, 1))
# plt.imshow(img_con[:,:,0])
# plt.show()
##img_con=cv2.dilate(img_con, self.kernel, iterations=30)
# plt.imshow(img_con[:,:,0])
# plt.show()
# print(np.unique(img_con[:,:,0]))
img_con_all_copy[:, :, 0] = img_con_all_copy[:, :, 0] + img_con[:, :, 0]
img_con_all_copy[:, :, 0][img_con_all_copy[:, :, 0] == 1] = 0
kherej_ghesmat = np.unique(img_con_all_copy[:, :, 0]) / 3
res_summed_pixels = np.unique(img_con_all_copy[:, :, 0]) % 3
region_with_intersected_drop = kherej_ghesmat[res_summed_pixels == 1]
# region_with_intersected_drop=region_with_intersected_drop/3
region_with_intersected_drop = region_with_intersected_drop.astype(np.uint8)
# print(len(region_with_intersected_drop),'region_with_intersected_drop1')
if len(region_with_intersected_drop) == 0:
img_con_all_copy = np.copy(img_con_all)
img_con = cv2.dilate(img_con, self.kernel, iterations=4)
img_con_all_copy[:, :, 0] = img_con_all_copy[:, :, 0] + img_con[:, :, 0]
img_con_all_copy[:, :, 0][img_con_all_copy[:, :, 0] == 1] = 0
kherej_ghesmat = np.unique(img_con_all_copy[:, :, 0]) / 3
res_summed_pixels = np.unique(img_con_all_copy[:, :, 0]) % 3
region_with_intersected_drop = kherej_ghesmat[res_summed_pixels == 1]
# 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 self.curved_line:
if len(region_with_intersected_drop) > 1:
sum_pixels_of_intersection = []
for i in range(len(region_with_intersected_drop)):
# print((region_with_intersected_drop[i]*3+1))
sum_pixels_of_intersection.append(((img_con_all_copy[:, :, 0] == (region_with_intersected_drop[i] * 3 + 1)) * 1).sum())
# print(sum_pixels_of_intersection)
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = np.array(cy_t) # all_box_coord[int(region_final)][0]+np.array(cy_t)
# print(y_lines)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
# contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
# 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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
except:
# print('gordun1')
pass
elif len(region_with_intersected_drop) == 1:
region_final = region_with_intersected_drop[0] - 1
# areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = np.array(cy_t) # all_box_coord[int(region_final)][0]+np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
# contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
# contours_biggest[:,0,1]=contours_biggest[:,0,1]#-all_box_coord[int(region_final)][0]
# print(np.shape(contours_biggest),'contours_biggest')
# print(np.shape(all_found_texline_polygons[int(region_final)][arg_min]))
##contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
# print(cx_t,'print')
try:
# print(all_found_texline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] # -all_box_coord[int(region_final)][2]
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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
# all_found_texline_polygons[int(region_final)][arg_min]=contours_biggest
except:
pass
else:
pass
##cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
###print(all_box_coord[j_cont])
###print(cx_t)
###print(cy_t)
###print(cx_d[i_drop])
###print(cy_d[i_drop])
##y_lines=all_box_coord[int(region_final)][0]+np.array(cy_t)
##y_lines[y_lines<y_min_d[i_drop]]=0
###print(y_lines)
##arg_min=np.argmin(np.abs(y_lines-y_min_d[i_drop]) )
###print(arg_min)
##cnt_nearest=np.copy(all_found_texline_polygons[int(region_final)][arg_min])
##cnt_nearest[:,0,0]=all_found_texline_polygons[int(region_final)][arg_min][:,0,0]#+all_box_coord[int(region_final)][2]
##cnt_nearest[:,0,1]=all_found_texline_polygons[int(region_final)][arg_min][:,0,1]#+all_box_coord[int(region_final)][0]
##img_textlines=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
##img_textlines=cv2.fillPoly(img_textlines,pts=[cnt_nearest],color=(255,255,255))
##img_textlines=cv2.fillPoly(img_textlines,pts=[polygons_of_drop_capitals[i_drop] ],color=(255,255,255))
##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,hierachy=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)]
###print(np.shape(contours_biggest))
###print(contours_biggest[:])
##contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
##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])
##all_found_texline_polygons[int(region_final)][arg_min]=contours_biggest
else:
if len(region_with_intersected_drop) > 1:
sum_pixels_of_intersection = []
for i in range(len(region_with_intersected_drop)):
# print((region_with_intersected_drop[i]*3+1))
sum_pixels_of_intersection.append(((img_con_all_copy[:, :, 0] == (region_with_intersected_drop[i] * 3 + 1)) * 1).sum())
# print(sum_pixels_of_intersection)
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
# print(y_lines)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0] + all_box_coord[int(region_final)][2]
cnt_nearest[:, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 1] + all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] - all_box_coord[int(region_final)][2]
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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
except:
# print('gordun1')
pass
elif len(region_with_intersected_drop) == 1:
region_final = region_with_intersected_drop[0] - 1
# areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(cx_t,'print')
try:
# print(all_found_texline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0] + all_box_coord[int(region_final)][2]
cnt_nearest[:, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 1] + all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] - all_box_coord[int(region_final)][2]
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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
# all_found_texline_polygons[int(region_final)][arg_min]=contours_biggest
except:
pass
else:
pass
#####for i_drop in range(len(polygons_of_drop_capitals)):
#####for j_cont in range(len(contours_only_text_parent)):
#####img_con=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
#####img_con=cv2.fillPoly(img_con,pts=[polygons_of_drop_capitals[i_drop] ],color=(255,255,255))
#####img_con=cv2.fillPoly(img_con,pts=[contours_only_text_parent[j_cont]],color=(255,255,255))
#####img_con=img_con.astype(np.uint8)
######imgray = cv2.cvtColor(img_con, cv2.COLOR_BGR2GRAY)
######ret, thresh = cv2.threshold(imgray, 0, 255, 0)
######contours_new,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
#####contours_new,hir_new=return_contours_of_image(img_con)
#####contours_new_parent=return_parent_contours( contours_new,hir_new)
######plt.imshow(img_con)
######plt.show()
#####try:
#####if len(contours_new_parent)==1:
######print(all_found_texline_polygons[j_cont][0])
#####cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[j_cont])
######print(all_box_coord[j_cont])
######print(cx_t)
######print(cy_t)
######print(cx_d[i_drop])
######print(cy_d[i_drop])
#####y_lines=all_box_coord[j_cont][0]+np.array(cy_t)
######print(y_lines)
#####arg_min=np.argmin(np.abs(y_lines-y_min_d[i_drop]) )
######print(arg_min)
#####cnt_nearest=np.copy(all_found_texline_polygons[j_cont][arg_min])
#####cnt_nearest[:,0]=all_found_texline_polygons[j_cont][arg_min][:,0]+all_box_coord[j_cont][2]
#####cnt_nearest[:,1]=all_found_texline_polygons[j_cont][arg_min][:,1]+all_box_coord[j_cont][0]
#####img_textlines=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
#####img_textlines=cv2.fillPoly(img_textlines,pts=[cnt_nearest],color=(255,255,255))
#####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,hierachy=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))])
#####contours_biggest=contours_combined[np.argmax(areas_cnt_text)]
######print(np.shape(contours_biggest))
######print(contours_biggest[:])
#####contours_biggest[:,0,0]=contours_biggest[:,0,0]-all_box_coord[j_cont][2]
#####contours_biggest[:,0,1]=contours_biggest[:,0,1]-all_box_coord[j_cont][0]
#####all_found_texline_polygons[j_cont][arg_min]=contours_biggest
######print(contours_biggest)
######plt.imshow(img_textlines[:,:,0])
######plt.show()
#####else:
#####pass
#####except:
#####pass
return all_found_texline_polygons
def save_plot_of_layout_main(self, text_regions_p, image_page): def save_plot_of_layout_main(self, text_regions_p, image_page):
values = np.unique(text_regions_p[:, :]) values = np.unique(text_regions_p[:, :])
@ -4654,7 +4213,7 @@ class eynollah:
polygons_of_drop_capitals = return_contours_of_interested_region_by_min_size(text_regions_p, pixel_img) polygons_of_drop_capitals = return_contours_of_interested_region_by_min_size(text_regions_p, pixel_img)
# polygons_of_drop_capitals=[] # polygons_of_drop_capitals=[]
all_found_texline_polygons = self.adhere_drop_capital_region_into_cprresponding_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_texline_polygons, all_found_texline_polygons_h) all_found_texline_polygons = adhere_drop_capital_region_into_cprresponding_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_texline_polygons, all_found_texline_polygons_h, kernel=self.kernel, curved_line=self.curved_line)
# print(len(contours_only_text_parent_h),len(contours_only_text_parent_h_d_ordered),'contours_only_text_parent_h') # print(len(contours_only_text_parent_h),len(contours_only_text_parent_h_d_ordered),'contours_only_text_parent_h')
pixel_lines = 6 pixel_lines = 6

2470
sbb_newspapers_org_image/utils.py
View File

File diff suppressed because it is too large Load Diff

2436
sbb_newspapers_org_image/utils/__init__.py
View File

File diff suppressed because it is too large Load Diff

96
sbb_newspapers_org_image/utils/contour.py
Unescape Escape View File

@ -1,3 +1,9 @@
import cv2
import numpy as np
from shapely import geometry
from .rotate import rotate_image, rotation_image_new
def contours_in_same_horizon(cy_main_hor): def contours_in_same_horizon(cy_main_hor):
X1 = np.zeros((len(cy_main_hor), len(cy_main_hor))) X1 = np.zeros((len(cy_main_hor), len(cy_main_hor)))
X2 = np.zeros((len(cy_main_hor), len(cy_main_hor))) X2 = np.zeros((len(cy_main_hor), len(cy_main_hor)))
@ -290,93 +296,3 @@ def return_contours_of_interested_region_by_size(region_pre_p, pixel, min_area,
img_ret = cv2.fillPoly(img_ret, pts=contours_imgs, color=(1, 1, 1)) img_ret = cv2.fillPoly(img_ret, pts=contours_imgs, color=(1, 1, 1))
return img_ret[:, :, 0] return img_ret[:, :, 0]
def textline_contours_postprocessing(textline_mask, slope, contour_text_interest, box_ind, slope_first, add_boxes_coor_into_textlines=False):
textline_mask = np.repeat(textline_mask[:, :, np.newaxis], 3, axis=2) * 255
textline_mask = textline_mask.astype(np.uint8)
kernel = np.ones((5, 5), np.uint8)
textline_mask = cv2.morphologyEx(textline_mask, cv2.MORPH_OPEN, kernel)
textline_mask = cv2.morphologyEx(textline_mask, cv2.MORPH_CLOSE, kernel)
textline_mask = cv2.erode(textline_mask, kernel, iterations=2)
# textline_mask = cv2.erode(textline_mask, kernel, iterations=1)
# print(textline_mask.shape[0]/float(textline_mask.shape[1]),'miz')
try:
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(textline_mask)
# plt.show()
# if abs(slope)>1:
# x_help=30
# y_help=2
# else:
# x_help=2
# y_help=2
x_help = 30
y_help = 2
textline_mask_help = np.zeros((textline_mask.shape[0] + int(2 * y_help), textline_mask.shape[1] + int(2 * x_help), 3))
textline_mask_help[y_help : y_help + textline_mask.shape[0], x_help : x_help + textline_mask.shape[1], :] = np.copy(textline_mask[:, :, :])
dst = rotate_image(textline_mask_help, slope)
dst = dst[:, :, 0]
dst[dst != 0] = 1
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(dst)
# plt.show()
contour_text_copy = contour_text_interest.copy()
contour_text_copy[:, 0, 0] = contour_text_copy[:, 0, 0] - box_ind[0]
contour_text_copy[:, 0, 1] = contour_text_copy[:, 0, 1] - box_ind[1]
img_contour = np.zeros((box_ind[3], box_ind[2], 3))
img_contour = cv2.fillPoly(img_contour, pts=[contour_text_copy], color=(255, 255, 255))
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(img_contour)
# plt.show()
img_contour_help = np.zeros((img_contour.shape[0] + int(2 * y_help), img_contour.shape[1] + int(2 * x_help), 3))
img_contour_help[y_help : y_help + img_contour.shape[0], x_help : x_help + img_contour.shape[1], :] = np.copy(img_contour[:, :, :])
img_contour_rot = rotate_image(img_contour_help, slope)
# plt.imshow(img_contour_rot_help)
# plt.show()
# plt.imshow(dst_help)
# plt.show()
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(img_contour_rot_help)
# plt.show()
# plt.imshow(dst_help)
# plt.show()
img_contour_rot = img_contour_rot.astype(np.uint8)
# dst_help = dst_help.astype(np.uint8)
imgrayrot = cv2.cvtColor(img_contour_rot, cv2.COLOR_BGR2GRAY)
_, threshrot = cv2.threshold(imgrayrot, 0, 255, 0)
contours_text_rot, _ = cv2.findContours(threshrot.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
len_con_text_rot = [len(contours_text_rot[ib]) for ib in range(len(contours_text_rot))]
ind_big_con = np.argmax(len_con_text_rot)
# print('juzaa')
if abs(slope) > 45:
# print(add_boxes_coor_into_textlines,'avval')
_, contours_rotated_clean = seperate_lines_vertical_cont(textline_mask, contours_text_rot[ind_big_con], box_ind, slope, add_boxes_coor_into_textlines=add_boxes_coor_into_textlines)
else:
_, contours_rotated_clean = seperate_lines(dst, contours_text_rot[ind_big_con], slope, x_help, y_help)
except:
contours_rotated_clean = []
return contours_rotated_clean

501
sbb_newspapers_org_image/utils/drop_capitals.py
Unescape Escape View File

@ -0,0 +1,501 @@
import numpy as np
import cv2
from .contour import (
find_new_features_of_contoures,
return_contours_of_image,
return_parent_contours,
)
def adhere_drop_capital_region_into_cprresponding_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_texline_polygons,
all_found_texline_polygons_h,
kernel=None,
curved_line=False,
):
# print(np.shape(all_found_texline_polygons),np.shape(all_found_texline_polygons[3]),'all_found_texline_polygonsshape')
# print(all_found_texline_polygons[3])
cx_m, cy_m, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent)
cx_h, cy_h, _, _, _, _, _ = find_new_features_of_contoures(contours_only_text_parent_h)
cx_d, cy_d, _, _, y_min_d, y_max_d, _ = find_new_features_of_contoures(polygons_of_drop_capitals)
img_con_all = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
for j_cont in range(len(contours_only_text_parent)):
img_con_all[all_box_coord[j_cont][0] : all_box_coord[j_cont][1], all_box_coord[j_cont][2] : all_box_coord[j_cont][3], 0] = (j_cont + 1) * 3
# img_con_all=cv2.fillPoly(img_con_all,pts=[contours_only_text_parent[j_cont]],color=((j_cont+1)*3,(j_cont+1)*3,(j_cont+1)*3))
# plt.imshow(img_con_all[:,:,0])
# plt.show()
# img_con_all=cv2.dilate(img_con_all, kernel, iterations=3)
# plt.imshow(img_con_all[:,:,0])
# plt.show()
# print(np.unique(img_con_all[:,:,0]))
for i_drop in range(len(polygons_of_drop_capitals)):
# print(i_drop,'i_drop')
img_con_all_copy = np.copy(img_con_all)
img_con = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_con = cv2.fillPoly(img_con, pts=[polygons_of_drop_capitals[i_drop]], color=(1, 1, 1))
# plt.imshow(img_con[:,:,0])
# plt.show()
##img_con=cv2.dilate(img_con, kernel, iterations=30)
# plt.imshow(img_con[:,:,0])
# plt.show()
# print(np.unique(img_con[:,:,0]))
img_con_all_copy[:, :, 0] = img_con_all_copy[:, :, 0] + img_con[:, :, 0]
img_con_all_copy[:, :, 0][img_con_all_copy[:, :, 0] == 1] = 0
kherej_ghesmat = np.unique(img_con_all_copy[:, :, 0]) / 3
res_summed_pixels = np.unique(img_con_all_copy[:, :, 0]) % 3
region_with_intersected_drop = kherej_ghesmat[res_summed_pixels == 1]
# region_with_intersected_drop=region_with_intersected_drop/3
region_with_intersected_drop = region_with_intersected_drop.astype(np.uint8)
# print(len(region_with_intersected_drop),'region_with_intersected_drop1')
if len(region_with_intersected_drop) == 0:
img_con_all_copy = np.copy(img_con_all)
img_con = cv2.dilate(img_con, kernel, iterations=4)
img_con_all_copy[:, :, 0] = img_con_all_copy[:, :, 0] + img_con[:, :, 0]
img_con_all_copy[:, :, 0][img_con_all_copy[:, :, 0] == 1] = 0
kherej_ghesmat = np.unique(img_con_all_copy[:, :, 0]) / 3
res_summed_pixels = np.unique(img_con_all_copy[:, :, 0]) % 3
region_with_intersected_drop = kherej_ghesmat[res_summed_pixels == 1]
# 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 len(region_with_intersected_drop) > 1:
sum_pixels_of_intersection = []
for i in range(len(region_with_intersected_drop)):
# print((region_with_intersected_drop[i]*3+1))
sum_pixels_of_intersection.append(((img_con_all_copy[:, :, 0] == (region_with_intersected_drop[i] * 3 + 1)) * 1).sum())
# print(sum_pixels_of_intersection)
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = np.array(cy_t) # all_box_coord[int(region_final)][0]+np.array(cy_t)
# print(y_lines)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
# contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
# 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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
except:
# print('gordun1')
pass
elif len(region_with_intersected_drop) == 1:
region_final = region_with_intersected_drop[0] - 1
# areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = np.array(cy_t) # all_box_coord[int(region_final)][0]+np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
# contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
# contours_biggest[:,0,1]=contours_biggest[:,0,1]#-all_box_coord[int(region_final)][0]
# print(np.shape(contours_biggest),'contours_biggest')
# print(np.shape(all_found_texline_polygons[int(region_final)][arg_min]))
##contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
# print(cx_t,'print')
try:
# print(all_found_texline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] # -all_box_coord[int(region_final)][2]
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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
# all_found_texline_polygons[int(region_final)][arg_min]=contours_biggest
except:
pass
else:
pass
##cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
###print(all_box_coord[j_cont])
###print(cx_t)
###print(cy_t)
###print(cx_d[i_drop])
###print(cy_d[i_drop])
##y_lines=all_box_coord[int(region_final)][0]+np.array(cy_t)
##y_lines[y_lines<y_min_d[i_drop]]=0
###print(y_lines)
##arg_min=np.argmin(np.abs(y_lines-y_min_d[i_drop]) )
###print(arg_min)
##cnt_nearest=np.copy(all_found_texline_polygons[int(region_final)][arg_min])
##cnt_nearest[:,0,0]=all_found_texline_polygons[int(region_final)][arg_min][:,0,0]#+all_box_coord[int(region_final)][2]
##cnt_nearest[:,0,1]=all_found_texline_polygons[int(region_final)][arg_min][:,0,1]#+all_box_coord[int(region_final)][0]
##img_textlines=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
##img_textlines=cv2.fillPoly(img_textlines,pts=[cnt_nearest],color=(255,255,255))
##img_textlines=cv2.fillPoly(img_textlines,pts=[polygons_of_drop_capitals[i_drop] ],color=(255,255,255))
##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,hierachy=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)]
###print(np.shape(contours_biggest))
###print(contours_biggest[:])
##contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
##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])
##all_found_texline_polygons[int(region_final)][arg_min]=contours_biggest
else:
if len(region_with_intersected_drop) > 1:
sum_pixels_of_intersection = []
for i in range(len(region_with_intersected_drop)):
# print((region_with_intersected_drop[i]*3+1))
sum_pixels_of_intersection.append(((img_con_all_copy[:, :, 0] == (region_with_intersected_drop[i] * 3 + 1)) * 1).sum())
# print(sum_pixels_of_intersection)
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
# print(y_lines)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0] + all_box_coord[int(region_final)][2]
cnt_nearest[:, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 1] + all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] - all_box_coord[int(region_final)][2]
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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
except:
# print('gordun1')
pass
elif len(region_with_intersected_drop) == 1:
region_final = region_with_intersected_drop[0] - 1
# areas_main=np.array([cv2.contourArea(all_found_texline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_texline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(cx_t,'print')
try:
# print(all_found_texline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contoures(all_found_texline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_texline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0] = all_found_texline_polygons[int(region_final)][arg_min][:, 0] + all_box_coord[int(region_final)][2]
cnt_nearest[:, 1] = all_found_texline_polygons[int(region_final)][arg_min][:, 1] + all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
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, hierachy = 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)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] - all_box_coord[int(region_final)][2]
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])
all_found_texline_polygons[int(region_final)][arg_min] = contours_biggest
# all_found_texline_polygons[int(region_final)][arg_min]=contours_biggest
except:
pass
else:
pass
#####for i_drop in range(len(polygons_of_drop_capitals)):
#####for j_cont in range(len(contours_only_text_parent)):
#####img_con=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
#####img_con=cv2.fillPoly(img_con,pts=[polygons_of_drop_capitals[i_drop] ],color=(255,255,255))
#####img_con=cv2.fillPoly(img_con,pts=[contours_only_text_parent[j_cont]],color=(255,255,255))
#####img_con=img_con.astype(np.uint8)
######imgray = cv2.cvtColor(img_con, cv2.COLOR_BGR2GRAY)
######ret, thresh = cv2.threshold(imgray, 0, 255, 0)
######contours_new,hierachy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
#####contours_new,hir_new=return_contours_of_image(img_con)
#####contours_new_parent=return_parent_contours( contours_new,hir_new)
######plt.imshow(img_con)
######plt.show()
#####try:
#####if len(contours_new_parent)==1:
######print(all_found_texline_polygons[j_cont][0])
#####cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contoures(all_found_texline_polygons[j_cont])
######print(all_box_coord[j_cont])
######print(cx_t)
######print(cy_t)
######print(cx_d[i_drop])
######print(cy_d[i_drop])
#####y_lines=all_box_coord[j_cont][0]+np.array(cy_t)
######print(y_lines)
#####arg_min=np.argmin(np.abs(y_lines-y_min_d[i_drop]) )
######print(arg_min)
#####cnt_nearest=np.copy(all_found_texline_polygons[j_cont][arg_min])
#####cnt_nearest[:,0]=all_found_texline_polygons[j_cont][arg_min][:,0]+all_box_coord[j_cont][2]
#####cnt_nearest[:,1]=all_found_texline_polygons[j_cont][arg_min][:,1]+all_box_coord[j_cont][0]
#####img_textlines=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
#####img_textlines=cv2.fillPoly(img_textlines,pts=[cnt_nearest],color=(255,255,255))
#####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,hierachy=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))])
#####contours_biggest=contours_combined[np.argmax(areas_cnt_text)]
######print(np.shape(contours_biggest))
######print(contours_biggest[:])
#####contours_biggest[:,0,0]=contours_biggest[:,0,0]-all_box_coord[j_cont][2]
#####contours_biggest[:,0,1]=contours_biggest[:,0,1]-all_box_coord[j_cont][0]
#####all_found_texline_polygons[j_cont][arg_min]=contours_biggest
######print(contours_biggest)
######plt.imshow(img_textlines[:,:,0])
######plt.show()
#####else:
#####pass
#####except:
#####pass
return all_found_texline_polygons
def filter_small_drop_capitals_from_no_patch_layout(layout_no_patch, layout1):
drop_only = (layout_no_patch[:, :, 0] == 4) * 1
contours_drop, hir_on_drop = return_contours_of_image(drop_only)
contours_drop_parent = return_parent_contours(contours_drop, hir_on_drop)
areas_cnt_text = np.array([cv2.contourArea(contours_drop_parent[j]) for j in range(len(contours_drop_parent))])
areas_cnt_text = areas_cnt_text / float(drop_only.shape[0] * drop_only.shape[1])
contours_drop_parent = [contours_drop_parent[jz] for jz in range(len(contours_drop_parent)) if areas_cnt_text[jz] > 0.001]
areas_cnt_text = [areas_cnt_text[jz] for jz in range(len(areas_cnt_text)) if areas_cnt_text[jz] > 0.001]
contours_drop_parent_final = []
for jj in range(len(contours_drop_parent)):
x, y, w, h = cv2.boundingRect(contours_drop_parent[jj])
# boxes.append([int(x), int(y), int(w), int(h)])
iou_of_box_and_contoure = float(drop_only.shape[0] * drop_only.shape[1]) * areas_cnt_text[jj] / float(w * h) * 100
height_to_weight_ratio = h / float(w)
weigh_to_height_ratio = w / float(h)
if iou_of_box_and_contoure > 60 and weigh_to_height_ratio < 1.2 and height_to_weight_ratio < 2:
map_of_drop_contour_bb = np.zeros((layout1.shape[0], layout1.shape[1]))
map_of_drop_contour_bb[y : y + h, x : x + w] = layout1[y : y + h, x : x + w]
if (((map_of_drop_contour_bb == 1) * 1).sum() / float(((map_of_drop_contour_bb == 5) * 1).sum()) * 100) >= 15:
contours_drop_parent_final.append(contours_drop_parent[jj])
layout_no_patch[:, :, 0][layout_no_patch[:, :, 0] == 4] = 0
layout_no_patch = cv2.fillPoly(layout_no_patch, pts=contours_drop_parent_final, color=(4, 4, 4))
return layout_no_patch

3
sbb_newspapers_org_image/utils/is_nan.py
Unescape Escape View File

@ -0,0 +1,3 @@
def isNaN(num):
return num != num

4
sbb_newspapers_org_image/utils/rotate.py
Unescape Escape View File

@ -1,3 +1,7 @@
import math
import imutils
import cv2
def rotatedRectWithMaxArea(w, h, angle): def rotatedRectWithMaxArea(w, h, angle):
if w <= 0 or h <= 0: if w <= 0 or h <= 0:

103
sbb_newspapers_org_image/utils/separate_lines.py
Unescape Escape View File

@ -1,3 +1,16 @@
import numpy as np
import cv2
from scipy.signal import find_peaks
from scipy.ndimage import gaussian_filter1d
from .rotate import rotate_image
from .contour import (
return_parent_contours,
filter_contours_area_of_image_tables,
return_contours_of_image,
filter_contours_area_of_image
)
from .is_nan import isNaN
def seperate_lines(img_patch, contour_text_interest, thetha, x_help, y_help): def seperate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
@ -1263,3 +1276,93 @@ def seperate_lines_vertical_cont(img_patch, contour_text_interest, thetha, box_i
return None, cont_final return None, cont_final
def textline_contours_postprocessing(textline_mask, slope, contour_text_interest, box_ind, slope_first, add_boxes_coor_into_textlines=False):
textline_mask = np.repeat(textline_mask[:, :, np.newaxis], 3, axis=2) * 255
textline_mask = textline_mask.astype(np.uint8)
kernel = np.ones((5, 5), np.uint8)
textline_mask = cv2.morphologyEx(textline_mask, cv2.MORPH_OPEN, kernel)
textline_mask = cv2.morphologyEx(textline_mask, cv2.MORPH_CLOSE, kernel)
textline_mask = cv2.erode(textline_mask, kernel, iterations=2)
# textline_mask = cv2.erode(textline_mask, kernel, iterations=1)
# print(textline_mask.shape[0]/float(textline_mask.shape[1]),'miz')
try:
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(textline_mask)
# plt.show()
# if abs(slope)>1:
# x_help=30
# y_help=2
# else:
# x_help=2
# y_help=2
x_help = 30
y_help = 2
textline_mask_help = np.zeros((textline_mask.shape[0] + int(2 * y_help), textline_mask.shape[1] + int(2 * x_help), 3))
textline_mask_help[y_help : y_help + textline_mask.shape[0], x_help : x_help + textline_mask.shape[1], :] = np.copy(textline_mask[:, :, :])
dst = rotate_image(textline_mask_help, slope)
dst = dst[:, :, 0]
dst[dst != 0] = 1
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(dst)
# plt.show()
contour_text_copy = contour_text_interest.copy()
contour_text_copy[:, 0, 0] = contour_text_copy[:, 0, 0] - box_ind[0]
contour_text_copy[:, 0, 1] = contour_text_copy[:, 0, 1] - box_ind[1]
img_contour = np.zeros((box_ind[3], box_ind[2], 3))
img_contour = cv2.fillPoly(img_contour, pts=[contour_text_copy], color=(255, 255, 255))
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(img_contour)
# plt.show()
img_contour_help = np.zeros((img_contour.shape[0] + int(2 * y_help), img_contour.shape[1] + int(2 * x_help), 3))
img_contour_help[y_help : y_help + img_contour.shape[0], x_help : x_help + img_contour.shape[1], :] = np.copy(img_contour[:, :, :])
img_contour_rot = rotate_image(img_contour_help, slope)
# plt.imshow(img_contour_rot_help)
# plt.show()
# plt.imshow(dst_help)
# plt.show()
# if np.abs(slope)>.5 and textline_mask.shape[0]/float(textline_mask.shape[1])>3:
# plt.imshow(img_contour_rot_help)
# plt.show()
# plt.imshow(dst_help)
# plt.show()
img_contour_rot = img_contour_rot.astype(np.uint8)
# dst_help = dst_help.astype(np.uint8)
imgrayrot = cv2.cvtColor(img_contour_rot, cv2.COLOR_BGR2GRAY)
_, threshrot = cv2.threshold(imgrayrot, 0, 255, 0)
contours_text_rot, _ = cv2.findContours(threshrot.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
len_con_text_rot = [len(contours_text_rot[ib]) for ib in range(len(contours_text_rot))]
ind_big_con = np.argmax(len_con_text_rot)
# print('juzaa')
if abs(slope) > 45:
# print(add_boxes_coor_into_textlines,'avval')
_, contours_rotated_clean = seperate_lines_vertical_cont(textline_mask, contours_text_rot[ind_big_con], box_ind, slope, add_boxes_coor_into_textlines=add_boxes_coor_into_textlines)
else:
_, contours_rotated_clean = seperate_lines(dst, contours_text_rot[ind_big_con], slope, x_help, y_help)
except:
contours_rotated_clean = []
return contours_rotated_clean

7
tests/test_smoke.py
Unescape Escape View File

@ -0,0 +1,7 @@
def test_utils_import():
import sbb_newspapers_org_image.utils
import sbb_newspapers_org_image.utils.contour
import sbb_newspapers_org_image.utils.drop_capitals
import sbb_newspapers_org_image.utils.drop_capitals
import sbb_newspapers_org_image.utils.is_nan
import sbb_newspapers_org_image.utils.rotate
Write Preview
Loading…
Cancel
Save