qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-10-07 06:59:58 +02:00
Code Issues Projects Releases Wiki Activity

indent extremely long lines

Browse source
This commit is contained in:
Robert Sachunsky 2025-09-30 03:52:19 +02:00
parent f857ee7b51
commit 08c8c26028
4 changed files with 652 additions and 289 deletions
Download patch file Download diff file Expand all files Collapse all files

746
src/eynollah/eynollah.py
View file

File diff suppressed because it is too large Load diff

30
src/eynollah/utils/__init__.py
View file

@ -1012,8 +1012,13 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
(regions_model_full[:,:,0]==2)).sum() (regions_model_full[:,:,0]==2)).sum()
pixels_main = all_pixels - pixels_header pixels_main = all_pixels - pixels_header
if ( (pixels_header/float(pixels_main)>=0.6) and ( (length_con[ii]/float(height_con[ii]) )>=1.3 ) and ( (length_con[ii]/float(height_con[ii]) )<=3 )) or ( (pixels_header/float(pixels_main)>=0.3) and ( (length_con[ii]/float(height_con[ii]) )>=3 ) ): if (( pixels_header / float(pixels_main) >= 0.6 and
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img[:,:,0]==255) ]=2 length_con[ii] / float(height_con[ii]) >= 1.3 and
length_con[ii] / float(height_con[ii]) <= 3 ) or
( pixels_header / float(pixels_main) >= 0.3 and
length_con[ii] / float(height_con[ii]) >=3 )):
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img[:,:,0]==255) ] = 2
contours_only_text_parent_head.append(contours_only_text_parent[ii]) contours_only_text_parent_head.append(contours_only_text_parent[ii])
conf_contours_head.append(None) # why not conf_contours[ii], too? conf_contours_head.append(None) # why not conf_contours[ii], too?
if contours_only_text_parent_d_ordered is not None: if contours_only_text_parent_d_ordered is not None:
@ -1021,8 +1026,9 @@ def check_any_text_region_in_model_one_is_main_or_header_light(
all_box_coord_head.append(all_box_coord[ii]) all_box_coord_head.append(all_box_coord[ii])
slopes_head.append(slopes[ii]) slopes_head.append(slopes[ii])
all_found_textline_polygons_head.append(all_found_textline_polygons[ii]) all_found_textline_polygons_head.append(all_found_textline_polygons[ii])
else: else:
regions_model_1[:,:][(regions_model_1[:,:]==1) & (img[:,:,0]==255) ]=1 regions_model_1[:,:][(regions_model_1[:,:]==1) & (img[:,:,0]==255) ] = 1
contours_only_text_parent_main.append(contours_only_text_parent[ii]) contours_only_text_parent_main.append(contours_only_text_parent[ii])
conf_contours_main.append(conf_contours[ii]) conf_contours_main.append(conf_contours[ii])
if contours_only_text_parent_d_ordered is not None: if contours_only_text_parent_d_ordered is not None:
@ -1883,7 +1889,8 @@ def return_boxes_of_images_by_order_of_reading_new(
range(x_start_without_mother[dj], range(x_start_without_mother[dj],
x_end_without_mother[dj])) x_end_without_mother[dj]))
columns_not_covered = list(all_columns - columns_covered_by_mothers) columns_not_covered = list(all_columns - columns_covered_by_mothers)
y_type_2 = np.append(y_type_2, np.ones(len(columns_not_covered) + len(x_start_without_mother), y_type_2 = np.append(y_type_2, np.ones(len(columns_not_covered) +
len(x_start_without_mother),
dtype=int) * splitter_y_new[i]) dtype=int) * splitter_y_new[i])
##y_lines_by_order = np.append(y_lines_by_order, [splitter_y_new[i]] * len(columns_not_covered)) ##y_lines_by_order = np.append(y_lines_by_order, [splitter_y_new[i]] * len(columns_not_covered))
##x_start_by_order = np.append(x_start_by_order, [0] * len(columns_not_covered)) ##x_start_by_order = np.append(x_start_by_order, [0] * len(columns_not_covered))
@ -1938,7 +1945,8 @@ def return_boxes_of_images_by_order_of_reading_new(
columns_covered_by_with_child_no_mothers.update( columns_covered_by_with_child_no_mothers.update(
range(x_start_with_child_without_mother[dj], range(x_start_with_child_without_mother[dj],
x_end_with_child_without_mother[dj])) x_end_with_child_without_mother[dj]))
columns_not_covered_child_no_mother = list(all_columns - columns_covered_by_with_child_no_mothers) columns_not_covered_child_no_mother = list(
all_columns - columns_covered_by_with_child_no_mothers)
#indexes_to_be_spanned=[] #indexes_to_be_spanned=[]
for i_s in range(len(x_end_with_child_without_mother)): for i_s in range(len(x_end_with_child_without_mother)):
columns_not_covered_child_no_mother.append(x_start_with_child_without_mother[i_s]) columns_not_covered_child_no_mother.append(x_start_with_child_without_mother[i_s])
@ -1948,7 +1956,8 @@ def return_boxes_of_images_by_order_of_reading_new(
x_start_with_child_without_mother = np.array(x_start_with_child_without_mother, int) x_start_with_child_without_mother = np.array(x_start_with_child_without_mother, int)
for i_s_nc in columns_not_covered_child_no_mother: for i_s_nc in columns_not_covered_child_no_mother:
if i_s_nc in x_start_with_child_without_mother: if i_s_nc in x_start_with_child_without_mother:
x_end_biggest_column = x_end_with_child_without_mother[x_start_with_child_without_mother==i_s_nc][0] x_end_biggest_column = \
x_end_with_child_without_mother[x_start_with_child_without_mother==i_s_nc][0]
args_all_biggest_lines = ind_args[(x_starting==i_s_nc) & args_all_biggest_lines = ind_args[(x_starting==i_s_nc) &
(x_ending==x_end_biggest_column)] (x_ending==x_end_biggest_column)]
y_column_nc = y_type_2[args_all_biggest_lines] y_column_nc = y_type_2[args_all_biggest_lines]
@ -1996,9 +2005,12 @@ def return_boxes_of_images_by_order_of_reading_new(
np.array(list(set(list(range(len(y_all_between_nm_wc)))) - np.array(list(set(list(range(len(y_all_between_nm_wc)))) -
set(list(index_lines_so_close_to_top_separator)))) set(list(index_lines_so_close_to_top_separator))))
if len(indexes_remained_after_deleting_closed_lines) > 0: if len(indexes_remained_after_deleting_closed_lines) > 0:
y_all_between_nm_wc = y_all_between_nm_wc[indexes_remained_after_deleting_closed_lines] y_all_between_nm_wc = \
x_starting_all_between_nm_wc = x_starting_all_between_nm_wc[indexes_remained_after_deleting_closed_lines] y_all_between_nm_wc[indexes_remained_after_deleting_closed_lines]
x_ending_all_between_nm_wc = x_ending_all_between_nm_wc[indexes_remained_after_deleting_closed_lines] x_starting_all_between_nm_wc = \
x_starting_all_between_nm_wc[indexes_remained_after_deleting_closed_lines]
x_ending_all_between_nm_wc = \
x_ending_all_between_nm_wc[indexes_remained_after_deleting_closed_lines]
y_all_between_nm_wc = np.append(y_all_between_nm_wc, y_column_nc[i_c]) y_all_between_nm_wc = np.append(y_all_between_nm_wc, y_column_nc[i_c])
x_starting_all_between_nm_wc = np.append(x_starting_all_between_nm_wc, i_s_nc) x_starting_all_between_nm_wc = np.append(x_starting_all_between_nm_wc, i_s_nc)

134
src/eynollah/utils/separate_lines.py
View file

@ -67,7 +67,8 @@ def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0) peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0)
neg_peaks_max = np.max(y_padded_up_to_down_padded_e[peaks_neg_e]) neg_peaks_max = np.max(y_padded_up_to_down_padded_e[peaks_neg_e])
arg_neg_must_be_deleted = np.arange(len(peaks_neg_e))[y_padded_up_to_down_padded_e[peaks_neg_e] / float(neg_peaks_max) < 0.3] arg_neg_must_be_deleted = np.arange(len(peaks_neg_e))[
y_padded_up_to_down_padded_e[peaks_neg_e] / float(neg_peaks_max) < 0.3]
diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted) diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted)
arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted))) arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted)))
@ -78,11 +79,14 @@ def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
clusters_to_be_deleted = [] clusters_to_be_deleted = []
if len(arg_diff_cluster) > 0: if len(arg_diff_cluster) > 0:
clusters_to_be_deleted.append(arg_neg_must_be_deleted[0 : arg_diff_cluster[0] + 1]) clusters_to_be_deleted.append(
arg_neg_must_be_deleted[0 : arg_diff_cluster[0] + 1])
for i in range(len(arg_diff_cluster) - 1): for i in range(len(arg_diff_cluster) - 1):
clusters_to_be_deleted.append(arg_neg_must_be_deleted[arg_diff_cluster[i] + 1 : clusters_to_be_deleted.append(
arg_neg_must_be_deleted[arg_diff_cluster[i] + 1 :
arg_diff_cluster[i + 1] + 1]) arg_diff_cluster[i + 1] + 1])
clusters_to_be_deleted.append(arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :]) clusters_to_be_deleted.append(
arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :])
if len(clusters_to_be_deleted) > 0: if len(clusters_to_be_deleted) > 0:
peaks_new_extra = [] peaks_new_extra = []
for m in range(len(clusters_to_be_deleted)): for m in range(len(clusters_to_be_deleted)):
@ -179,7 +183,8 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0) peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0)
neg_peaks_max=np.max(y_padded_up_to_down_padded_e[peaks_neg_e]) neg_peaks_max=np.max(y_padded_up_to_down_padded_e[peaks_neg_e])
arg_neg_must_be_deleted= np.arange(len(peaks_neg_e))[y_padded_up_to_down_padded_e[peaks_neg_e]/float(neg_peaks_max)<0.3] arg_neg_must_be_deleted = np.arange(len(peaks_neg_e))[
y_padded_up_to_down_padded_e[peaks_neg_e]/float(neg_peaks_max)<0.3]
diff_arg_neg_must_be_deleted=np.diff(arg_neg_must_be_deleted) diff_arg_neg_must_be_deleted=np.diff(arg_neg_must_be_deleted)
arg_diff=np.array(range(len(diff_arg_neg_must_be_deleted))) arg_diff=np.array(range(len(diff_arg_neg_must_be_deleted)))
@ -239,7 +244,8 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
try: try:
neg_peaks_max=np.max(y_padded_smoothed[peaks]) neg_peaks_max=np.max(y_padded_smoothed[peaks])
arg_neg_must_be_deleted= np.arange(len(peaks_neg))[y_padded_up_to_down_padded[peaks_neg]/float(neg_peaks_max)<0.42] arg_neg_must_be_deleted = np.arange(len(peaks_neg))[
y_padded_up_to_down_padded[peaks_neg]/float(neg_peaks_max)<0.42]
diff_arg_neg_must_be_deleted=np.diff(arg_neg_must_be_deleted) diff_arg_neg_must_be_deleted=np.diff(arg_neg_must_be_deleted)
arg_diff=np.array(range(len(diff_arg_neg_must_be_deleted))) arg_diff=np.array(range(len(diff_arg_neg_must_be_deleted)))
@ -316,23 +322,36 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
if peaks_values[jj]>mean_value_of_peaks-std_value_of_peaks/2.: if peaks_values[jj]>mean_value_of_peaks-std_value_of_peaks/2.:
point_up = peaks[jj] + first_nonzero - int(1.3 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.3 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0)
point_down =y_max_cont-1##peaks[jj] + first_nonzero + int(1.3 * dis_to_next_down) #point_up# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) point_down =y_max_cont-1
##peaks[jj] + first_nonzero + int(1.3 * dis_to_next_down)
#point_up
# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
else: else:
point_up = peaks[jj] + first_nonzero - int(1.4 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.4 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0)
point_down =y_max_cont-1##peaks[jj] + first_nonzero + int(1.6 * dis_to_next_down) #point_up# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) point_down =y_max_cont-1
##peaks[jj] + first_nonzero + int(1.6 * dis_to_next_down)
#point_up
# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
point_down_narrow = peaks[jj] + first_nonzero + int( point_down_narrow = peaks[jj] + first_nonzero + int(
1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./2) 1.4 * dis_to_next_down)
###-int(dis_to_next_down*1./2)
else: else:
dis_to_next_up = abs(peaks[jj] - peaks_neg[jj]) dis_to_next_up = abs(peaks[jj] - peaks_neg[jj])
dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1]) dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1])
if peaks_values[jj]>mean_value_of_peaks-std_value_of_peaks/2.: if peaks_values[jj]>mean_value_of_peaks-std_value_of_peaks/2.:
point_up = peaks[jj] + first_nonzero - int(1.1 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.1 * dis_to_next_up)
point_down = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) ##+int(dis_to_next_up*1./4.0)
point_down = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
else: else:
point_up = peaks[jj] + first_nonzero - int(1.23 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.23 * dis_to_next_up)
point_down = peaks[jj] + first_nonzero + int(1.33 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) ##+int(dis_to_next_up*1./4.0)
point_down = peaks[jj] + first_nonzero + int(1.33 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
point_down_narrow = peaks[jj] + first_nonzero + int( point_down_narrow = peaks[jj] + first_nonzero + int(
1.1 * dis_to_next_down) ###-int(dis_to_next_down*1./2) 1.1 * dis_to_next_down) ###-int(dis_to_next_down*1./2)
@ -341,7 +360,9 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
point_down_narrow = img_patch.shape[0] - 2 point_down_narrow = img_patch.shape[0] - 2
distances = [cv2.pointPolygonTest(contour_text_interest_copy, tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) distances = [cv2.pointPolygonTest(contour_text_interest_copy,
tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])),
True)
for mj in range(len(xv))] for mj in range(len(xv))]
distances = np.array(distances) distances = np.array(distances)
@ -468,7 +489,8 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
point_up =peaks[jj] + first_nonzero - int(1. / 1.8 * dis_to_next) point_up =peaks[jj] + first_nonzero - int(1. / 1.8 * dis_to_next)
distances = [cv2.pointPolygonTest(contour_text_interest_copy, distances = [cv2.pointPolygonTest(contour_text_interest_copy,
tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])),
True)
for mj in range(len(xv))] for mj in range(len(xv))]
distances = np.array(distances) distances = np.array(distances)
@ -543,7 +565,8 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
point_down = peaks[jj] + first_nonzero + int(1. / 1.9 * dis_to_next_down) point_down = peaks[jj] + first_nonzero + int(1. / 1.9 * dis_to_next_down)
distances = [cv2.pointPolygonTest(contour_text_interest_copy, distances = [cv2.pointPolygonTest(contour_text_interest_copy,
tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])),
True)
for mj in range(len(xv))] for mj in range(len(xv))]
distances = np.array(distances) distances = np.array(distances)
@ -613,7 +636,8 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
neg_peaks_max = np.max(y_padded_up_to_down_padded[peaks_neg]) neg_peaks_max = np.max(y_padded_up_to_down_padded[peaks_neg])
arg_neg_must_be_deleted = np.arange(len(peaks_neg))[y_padded_up_to_down_padded[peaks_neg] / float(neg_peaks_max) < 0.42] arg_neg_must_be_deleted = np.arange(len(peaks_neg))[
y_padded_up_to_down_padded[peaks_neg] / float(neg_peaks_max) < 0.42]
diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted) diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted)
arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted))) arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted)))
@ -689,30 +713,50 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1]) dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1])
if peaks_values[jj] > mean_value_of_peaks - std_value_of_peaks / 2.0: if peaks_values[jj] > mean_value_of_peaks - std_value_of_peaks / 2.0:
point_up = peaks[jj] + first_nonzero - int(1.3 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.3 * dis_to_next_up)
point_down = x_max_cont - 1 ##peaks[jj] + first_nonzero + int(1.3 * dis_to_next_down) #point_up# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) ##+int(dis_to_next_up*1./4.0)
point_down = x_max_cont - 1
##peaks[jj] + first_nonzero + int(1.3 * dis_to_next_down)
#point_up
# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
else: else:
point_up = peaks[jj] + first_nonzero - int(1.4 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.4 * dis_to_next_up)
point_down = x_max_cont - 1 ##peaks[jj] + first_nonzero + int(1.6 * dis_to_next_down) #point_up# np.max(y_cont)#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) ##+int(dis_to_next_up*1./4.0)
point_down = x_max_cont - 1
##peaks[jj] + first_nonzero + int(1.6 * dis_to_next_down)
#point_up
# np.max(y_cont)
#peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
point_down_narrow = peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down) ###-int(dis_to_next_down*1./2) point_down_narrow = peaks[jj] + first_nonzero + int(1.4 * dis_to_next_down)
###-int(dis_to_next_down*1./2)
else: else:
dis_to_next_up = abs(peaks[jj] - peaks_neg[jj]) dis_to_next_up = abs(peaks[jj] - peaks_neg[jj])
dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1]) dis_to_next_down = abs(peaks[jj] - peaks_neg[jj + 1])
if peaks_values[jj] > mean_value_of_peaks - std_value_of_peaks / 2.0: if peaks_values[jj] > mean_value_of_peaks - std_value_of_peaks / 2.0:
point_up = peaks[jj] + first_nonzero - int(1.1 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.1 * dis_to_next_up)
point_down = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) ##+int(dis_to_next_up*1./4.0)
point_down = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
else: else:
point_up = peaks[jj] + first_nonzero - int(1.23 * dis_to_next_up) ##+int(dis_to_next_up*1./4.0) point_up = peaks[jj] + first_nonzero - int(1.23 * dis_to_next_up)
point_down = peaks[jj] + first_nonzero + int(1.33 * dis_to_next_down) ###-int(dis_to_next_down*1./4.0) ##+int(dis_to_next_up*1./4.0)
point_down = peaks[jj] + first_nonzero + int(1.33 * dis_to_next_down)
###-int(dis_to_next_down*1./4.0)
point_down_narrow = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down) ###-int(dis_to_next_down*1./2) point_down_narrow = peaks[jj] + first_nonzero + int(1.1 * dis_to_next_down)
###-int(dis_to_next_down*1./2)
if point_down_narrow >= img_patch.shape[0]: if point_down_narrow >= img_patch.shape[0]:
point_down_narrow = img_patch.shape[0] - 2 point_down_narrow = img_patch.shape[0] - 2
distances = [cv2.pointPolygonTest(contour_text_interest_copy, tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) for mj in range(len(xv))] distances = [cv2.pointPolygonTest(contour_text_interest_copy,
tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])),
True)
for mj in range(len(xv))]
distances = np.array(distances) distances = np.array(distances)
xvinside = xv[distances >= 0] xvinside = xv[distances >= 0]
@ -801,7 +845,8 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
point_up = peaks[jj] + first_nonzero - int(1.0 / 1.8 * dis_to_next) point_up = peaks[jj] + first_nonzero - int(1.0 / 1.8 * dis_to_next)
distances = [cv2.pointPolygonTest(contour_text_interest_copy, distances = [cv2.pointPolygonTest(contour_text_interest_copy,
tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])),
True)
for mj in range(len(xv))] for mj in range(len(xv))]
distances = np.array(distances) distances = np.array(distances)
@ -866,7 +911,8 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
point_down = peaks[jj] + first_nonzero + int(1.0 / 1.9 * dis_to_next_down) point_down = peaks[jj] + first_nonzero + int(1.0 / 1.9 * dis_to_next_down)
distances = [cv2.pointPolygonTest(contour_text_interest_copy, distances = [cv2.pointPolygonTest(contour_text_interest_copy,
tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])), True) tuple(int(x) for x in np.array([xv[mj], peaks[jj] + first_nonzero])),
True)
for mj in range(len(xv))] for mj in range(len(xv))]
distances = np.array(distances) distances = np.array(distances)
@ -950,7 +996,8 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0) peaks_neg_e, _ = find_peaks(y_padded_up_to_down_padded_e, height=0)
neg_peaks_max = np.max(y_padded_up_to_down_padded_e[peaks_neg_e]) neg_peaks_max = np.max(y_padded_up_to_down_padded_e[peaks_neg_e])
arg_neg_must_be_deleted = np.arange(len(peaks_neg_e))[y_padded_up_to_down_padded_e[peaks_neg_e] / float(neg_peaks_max) < 0.3] arg_neg_must_be_deleted = np.arange(len(peaks_neg_e))[
y_padded_up_to_down_padded_e[peaks_neg_e] / float(neg_peaks_max) < 0.3]
diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted) diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted)
arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted))) arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted)))
@ -963,8 +1010,11 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
if len(arg_diff_cluster) > 0: if len(arg_diff_cluster) > 0:
clusters_to_be_deleted.append(arg_neg_must_be_deleted[0 : arg_diff_cluster[0] + 1]) clusters_to_be_deleted.append(arg_neg_must_be_deleted[0 : arg_diff_cluster[0] + 1])
for i in range(len(arg_diff_cluster) - 1): for i in range(len(arg_diff_cluster) - 1):
clusters_to_be_deleted.append(arg_neg_must_be_deleted[arg_diff_cluster[i] + 1 : arg_diff_cluster[i + 1] + 1]) clusters_to_be_deleted.append(
clusters_to_be_deleted.append(arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :]) arg_neg_must_be_deleted[arg_diff_cluster[i] + 1:
arg_diff_cluster[i + 1] + 1])
clusters_to_be_deleted.append(
arg_neg_must_be_deleted[arg_diff_cluster[len(arg_diff_cluster) - 1] + 1 :])
if len(clusters_to_be_deleted) > 0: if len(clusters_to_be_deleted) > 0:
peaks_new_extra = [] peaks_new_extra = []
for m in range(len(clusters_to_be_deleted)): for m in range(len(clusters_to_be_deleted)):
@ -1014,7 +1064,8 @@ def separate_lines_new_inside_tiles2(img_patch, thetha):
try: try:
neg_peaks_max = np.max(y_padded_smoothed[peaks]) neg_peaks_max = np.max(y_padded_smoothed[peaks])
arg_neg_must_be_deleted = np.arange(len(peaks_neg))[y_padded_up_to_down_padded[peaks_neg] / float(neg_peaks_max) < 0.24] arg_neg_must_be_deleted = np.arange(len(peaks_neg))[
y_padded_up_to_down_padded[peaks_neg] / float(neg_peaks_max) < 0.24]
diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted) diff_arg_neg_must_be_deleted = np.diff(arg_neg_must_be_deleted)
arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted))) arg_diff = np.array(range(len(diff_arg_neg_must_be_deleted)))
@ -1290,7 +1341,9 @@ def separate_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, add_boxes_coor_into_textlines=False): def textline_contours_postprocessing(textline_mask, slope,
contour_text_interest, box_ind,
add_boxes_coor_into_textlines=False):
textline_mask = np.repeat(textline_mask[:, :, np.newaxis], 3, axis=2) * 255 textline_mask = np.repeat(textline_mask[:, :, np.newaxis], 3, axis=2) * 255
textline_mask = textline_mask.astype(np.uint8) textline_mask = textline_mask.astype(np.uint8)
kernel = np.ones((5, 5), np.uint8) kernel = np.ones((5, 5), np.uint8)
@ -1485,7 +1538,8 @@ def return_deskew_slop(img_patch_org, sigma_des,n_tot_angles=100,
onset_y=int((img_resized.shape[0]-img_int.shape[0])/2.) onset_y=int((img_resized.shape[0]-img_int.shape[0])/2.)
#img_resized=np.zeros((int( img_int.shape[0]*(1.8) ) , int( img_int.shape[1]*(2.6) ) )) #img_resized=np.zeros((int( img_int.shape[0]*(1.8) ) , int( img_int.shape[1]*(2.6) ) ))
#img_resized[ int( img_int.shape[0]*(.4)):int( img_int.shape[0]*(.4))+img_int.shape[0] , int( img_int.shape[1]*(.8)):int( img_int.shape[1]*(.8))+img_int.shape[1] ]=img_int[:,:] #img_resized[ int( img_int.shape[0]*(.4)):int( img_int.shape[0]*(.4))+img_int.shape[0],
# int( img_int.shape[1]*(.8)):int( img_int.shape[1]*(.8))+img_int.shape[1] ]=img_int[:,:]
img_resized[ onset_y:onset_y+img_int.shape[0] , onset_x:onset_x+img_int.shape[1] ]=img_int[:,:] img_resized[ onset_y:onset_y+img_int.shape[0] , onset_x:onset_x+img_int.shape[1] ]=img_int[:,:]
if main_page and img_patch_org.shape[1] > img_patch_org.shape[0]: if main_page and img_patch_org.shape[1] > img_patch_org.shape[0]:
@ -1689,14 +1743,18 @@ def do_work_of_slopes_new_curved(
mask_biggest2 = cv2.dilate(mask_biggest2, KERNEL, iterations=4) mask_biggest2 = cv2.dilate(mask_biggest2, KERNEL, iterations=4)
pixel_img = 1 pixel_img = 1
mask_biggest2 = resize_image(mask_biggest2, int(mask_biggest2.shape[0] * scale_par), int(mask_biggest2.shape[1] * scale_par)) mask_biggest2 = resize_image(mask_biggest2,
int(mask_biggest2.shape[0] * scale_par),
int(mask_biggest2.shape[1] * scale_par))
cnt_textlines_in_image_ind = return_contours_of_interested_textline(mask_biggest2, pixel_img) cnt_textlines_in_image_ind = return_contours_of_interested_textline(mask_biggest2, pixel_img)
try: try:
textlines_cnt_per_region.append(cnt_textlines_in_image_ind[0]) textlines_cnt_per_region.append(cnt_textlines_in_image_ind[0])
except Exception as why: except Exception as why:
logger.error(why) logger.error(why)
else: else:
textlines_cnt_per_region = textline_contours_postprocessing(all_text_region_raw, slope_for_all, contour_par, box_text, True) textlines_cnt_per_region = textline_contours_postprocessing(all_text_region_raw,
slope_for_all, contour_par,
box_text, True)
return textlines_cnt_per_region[::-1], box_text, contour, contour_par, crop_coor, index_r_con, slope return textlines_cnt_per_region[::-1], box_text, contour, contour_par, crop_coor, index_r_con, slope

25
src/eynollah/utils/utils_ocr.py
View file

@ -370,7 +370,11 @@ def return_textline_contour_with_added_box_coordinate(textline_contour, box_ind
return textline_contour return textline_contour
def return_rnn_cnn_ocr_of_given_textlines(image, all_found_textline_polygons, prediction_model, b_s_ocr, num_to_char, textline_light=False, curved_line=False): def return_rnn_cnn_ocr_of_given_textlines(image, all_found_textline_polygons,
prediction_model,
b_s_ocr, num_to_char,
textline_light=False,
curved_line=False):
max_len = 512 max_len = 512
padding_token = 299 padding_token = 299
image_width = 512#max_len * 4 image_width = 512#max_len * 4
@ -426,17 +430,23 @@ def return_rnn_cnn_ocr_of_given_textlines(image, all_found_textline_polygons, pr
splited_images, splited_images_bin = return_textlines_split_if_needed(img_crop, None) splited_images, splited_images_bin = return_textlines_split_if_needed(img_crop, None)
if splited_images: if splited_images:
img_fin = preprocess_and_resize_image_for_ocrcnn_model(splited_images[0], image_height, image_width) img_fin = preprocess_and_resize_image_for_ocrcnn_model(splited_images[0],
image_height,
image_width)
cropped_lines.append(img_fin) cropped_lines.append(img_fin)
cropped_lines_meging_indexing.append(1) cropped_lines_meging_indexing.append(1)
img_fin = preprocess_and_resize_image_for_ocrcnn_model(splited_images[1], image_height, image_width) img_fin = preprocess_and_resize_image_for_ocrcnn_model(splited_images[1],
image_height,
image_width)
cropped_lines.append(img_fin) cropped_lines.append(img_fin)
cropped_lines_meging_indexing.append(-1) cropped_lines_meging_indexing.append(-1)
else: else:
img_fin = preprocess_and_resize_image_for_ocrcnn_model(img_crop, image_height, image_width) img_fin = preprocess_and_resize_image_for_ocrcnn_model(img_crop,
image_height,
image_width)
cropped_lines.append(img_fin) cropped_lines.append(img_fin)
cropped_lines_meging_indexing.append(0) cropped_lines_meging_indexing.append(0)
@ -469,7 +479,12 @@ def return_rnn_cnn_ocr_of_given_textlines(image, all_found_textline_polygons, pr
pred_texts_ib = pred_texts[ib].replace("[UNK]", "") pred_texts_ib = pred_texts[ib].replace("[UNK]", "")
extracted_texts.append(pred_texts_ib) extracted_texts.append(pred_texts_ib)
extracted_texts_merged = [extracted_texts[ind] if cropped_lines_meging_indexing[ind]==0 else extracted_texts[ind]+" "+extracted_texts[ind+1] if cropped_lines_meging_indexing[ind]==1 else None for ind in range(len(cropped_lines_meging_indexing))] extracted_texts_merged = [extracted_texts[ind]
if cropped_lines_meging_indexing[ind]==0
else extracted_texts[ind]+" "+extracted_texts[ind+1]
if cropped_lines_meging_indexing[ind]==1
else None
for ind in range(len(cropped_lines_meging_indexing))]
extracted_texts_merged = [ind for ind in extracted_texts_merged if ind is not None] extracted_texts_merged = [ind for ind in extracted_texts_merged if ind is not None]
unique_cropped_lines_region_indexer = np.unique(cropped_lines_region_indexer) unique_cropped_lines_region_indexer = np.unique(cropped_lines_region_indexer)