mirror of
https://github.com/qurator-spk/eynollah.git
synced 2025-11-17 01:44:14 +01:00
Merge e428e7ad78 into 38c028c6b5
This commit is contained in:
Robert Sachunsky
GitHub
commit
850221d9ea
7 changed files with 1086 additions and 1414 deletions
|
|
@ -79,18 +79,28 @@ def machine_based_reading_order(input, dir_in, out, model, log_level):
|
|||
type=click.Path(file_okay=True, dir_okay=True),
|
||||
required=True,
|
||||
)
|
||||
@click.option(
|
||||
"--overwrite",
|
||||
"-O",
|
||||
help="overwrite (instead of skipping) if output xml exists",
|
||||
is_flag=True,
|
||||
)
|
||||
@click.option(
|
||||
"--log_level",
|
||||
"-l",
|
||||
type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
|
||||
help="Override log level globally to this",
|
||||
)
|
||||
def binarization(patches, model_dir, input_image, dir_in, output, log_level):
|
||||
def binarization(patches, model_dir, input_image, dir_in, output, overwrite, log_level):
|
||||
assert bool(input_image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
|
||||
binarizer = SbbBinarizer(model_dir)
|
||||
if log_level:
|
||||
binarizer.log.setLevel(getLevelName(log_level))
|
||||
binarizer.run(image_path=input_image, use_patches=patches, output=output, dir_in=dir_in)
|
||||
binarizer.logger.setLevel(getLevelName(log_level))
|
||||
binarizer.run(overwrite=overwrite,
|
||||
use_patches=patches,
|
||||
image_path=input_image,
|
||||
output=output,
|
||||
dir_in=dir_in)
|
||||
|
||||
|
||||
@main.command()
|
||||
|
|
|
|||
|
|
@ -88,12 +88,7 @@ from .utils.contour import (
|
|||
join_polygons,
|
||||
make_intersection,
|
||||
)
|
||||
from .utils.rotate import (
|
||||
rotate_image,
|
||||
rotation_not_90_func,
|
||||
rotation_not_90_func_full_layout,
|
||||
rotation_image_new
|
||||
)
|
||||
from .utils.rotate import rotate_image
|
||||
from .utils.utils_ocr import (
|
||||
return_start_and_end_of_common_text_of_textline_ocr_without_common_section,
|
||||
return_textline_contour_with_added_box_coordinate,
|
||||
|
|
@ -139,7 +134,6 @@ from .utils import (
|
|||
return_boxes_of_images_by_order_of_reading_new
|
||||
)
|
||||
from .utils.pil_cv2 import check_dpi, pil2cv
|
||||
from .utils.xml import order_and_id_of_texts
|
||||
from .plot import EynollahPlotter
|
||||
from .writer import EynollahXmlWriter
|
||||
|
||||
|
|
@ -2091,19 +2085,19 @@ class Eynollah:
|
|||
prediction_regions_org = prediction_regions_org[page_coord[0] : page_coord[1], page_coord[2] : page_coord[3]]
|
||||
prediction_regions_org=prediction_regions_org[:,:,0]
|
||||
|
||||
mask_lines_only = (prediction_regions_org[:,:] ==3)*1
|
||||
mask_seps_only = (prediction_regions_org[:,:] == 3)*1
|
||||
mask_texts_only = (prediction_regions_org[:,:] ==1)*1
|
||||
mask_images_only=(prediction_regions_org[:,:] ==2)*1
|
||||
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_lines_only)
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_seps_only)
|
||||
polygons_seplines = filter_contours_area_of_image(
|
||||
mask_lines_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
mask_seps_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
|
||||
polygons_of_only_texts = return_contours_of_interested_region(mask_texts_only,1,0.00001)
|
||||
polygons_of_only_lines = return_contours_of_interested_region(mask_lines_only,1,0.00001)
|
||||
polygons_of_only_seps = return_contours_of_interested_region(mask_seps_only,1,0.00001)
|
||||
|
||||
text_regions_p_true = np.zeros(prediction_regions_org.shape)
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_lines, color=(3,3,3))
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_seps, color=(3,3,3))
|
||||
|
||||
text_regions_p_true[:,:][mask_images_only[:,:] == 1] = 2
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts=polygons_of_only_texts, color=(1,1,1))
|
||||
|
|
@ -2282,7 +2276,7 @@ class Eynollah:
|
|||
img_bin = resize_image(img_bin, img_height_h, img_width_h )
|
||||
prediction_regions_org=prediction_regions_org[:,:,0]
|
||||
|
||||
mask_lines_only = (prediction_regions_org[:,:] ==3)*1
|
||||
mask_seps_only = (prediction_regions_org[:,:] == 3)*1
|
||||
mask_texts_only = (prediction_regions_org[:,:] ==1)*1
|
||||
mask_texts_only = mask_texts_only.astype('uint8')
|
||||
|
||||
|
|
@ -2293,7 +2287,7 @@ class Eynollah:
|
|||
mask_texts_only = cv2.dilate(mask_texts_only, kernel=np.ones((2,2), np.uint8), iterations=1)
|
||||
mask_images_only=(prediction_regions_org[:,:] ==2)*1
|
||||
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_lines_only)
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_seps_only)
|
||||
test_khat = np.zeros(prediction_regions_org.shape)
|
||||
test_khat = cv2.fillPoly(test_khat, pts=polygons_seplines, color=(1,1,1))
|
||||
|
||||
|
|
@ -2307,7 +2301,7 @@ class Eynollah:
|
|||
#plt.show()
|
||||
|
||||
polygons_seplines = filter_contours_area_of_image(
|
||||
mask_lines_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
mask_seps_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
|
||||
test_khat = np.zeros(prediction_regions_org.shape)
|
||||
test_khat = cv2.fillPoly(test_khat, pts = polygons_seplines, color=(1,1,1))
|
||||
|
|
@ -2318,10 +2312,10 @@ class Eynollah:
|
|||
|
||||
polygons_of_only_texts = return_contours_of_interested_region(mask_texts_only,1,0.00001)
|
||||
##polygons_of_only_texts = dilate_textregion_contours(polygons_of_only_texts)
|
||||
polygons_of_only_lines = return_contours_of_interested_region(mask_lines_only,1,0.00001)
|
||||
polygons_of_only_seps = return_contours_of_interested_region(mask_seps_only,1,0.00001)
|
||||
|
||||
text_regions_p_true = np.zeros(prediction_regions_org.shape)
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts=polygons_of_only_lines, color=(3,3,3))
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts=polygons_of_only_seps, color=(3,3,3))
|
||||
|
||||
text_regions_p_true[:,:][mask_images_only[:,:] == 1] = 2
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_texts, color=(1,1,1))
|
||||
|
|
@ -2377,7 +2371,7 @@ class Eynollah:
|
|||
prediction_regions_org2=resize_image(prediction_regions_org2, img_height_h, img_width_h )
|
||||
|
||||
mask_zeros2 = (prediction_regions_org2[:,:,0] == 0)
|
||||
mask_lines2 = (prediction_regions_org2[:,:,0] == 3)
|
||||
mask_seps2 = (prediction_regions_org2[:,:,0] == 3)
|
||||
text_sume_early = (prediction_regions_org[:,:] == 1).sum()
|
||||
prediction_regions_org_copy = np.copy(prediction_regions_org)
|
||||
prediction_regions_org_copy[(prediction_regions_org_copy[:,:]==1) & (mask_zeros2[:,:]==1)] = 0
|
||||
|
|
@ -2388,8 +2382,8 @@ class Eynollah:
|
|||
if not(is_image_enhanced and rate_two_models < RATIO_OF_TWO_MODEL_THRESHOLD):
|
||||
prediction_regions_org = np.copy(prediction_regions_org_copy)
|
||||
|
||||
prediction_regions_org[(mask_lines2[:,:]==1) & (prediction_regions_org[:,:]==0)]=3
|
||||
mask_lines_only=(prediction_regions_org[:,:]==3)*1
|
||||
prediction_regions_org[(mask_seps2[:,:]==1) & (prediction_regions_org[:,:]==0)]=3
|
||||
mask_seps_only=(prediction_regions_org[:,:]==3)*1
|
||||
prediction_regions_org = cv2.erode(prediction_regions_org[:,:], KERNEL, iterations=2)
|
||||
prediction_regions_org = cv2.dilate(prediction_regions_org[:,:], KERNEL, iterations=2)
|
||||
|
||||
|
|
@ -2411,20 +2405,20 @@ class Eynollah:
|
|||
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h )
|
||||
prediction_regions_org=prediction_regions_org[:,:,0]
|
||||
|
||||
mask_lines_only=(prediction_regions_org[:,:]==3)*1
|
||||
mask_seps_only=(prediction_regions_org[:,:]==3)*1
|
||||
|
||||
mask_texts_only=(prediction_regions_org[:,:]==1)*1
|
||||
mask_images_only=(prediction_regions_org[:,:]==2)*1
|
||||
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_lines_only)
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_seps_only)
|
||||
polygons_seplines = filter_contours_area_of_image(
|
||||
mask_lines_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
mask_seps_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
|
||||
polygons_of_only_texts = return_contours_of_interested_region(mask_texts_only, 1, 0.00001)
|
||||
polygons_of_only_lines = return_contours_of_interested_region(mask_lines_only, 1, 0.00001)
|
||||
polygons_of_only_seps = return_contours_of_interested_region(mask_seps_only, 1, 0.00001)
|
||||
|
||||
text_regions_p_true = np.zeros(prediction_regions_org.shape)
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true,pts = polygons_of_only_lines, color=(3, 3, 3))
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true,pts = polygons_of_only_seps, color=(3, 3, 3))
|
||||
text_regions_p_true[:,:][mask_images_only[:,:] == 1] = 2
|
||||
|
||||
text_regions_p_true=cv2.fillPoly(text_regions_p_true,pts=polygons_of_only_texts, color=(1,1,1))
|
||||
|
|
@ -2449,7 +2443,7 @@ class Eynollah:
|
|||
prediction_regions_org = resize_image(prediction_regions_org, img_height_h, img_width_h )
|
||||
prediction_regions_org=prediction_regions_org[:,:,0]
|
||||
|
||||
#mask_lines_only=(prediction_regions_org[:,:]==3)*1
|
||||
#mask_seps_only=(prediction_regions_org[:,:]==3)*1
|
||||
#img = resize_image(img_org, int(img_org.shape[0]*1), int(img_org.shape[1]*1))
|
||||
|
||||
#prediction_regions_org = self.do_prediction(True, img, self.models["region"])
|
||||
|
|
@ -2457,19 +2451,19 @@ class Eynollah:
|
|||
#prediction_regions_org = prediction_regions_org[:,:,0]
|
||||
#prediction_regions_org[(prediction_regions_org[:,:] == 1) & (mask_zeros_y[:,:] == 1)]=0
|
||||
|
||||
mask_lines_only = (prediction_regions_org == 3)*1
|
||||
mask_seps_only = (prediction_regions_org == 3)*1
|
||||
mask_texts_only = (prediction_regions_org == 1)*1
|
||||
mask_images_only= (prediction_regions_org == 2)*1
|
||||
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_lines_only)
|
||||
polygons_seplines, hir_seplines = return_contours_of_image(mask_seps_only)
|
||||
polygons_seplines = filter_contours_area_of_image(
|
||||
mask_lines_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
mask_seps_only, polygons_seplines, hir_seplines, max_area=1, min_area=0.00001, dilate=1)
|
||||
|
||||
polygons_of_only_texts = return_contours_of_interested_region(mask_texts_only,1,0.00001)
|
||||
polygons_of_only_lines = return_contours_of_interested_region(mask_lines_only,1,0.00001)
|
||||
polygons_of_only_seps = return_contours_of_interested_region(mask_seps_only,1,0.00001)
|
||||
|
||||
text_regions_p_true = np.zeros(prediction_regions_org.shape)
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_lines, color=(3,3,3))
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_seps, color=(3,3,3))
|
||||
|
||||
text_regions_p_true[:,:][mask_images_only[:,:] == 1] = 2
|
||||
text_regions_p_true = cv2.fillPoly(text_regions_p_true, pts = polygons_of_only_texts, color=(1,1,1))
|
||||
|
|
@ -2491,11 +2485,15 @@ class Eynollah:
|
|||
contours_only_text_parent)
|
||||
cx_head, cy_head, mx_head, Mx_head, my_head, My_head, mxy_head = find_new_features_of_contours(
|
||||
contours_only_text_parent_h)
|
||||
cx_main = np.array(cx_main, dtype=int)
|
||||
cy_main = np.array(cy_main, dtype=int)
|
||||
cx_head = np.array(cx_head, dtype=int)
|
||||
cy_head = np.array(cy_head, dtype=int)
|
||||
|
||||
def match_boxes(only_centers: bool):
|
||||
arg_text_con_main = np.zeros(len(contours_only_text_parent), dtype=int)
|
||||
for ii in range(len(contours_only_text_parent)):
|
||||
check_if_textregion_located_in_a_box = False
|
||||
box_found = False
|
||||
for jj, box in enumerate(boxes):
|
||||
if ((cx_main[ii] >= box[0] and
|
||||
cx_main[ii] < box[1] and
|
||||
|
|
@ -2506,20 +2504,23 @@ class Eynollah:
|
|||
my_main[ii] >= box[2] and
|
||||
My_main[ii] < box[3])):
|
||||
arg_text_con_main[ii] = jj
|
||||
check_if_textregion_located_in_a_box = True
|
||||
box_found = True
|
||||
# print("main/matched ", ii, "\t", (mx_main[ii], Mx_main[ii], my_main[ii], My_main[ii]), "\tin", jj, box, only_centers)
|
||||
break
|
||||
if not check_if_textregion_located_in_a_box:
|
||||
if not box_found:
|
||||
dists_tr_from_box = np.linalg.norm(c_boxes - np.array([[cy_main[ii]], [cx_main[ii]]]), axis=0)
|
||||
pcontained_in_box = ((boxes[:, 2] <= cy_main[ii]) & (cy_main[ii] < boxes[:, 3]) &
|
||||
(boxes[:, 0] <= cx_main[ii]) & (cx_main[ii] < boxes[:, 1]))
|
||||
assert pcontained_in_box.any(), (ii, cx_main[ii], cy_main[ii])
|
||||
ind_min = np.argmin(np.ma.masked_array(dists_tr_from_box, ~pcontained_in_box))
|
||||
arg_text_con_main[ii] = ind_min
|
||||
# print("main/fallback ", ii, "\t", (mx_main[ii], Mx_main[ii], my_main[ii], My_main[ii]), "\tin", ind_min, boxes[ind_min], only_centers)
|
||||
args_contours_main = np.arange(len(contours_only_text_parent))
|
||||
order_by_con_main = np.zeros_like(arg_text_con_main)
|
||||
|
||||
arg_text_con_head = np.zeros(len(contours_only_text_parent_h), dtype=int)
|
||||
for ii in range(len(contours_only_text_parent_h)):
|
||||
check_if_textregion_located_in_a_box = False
|
||||
box_found = False
|
||||
for jj, box in enumerate(boxes):
|
||||
if ((cx_head[ii] >= box[0] and
|
||||
cx_head[ii] < box[1] and
|
||||
|
|
@ -2530,20 +2531,21 @@ class Eynollah:
|
|||
my_head[ii] >= box[2] and
|
||||
My_head[ii] < box[3])):
|
||||
arg_text_con_head[ii] = jj
|
||||
check_if_textregion_located_in_a_box = True
|
||||
box_found = True
|
||||
# print("head/matched ", ii, "\t", (mx_head[ii], Mx_head[ii], my_head[ii], My_head[ii]), "\tin", jj, box, only_centers)
|
||||
break
|
||||
if not check_if_textregion_located_in_a_box:
|
||||
if not box_found:
|
||||
dists_tr_from_box = np.linalg.norm(c_boxes - np.array([[cy_head[ii]], [cx_head[ii]]]), axis=0)
|
||||
pcontained_in_box = ((boxes[:, 2] <= cy_head[ii]) & (cy_head[ii] < boxes[:, 3]) &
|
||||
(boxes[:, 0] <= cx_head[ii]) & (cx_head[ii] < boxes[:, 1]))
|
||||
assert pcontained_in_box.any(), (ii, cx_head[ii], cy_head[ii])
|
||||
ind_min = np.argmin(np.ma.masked_array(dists_tr_from_box, ~pcontained_in_box))
|
||||
arg_text_con_head[ii] = ind_min
|
||||
# print("head/fallback ", ii, "\t", (mx_head[ii], Mx_head[ii], my_head[ii], My_head[ii]), "\tin", ind_min, boxes[ind_min], only_centers)
|
||||
args_contours_head = np.arange(len(contours_only_text_parent_h))
|
||||
order_by_con_head = np.zeros_like(arg_text_con_head)
|
||||
|
||||
ref_point = 0
|
||||
order_of_texts_tot = []
|
||||
id_of_texts_tot = []
|
||||
idx = 0
|
||||
for iij, box in enumerate(boxes):
|
||||
ys = slice(*box[2:4])
|
||||
xs = slice(*box[0:2])
|
||||
|
|
@ -2552,42 +2554,30 @@ class Eynollah:
|
|||
con_inter_box = contours_only_text_parent[args_contours_box_main]
|
||||
con_inter_box_h = contours_only_text_parent_h[args_contours_box_head]
|
||||
|
||||
indexes_sorted, kind_of_texts_sorted, index_by_kind_sorted = order_of_regions(
|
||||
textline_mask_tot[ys, xs], con_inter_box, con_inter_box_h, box[2])
|
||||
_, kind_of_texts_sorted, index_by_kind_sorted = order_of_regions(
|
||||
textline_mask_tot[ys, xs], con_inter_box, con_inter_box_h, box[2], box[0])
|
||||
|
||||
order_of_texts, id_of_texts = order_and_id_of_texts(
|
||||
con_inter_box, con_inter_box_h,
|
||||
indexes_sorted, index_by_kind_sorted, kind_of_texts_sorted, ref_point)
|
||||
for tidx, kind in zip(index_by_kind_sorted, kind_of_texts_sorted):
|
||||
if kind == 1:
|
||||
# print(iij, "main", args_contours_box_main[tidx], "becomes", idx)
|
||||
order_by_con_main[args_contours_box_main[tidx]] = idx
|
||||
else:
|
||||
# print(iij, "head", args_contours_box_head[tidx], "becomes", idx)
|
||||
order_by_con_head[args_contours_box_head[tidx]] = idx
|
||||
idx += 1
|
||||
|
||||
indexes_sorted_main = indexes_sorted[kind_of_texts_sorted == 1]
|
||||
indexes_by_type_main = index_by_kind_sorted[kind_of_texts_sorted == 1]
|
||||
indexes_sorted_head = indexes_sorted[kind_of_texts_sorted == 2]
|
||||
indexes_by_type_head = index_by_kind_sorted[kind_of_texts_sorted == 2]
|
||||
|
||||
for zahler, _ in enumerate(args_contours_box_main):
|
||||
arg_order_v = indexes_sorted_main[zahler]
|
||||
order_by_con_main[args_contours_box_main[indexes_by_type_main[zahler]]] = \
|
||||
np.flatnonzero(indexes_sorted == arg_order_v) + ref_point
|
||||
|
||||
for zahler, _ in enumerate(args_contours_box_head):
|
||||
arg_order_v = indexes_sorted_head[zahler]
|
||||
order_by_con_head[args_contours_box_head[indexes_by_type_head[zahler]]] = \
|
||||
np.flatnonzero(indexes_sorted == arg_order_v) + ref_point
|
||||
|
||||
for jji in range(len(id_of_texts)):
|
||||
order_of_texts_tot.append(order_of_texts[jji] + ref_point)
|
||||
id_of_texts_tot.append(id_of_texts[jji])
|
||||
ref_point += len(id_of_texts)
|
||||
|
||||
order_of_texts_tot = np.concatenate((order_by_con_main,
|
||||
order_by_con_head))
|
||||
order_text_new = np.argsort(order_of_texts_tot)
|
||||
return order_text_new, id_of_texts_tot
|
||||
# xml writer will create region ids in order of
|
||||
# - contours_only_text_parent (main text), followed by
|
||||
# - contours_only_text_parent (headings),
|
||||
# and then create regionrefs into these ordered by order_text_new
|
||||
order_text_new = np.argsort(np.concatenate((order_by_con_main,
|
||||
order_by_con_head)))
|
||||
return order_text_new
|
||||
|
||||
try:
|
||||
results = match_boxes(False)
|
||||
except Exception as why:
|
||||
self.logger.error(why)
|
||||
self.logger.exception(why)
|
||||
results = match_boxes(True)
|
||||
|
||||
self.logger.debug("exit do_order_of_regions")
|
||||
|
|
@ -2665,45 +2655,35 @@ class Eynollah:
|
|||
|
||||
return layout_org, contours_new
|
||||
|
||||
def delete_separator_around(self, spliter_y,peaks_neg,image_by_region, pixel_line, pixel_table):
|
||||
def delete_separator_around(self, splitter_y, peaks_neg, image_by_region, label_seps, label_table):
|
||||
# format of subboxes: box=[x1, x2 , y1, y2]
|
||||
pix_del = 100
|
||||
if len(image_by_region.shape)==3:
|
||||
for i in range(len(spliter_y)-1):
|
||||
for i in range(len(splitter_y)-1):
|
||||
for j in range(1,len(peaks_neg[i])-1):
|
||||
ys = slice(int(spliter_y[i]),
|
||||
int(spliter_y[i+1]))
|
||||
xs = slice(peaks_neg[i][j] - pix_del,
|
||||
peaks_neg[i][j] + pix_del)
|
||||
image_by_region[ys,xs,0][image_by_region[ys,xs,0]==pixel_line] = 0
|
||||
image_by_region[ys,xs,0][image_by_region[ys,xs,1]==pixel_line] = 0
|
||||
image_by_region[ys,xs,0][image_by_region[ys,xs,2]==pixel_line] = 0
|
||||
|
||||
image_by_region[ys,xs,0][image_by_region[ys,xs,0]==pixel_table] = 0
|
||||
image_by_region[ys,xs,0][image_by_region[ys,xs,1]==pixel_table] = 0
|
||||
image_by_region[ys,xs,0][image_by_region[ys,xs,2]==pixel_table] = 0
|
||||
where = np.index_exp[splitter_y[i]:
|
||||
splitter_y[i+1],
|
||||
peaks_neg[i][j] - pix_del:
|
||||
peaks_neg[i][j] + pix_del,
|
||||
:]
|
||||
if image_by_region.ndim < 3:
|
||||
where = where[:2]
|
||||
else:
|
||||
for i in range(len(spliter_y)-1):
|
||||
for j in range(1,len(peaks_neg[i])-1):
|
||||
ys = slice(int(spliter_y[i]),
|
||||
int(spliter_y[i+1]))
|
||||
xs = slice(peaks_neg[i][j] - pix_del,
|
||||
peaks_neg[i][j] + pix_del)
|
||||
image_by_region[ys,xs][image_by_region[ys,xs]==pixel_line] = 0
|
||||
image_by_region[ys,xs][image_by_region[ys,xs]==pixel_table] = 0
|
||||
print("image_by_region ndim is 3!") # rs
|
||||
image_by_region[where][image_by_region[where] == label_seps] = 0
|
||||
image_by_region[where][image_by_region[where] == label_table] = 0
|
||||
return image_by_region
|
||||
|
||||
def add_tables_heuristic_to_layout(
|
||||
self, image_regions_eraly_p, boxes,
|
||||
slope_mean_hor, spliter_y, peaks_neg_tot, image_revised,
|
||||
num_col_classifier, min_area, pixel_line):
|
||||
slope_mean_hor, splitter_y, peaks_neg_tot, image_revised,
|
||||
num_col_classifier, min_area, label_seps):
|
||||
|
||||
pixel_table =10
|
||||
image_revised_1 = self.delete_separator_around(spliter_y, peaks_neg_tot, image_revised, pixel_line, pixel_table)
|
||||
label_table =10
|
||||
image_revised_1 = self.delete_separator_around(splitter_y, peaks_neg_tot, image_revised, label_seps, label_table)
|
||||
|
||||
try:
|
||||
image_revised_1[:,:30][image_revised_1[:,:30]==pixel_line] = 0
|
||||
image_revised_1[:,-30:][image_revised_1[:,-30:]==pixel_line] = 0
|
||||
image_revised_1[:,:30][image_revised_1[:,:30]==label_seps] = 0
|
||||
image_revised_1[:,-30:][image_revised_1[:,-30:]==label_seps] = 0
|
||||
except:
|
||||
pass
|
||||
boxes = np.array(boxes, dtype=int) # to be on the safe side
|
||||
|
|
@ -2714,7 +2694,7 @@ class Eynollah:
|
|||
_, thresh = cv2.threshold(image_col, 0, 255, 0)
|
||||
contours,hirarchy=cv2.findContours(thresh.copy(), cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
|
||||
|
||||
if indiv==pixel_table:
|
||||
if indiv==label_table:
|
||||
main_contours = filter_contours_area_of_image_tables(thresh, contours, hirarchy,
|
||||
max_area=1, min_area=0.001)
|
||||
else:
|
||||
|
|
@ -2730,11 +2710,11 @@ class Eynollah:
|
|||
box_xs = slice(*boxes[i][0:2])
|
||||
image_box = img_comm[box_ys, box_xs]
|
||||
try:
|
||||
image_box_tabels_1 = (image_box == pixel_table) * 1
|
||||
image_box_tabels_1 = (image_box == label_table) * 1
|
||||
contours_tab,_=return_contours_of_image(image_box_tabels_1)
|
||||
contours_tab=filter_contours_area_of_image_tables(image_box_tabels_1,contours_tab,_,1,0.003)
|
||||
image_box_tabels_1 = (image_box == pixel_line).astype(np.uint8) * 1
|
||||
image_box_tabels_and_m_text = ( (image_box == pixel_table) |
|
||||
image_box_tabels_1 = (image_box == label_seps).astype(np.uint8) * 1
|
||||
image_box_tabels_and_m_text = ( (image_box == label_table) |
|
||||
(image_box == 1) ).astype(np.uint8) * 1
|
||||
|
||||
image_box_tabels_1 = cv2.dilate(image_box_tabels_1, KERNEL, iterations=5)
|
||||
|
|
@ -2796,7 +2776,7 @@ class Eynollah:
|
|||
y_up_tabs=[]
|
||||
|
||||
for ii in range(len(y_up_tabs)):
|
||||
image_box[y_up_tabs[ii]:y_down_tabs[ii]] = pixel_table
|
||||
image_box[y_up_tabs[ii]:y_down_tabs[ii]] = label_table
|
||||
|
||||
image_revised_last[box_ys, box_xs] = image_box
|
||||
else:
|
||||
|
|
@ -2807,14 +2787,14 @@ class Eynollah:
|
|||
image_revised_last[box_ys, box_xs] = image_box
|
||||
|
||||
if num_col_classifier==1:
|
||||
img_tables_col_1 = (image_revised_last == pixel_table).astype(np.uint8)
|
||||
img_tables_col_1 = (image_revised_last == label_table).astype(np.uint8)
|
||||
contours_table_col1, _ = return_contours_of_image(img_tables_col_1)
|
||||
|
||||
_,_ ,_ , _, y_min_tab_col1 ,y_max_tab_col1, _= find_new_features_of_contours(contours_table_col1)
|
||||
|
||||
if len(y_min_tab_col1)>0:
|
||||
for ijv in range(len(y_min_tab_col1)):
|
||||
image_revised_last[int(y_min_tab_col1[ijv]):int(y_max_tab_col1[ijv])] = pixel_table
|
||||
image_revised_last[int(y_min_tab_col1[ijv]):int(y_max_tab_col1[ijv])] = label_table
|
||||
return image_revised_last
|
||||
|
||||
def get_tables_from_model(self, img, num_col_classifier):
|
||||
|
|
@ -2952,8 +2932,8 @@ class Eynollah:
|
|||
mask_images = (text_regions_p_1[:, :] == 2) * 1
|
||||
mask_images = mask_images.astype(np.uint8)
|
||||
mask_images = cv2.erode(mask_images[:, :], KERNEL, iterations=10)
|
||||
mask_lines = (text_regions_p_1[:, :] == 3) * 1
|
||||
mask_lines = mask_lines.astype(np.uint8)
|
||||
mask_seps = (text_regions_p_1[:, :] == 3) * 1
|
||||
mask_seps = mask_seps.astype(np.uint8)
|
||||
img_only_regions_with_sep = ((text_regions_p_1[:, :] != 3) & (text_regions_p_1[:, :] != 0)) * 1
|
||||
img_only_regions_with_sep = img_only_regions_with_sep.astype(np.uint8)
|
||||
|
||||
|
|
@ -2976,10 +2956,10 @@ class Eynollah:
|
|||
max(self.num_col_lower or num_col_classifier,
|
||||
num_col_classifier))
|
||||
except Exception as why:
|
||||
self.logger.error(why)
|
||||
self.logger.exception(why)
|
||||
num_col = None
|
||||
#print("inside graphics 3 ", time.time() - t_in_gr)
|
||||
return (num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines,
|
||||
return (num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_seps,
|
||||
text_regions_p_1, cont_page, table_prediction, textline_mask_tot_ea, img_bin_light)
|
||||
|
||||
def run_graphics_and_columns_without_layout(self, textline_mask_tot_ea, img_bin_light):
|
||||
|
|
@ -3029,8 +3009,8 @@ class Eynollah:
|
|||
mask_images = (text_regions_p_1[:, :] == 2) * 1
|
||||
mask_images = mask_images.astype(np.uint8)
|
||||
mask_images = cv2.erode(mask_images[:, :], KERNEL, iterations=10)
|
||||
mask_lines = (text_regions_p_1[:, :] == 3) * 1
|
||||
mask_lines = mask_lines.astype(np.uint8)
|
||||
mask_seps = (text_regions_p_1[:, :] == 3) * 1
|
||||
mask_seps = mask_seps.astype(np.uint8)
|
||||
img_only_regions_with_sep = ((text_regions_p_1[:, :] != 3) & (text_regions_p_1[:, :] != 0)) * 1
|
||||
img_only_regions_with_sep = img_only_regions_with_sep.astype(np.uint8)
|
||||
|
||||
|
|
@ -3044,9 +3024,9 @@ class Eynollah:
|
|||
if not num_column_is_classified:
|
||||
num_col_classifier = num_col + 1
|
||||
except Exception as why:
|
||||
self.logger.error(why)
|
||||
self.logger.exception(why)
|
||||
num_col = None
|
||||
return (num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines,
|
||||
return (num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_seps,
|
||||
text_regions_p_1, cont_page, table_prediction)
|
||||
|
||||
def run_enhancement(self, light_version):
|
||||
|
|
@ -3101,13 +3081,13 @@ class Eynollah:
|
|||
return slope_deskew
|
||||
|
||||
def run_marginals(
|
||||
self, textline_mask_tot_ea, mask_images, mask_lines,
|
||||
self, textline_mask_tot_ea, mask_images, mask_seps,
|
||||
num_col_classifier, slope_deskew, text_regions_p_1, table_prediction):
|
||||
|
||||
textline_mask_tot = textline_mask_tot_ea[:, :]
|
||||
textline_mask_tot[mask_images[:, :] == 1] = 0
|
||||
|
||||
text_regions_p_1[mask_lines[:, :] == 1] = 3
|
||||
text_regions_p_1[mask_seps[:, :] == 1] = 3
|
||||
text_regions_p = text_regions_p_1[:, :]
|
||||
text_regions_p = np.array(text_regions_p)
|
||||
if num_col_classifier in (1, 2):
|
||||
|
|
@ -3131,12 +3111,10 @@ class Eynollah:
|
|||
self.logger.debug('enter run_boxes_no_full_layout')
|
||||
t_0_box = time.time()
|
||||
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
|
||||
_, textline_mask_tot_d, text_regions_p_1_n, table_prediction_n = rotation_not_90_func(
|
||||
image_page, textline_mask_tot, text_regions_p, table_prediction, slope_deskew)
|
||||
text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1])
|
||||
textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1])
|
||||
table_prediction_n = resize_image(table_prediction_n, text_regions_p.shape[0], text_regions_p.shape[1])
|
||||
regions_without_separators_d = (text_regions_p_1_n[:, :] == 1) * 1
|
||||
textline_mask_tot_d = rotate_image(textline_mask_tot, slope_deskew)
|
||||
text_regions_p_d = rotate_image(text_regions_p, slope_deskew)
|
||||
table_prediction_n = rotate_image(table_prediction, slope_deskew)
|
||||
regions_without_separators_d = (text_regions_p_d[:, :] == 1) * 1
|
||||
if self.tables:
|
||||
regions_without_separators_d[table_prediction_n[:,:] == 1] = 1
|
||||
regions_without_separators = (text_regions_p[:, :] == 1) * 1
|
||||
|
|
@ -3146,17 +3124,17 @@ class Eynollah:
|
|||
if self.tables:
|
||||
regions_without_separators[table_prediction ==1 ] = 1
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
text_regions_p_1_n = None
|
||||
text_regions_p_d = None
|
||||
textline_mask_tot_d = None
|
||||
regions_without_separators_d = None
|
||||
pixel_lines = 3
|
||||
label_seps = 3
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
_, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
text_regions_p, num_col_classifier, self.tables, pixel_lines)
|
||||
_, _, matrix_of_seps_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
text_regions_p, num_col_classifier, self.tables, label_seps)
|
||||
|
||||
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
|
||||
_, _, matrix_of_lines_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_1_n, num_col_classifier, self.tables, pixel_lines)
|
||||
_, _, matrix_of_seps_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_d, num_col_classifier, self.tables, label_seps)
|
||||
#print(time.time()-t_0_box,'time box in 2')
|
||||
self.logger.info("num_col_classifier: %s", num_col_classifier)
|
||||
|
||||
|
|
@ -3171,7 +3149,7 @@ class Eynollah:
|
|||
t1 = time.time()
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
boxes, peaks_neg_tot_tables = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new, regions_without_separators, matrix_of_lines_ch,
|
||||
splitter_y_new, regions_without_separators, text_regions_p, matrix_of_seps_ch,
|
||||
num_col_classifier, erosion_hurts, self.tables, self.right2left)
|
||||
boxes_d = None
|
||||
self.logger.debug("len(boxes): %s", len(boxes))
|
||||
|
|
@ -3183,17 +3161,17 @@ class Eynollah:
|
|||
else:
|
||||
text_regions_p_tables = np.copy(text_regions_p)
|
||||
text_regions_p_tables[(table_prediction == 1)] = 10
|
||||
pixel_line = 3
|
||||
label_seps = 3
|
||||
img_revised_tab2 = self.add_tables_heuristic_to_layout(
|
||||
text_regions_p_tables, boxes, 0, splitter_y_new, peaks_neg_tot_tables, text_regions_p_tables,
|
||||
num_col_classifier , 0.000005, pixel_line)
|
||||
num_col_classifier , 0.000005, label_seps)
|
||||
#print(time.time()-t_0_box,'time box in 3.2')
|
||||
img_revised_tab2, contoures_tables = self.check_iou_of_bounding_box_and_contour_for_tables(
|
||||
img_revised_tab2, table_prediction, 10, num_col_classifier)
|
||||
#print(time.time()-t_0_box,'time box in 3.3')
|
||||
else:
|
||||
boxes_d, peaks_neg_tot_tables_d = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new_d, regions_without_separators_d, matrix_of_lines_ch_d,
|
||||
splitter_y_new_d, regions_without_separators_d, text_regions_p_d, matrix_of_seps_ch_d,
|
||||
num_col_classifier, erosion_hurts, self.tables, self.right2left)
|
||||
boxes = None
|
||||
self.logger.debug("len(boxes): %s", len(boxes_d))
|
||||
|
|
@ -3202,15 +3180,15 @@ class Eynollah:
|
|||
if self.light_version:
|
||||
pass
|
||||
else:
|
||||
text_regions_p_tables = np.copy(text_regions_p_1_n)
|
||||
text_regions_p_tables = np.copy(text_regions_p_d)
|
||||
text_regions_p_tables = np.round(text_regions_p_tables)
|
||||
text_regions_p_tables[(text_regions_p_tables != 3) & (table_prediction_n == 1)] = 10
|
||||
|
||||
pixel_line = 3
|
||||
label_seps = 3
|
||||
img_revised_tab2 = self.add_tables_heuristic_to_layout(
|
||||
text_regions_p_tables, boxes_d, 0, splitter_y_new_d,
|
||||
peaks_neg_tot_tables_d, text_regions_p_tables,
|
||||
num_col_classifier, 0.000005, pixel_line)
|
||||
num_col_classifier, 0.000005, label_seps)
|
||||
img_revised_tab2_d,_ = self.check_iou_of_bounding_box_and_contour_for_tables(
|
||||
img_revised_tab2, table_prediction_n, 10, num_col_classifier)
|
||||
|
||||
|
|
@ -3245,22 +3223,22 @@ class Eynollah:
|
|||
else:
|
||||
polygons_of_images = return_contours_of_interested_region(img_revised_tab, 2)
|
||||
|
||||
pixel_img = 4
|
||||
label_marginalia = 4
|
||||
min_area_mar = 0.00001
|
||||
if self.light_version:
|
||||
marginal_mask = (text_regions_p[:,:]==pixel_img)*1
|
||||
marginal_mask = (text_regions_p[:,:]==label_marginalia)*1
|
||||
marginal_mask = marginal_mask.astype('uint8')
|
||||
marginal_mask = cv2.dilate(marginal_mask, KERNEL, iterations=2)
|
||||
|
||||
polygons_of_marginals = return_contours_of_interested_region(marginal_mask, 1, min_area_mar)
|
||||
else:
|
||||
polygons_of_marginals = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar)
|
||||
polygons_of_marginals = return_contours_of_interested_region(text_regions_p, label_marginalia, min_area_mar)
|
||||
|
||||
pixel_img = 10
|
||||
contours_tables = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar)
|
||||
label_tables = 10
|
||||
contours_tables = return_contours_of_interested_region(text_regions_p, label_tables, min_area_mar)
|
||||
#print(time.time()-t_0_box,'time box in 5')
|
||||
self.logger.debug('exit run_boxes_no_full_layout')
|
||||
return (polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d,
|
||||
return (polygons_of_images, img_revised_tab, text_regions_p_d, textline_mask_tot_d,
|
||||
regions_without_separators_d, boxes, boxes_d,
|
||||
polygons_of_marginals, contours_tables)
|
||||
|
||||
|
|
@ -3276,24 +3254,13 @@ class Eynollah:
|
|||
text_regions_p[:,:][table_prediction[:,:]==1] = 10
|
||||
img_revised_tab = text_regions_p[:,:]
|
||||
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
|
||||
_, textline_mask_tot_d, text_regions_p_1_n, table_prediction_n = \
|
||||
rotation_not_90_func(image_page, textline_mask_tot, text_regions_p,
|
||||
table_prediction, slope_deskew)
|
||||
|
||||
text_regions_p_1_n = resize_image(text_regions_p_1_n,
|
||||
text_regions_p.shape[0],
|
||||
text_regions_p.shape[1])
|
||||
textline_mask_tot_d = resize_image(textline_mask_tot_d,
|
||||
text_regions_p.shape[0],
|
||||
text_regions_p.shape[1])
|
||||
table_prediction_n = resize_image(table_prediction_n,
|
||||
text_regions_p.shape[0],
|
||||
text_regions_p.shape[1])
|
||||
|
||||
regions_without_separators_d = (text_regions_p_1_n[:,:] == 1)*1
|
||||
textline_mask_tot_d = rotate_image(textline_mask_tot, slope_deskew)
|
||||
text_regions_p_d = rotate_image(text_regions_p, slope_deskew)
|
||||
table_prediction_n = rotate_image(table_prediction, slope_deskew)
|
||||
regions_without_separators_d = (text_regions_p_d[:,:] == 1)*1
|
||||
regions_without_separators_d[table_prediction_n[:,:] == 1] = 1
|
||||
else:
|
||||
text_regions_p_1_n = None
|
||||
text_regions_p_d = None
|
||||
textline_mask_tot_d = None
|
||||
regions_without_separators_d = None
|
||||
# regions_without_separators = ( text_regions_p[:,:]==1 | text_regions_p[:,:]==2 )*1
|
||||
|
|
@ -3303,24 +3270,13 @@ class Eynollah:
|
|||
|
||||
else:
|
||||
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
|
||||
_, textline_mask_tot_d, text_regions_p_1_n, table_prediction_n = \
|
||||
rotation_not_90_func(image_page, textline_mask_tot, text_regions_p,
|
||||
table_prediction, slope_deskew)
|
||||
|
||||
text_regions_p_1_n = resize_image(text_regions_p_1_n,
|
||||
text_regions_p.shape[0],
|
||||
text_regions_p.shape[1])
|
||||
textline_mask_tot_d = resize_image(textline_mask_tot_d,
|
||||
text_regions_p.shape[0],
|
||||
text_regions_p.shape[1])
|
||||
table_prediction_n = resize_image(table_prediction_n,
|
||||
text_regions_p.shape[0],
|
||||
text_regions_p.shape[1])
|
||||
|
||||
regions_without_separators_d = (text_regions_p_1_n[:,:] == 1)*1
|
||||
textline_mask_tot_d = rotate_image(textline_mask_tot, slope_deskew)
|
||||
text_regions_p_d = rotate_image(text_regions_p, slope_deskew)
|
||||
table_prediction_n = rotate_image(table_prediction, slope_deskew)
|
||||
regions_without_separators_d = (text_regions_p_d[:,:] == 1)*1
|
||||
regions_without_separators_d[table_prediction_n[:,:] == 1] = 1
|
||||
else:
|
||||
text_regions_p_1_n = None
|
||||
text_regions_p_d = None
|
||||
textline_mask_tot_d = None
|
||||
regions_without_separators_d = None
|
||||
|
||||
|
|
@ -3329,14 +3285,14 @@ class Eynollah:
|
|||
regions_without_separators = (text_regions_p[:,:] == 1)*1
|
||||
regions_without_separators[table_prediction == 1] = 1
|
||||
|
||||
pixel_lines=3
|
||||
label_seps=3
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
num_col, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
text_regions_p, num_col_classifier, self.tables, pixel_lines)
|
||||
num_col, _, matrix_of_seps_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
text_regions_p, num_col_classifier, self.tables, label_seps)
|
||||
|
||||
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
|
||||
num_col_d, _, matrix_of_lines_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_1_n, num_col_classifier, self.tables, pixel_lines)
|
||||
num_col_d, _, matrix_of_seps_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_d, num_col_classifier, self.tables, label_seps)
|
||||
|
||||
if num_col_classifier>=3:
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
|
|
@ -3351,30 +3307,30 @@ class Eynollah:
|
|||
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
boxes, peaks_neg_tot_tables = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new, regions_without_separators, matrix_of_lines_ch,
|
||||
splitter_y_new, regions_without_separators, text_regions_p, matrix_of_seps_ch,
|
||||
num_col_classifier, erosion_hurts, self.tables, self.right2left)
|
||||
text_regions_p_tables = np.copy(text_regions_p)
|
||||
text_regions_p_tables[:,:][(table_prediction[:,:]==1)] = 10
|
||||
pixel_line = 3
|
||||
label_seps = 3
|
||||
img_revised_tab2 = self.add_tables_heuristic_to_layout(
|
||||
text_regions_p_tables, boxes, 0, splitter_y_new, peaks_neg_tot_tables, text_regions_p_tables,
|
||||
num_col_classifier , 0.000005, pixel_line)
|
||||
num_col_classifier , 0.000005, label_seps)
|
||||
|
||||
img_revised_tab2,contoures_tables = self.check_iou_of_bounding_box_and_contour_for_tables(
|
||||
img_revised_tab2, table_prediction, 10, num_col_classifier)
|
||||
else:
|
||||
boxes_d, peaks_neg_tot_tables_d = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new_d, regions_without_separators_d, matrix_of_lines_ch_d,
|
||||
splitter_y_new_d, regions_without_separators_d, text_regions_p_d, matrix_of_seps_ch_d,
|
||||
num_col_classifier, erosion_hurts, self.tables, self.right2left)
|
||||
text_regions_p_tables = np.copy(text_regions_p_1_n)
|
||||
text_regions_p_tables = np.copy(text_regions_p_d)
|
||||
text_regions_p_tables = np.round(text_regions_p_tables)
|
||||
text_regions_p_tables[(text_regions_p_tables != 3) & (table_prediction_n == 1)] = 10
|
||||
|
||||
pixel_line = 3
|
||||
label_seps = 3
|
||||
img_revised_tab2 = self.add_tables_heuristic_to_layout(
|
||||
text_regions_p_tables, boxes_d, 0, splitter_y_new_d,
|
||||
peaks_neg_tot_tables_d, text_regions_p_tables,
|
||||
num_col_classifier, 0.000005, pixel_line)
|
||||
num_col_classifier, 0.000005, label_seps)
|
||||
|
||||
img_revised_tab2_d,_ = self.check_iou_of_bounding_box_and_contour_for_tables(
|
||||
img_revised_tab2, table_prediction_n, 10, num_col_classifier)
|
||||
|
|
@ -3399,20 +3355,20 @@ class Eynollah:
|
|||
text_regions_p[img_revised_tab == 10] = 10
|
||||
#img_revised_tab[img_revised_tab2 == 10] = 10
|
||||
|
||||
pixel_img = 4
|
||||
label_marginalia = 4
|
||||
min_area_mar = 0.00001
|
||||
|
||||
if self.light_version:
|
||||
marginal_mask = (text_regions_p[:,:]==pixel_img)*1
|
||||
marginal_mask = (text_regions_p[:,:]==label_marginalia)*1
|
||||
marginal_mask = marginal_mask.astype('uint8')
|
||||
marginal_mask = cv2.dilate(marginal_mask, KERNEL, iterations=2)
|
||||
|
||||
polygons_of_marginals = return_contours_of_interested_region(marginal_mask, 1, min_area_mar)
|
||||
else:
|
||||
polygons_of_marginals = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar)
|
||||
polygons_of_marginals = return_contours_of_interested_region(text_regions_p, label_marginalia, min_area_mar)
|
||||
|
||||
pixel_img = 10
|
||||
contours_tables = return_contours_of_interested_region(text_regions_p, pixel_img, min_area_mar)
|
||||
label_tables = 10
|
||||
contours_tables = return_contours_of_interested_region(text_regions_p, label_tables, min_area_mar)
|
||||
|
||||
# set first model with second model
|
||||
text_regions_p[:, :][text_regions_p[:, :] == 2] = 5
|
||||
|
|
@ -3465,16 +3421,13 @@ class Eynollah:
|
|||
#plt.show()
|
||||
####if not self.tables:
|
||||
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
|
||||
_, textline_mask_tot_d, text_regions_p_1_n, regions_fully_n = rotation_not_90_func_full_layout(
|
||||
image_page, textline_mask_tot, text_regions_p, regions_fully, slope_deskew)
|
||||
|
||||
text_regions_p_1_n = resize_image(text_regions_p_1_n, text_regions_p.shape[0], text_regions_p.shape[1])
|
||||
textline_mask_tot_d = resize_image(textline_mask_tot_d, text_regions_p.shape[0], text_regions_p.shape[1])
|
||||
regions_fully_n = resize_image(regions_fully_n, text_regions_p.shape[0], text_regions_p.shape[1])
|
||||
textline_mask_tot_d = rotate_image(textline_mask_tot, slope_deskew)
|
||||
text_regions_p_d = rotate_image(text_regions_p, slope_deskew)
|
||||
regions_fully_n = rotate_image(regions_fully, slope_deskew)
|
||||
if not self.tables:
|
||||
regions_without_separators_d = (text_regions_p_1_n[:, :] == 1) * 1
|
||||
regions_without_separators_d = (text_regions_p_d[:, :] == 1) * 1
|
||||
else:
|
||||
text_regions_p_1_n = None
|
||||
text_regions_p_d = None
|
||||
textline_mask_tot_d = None
|
||||
regions_without_separators_d = None
|
||||
if not self.tables:
|
||||
|
|
@ -3484,7 +3437,7 @@ class Eynollah:
|
|||
|
||||
self.logger.debug('exit run_boxes_full_layout')
|
||||
#print("full inside 3", time.time()- t_full0)
|
||||
return (polygons_of_images, img_revised_tab, text_regions_p_1_n, textline_mask_tot_d,
|
||||
return (polygons_of_images, img_revised_tab, text_regions_p_d, textline_mask_tot_d,
|
||||
regions_without_separators_d, regions_fully, regions_without_separators,
|
||||
polygons_of_marginals, contours_tables)
|
||||
|
||||
|
|
@ -3632,7 +3585,7 @@ class Eynollah:
|
|||
co_text_all = contours_only_text_parent
|
||||
|
||||
if not len(co_text_all):
|
||||
return [], []
|
||||
return []
|
||||
|
||||
labels_con = np.zeros((int(y_len /6.), int(x_len/6.), len(co_text_all)), dtype=bool)
|
||||
co_text_all = [(i/6).astype(int) for i in co_text_all]
|
||||
|
|
@ -3715,11 +3668,9 @@ class Eynollah:
|
|||
else:
|
||||
org_contours_indexes.extend([indexes_of_located_cont[region_with_curr_order]])
|
||||
|
||||
region_ids = ['region_%04d' % i for i in range(len(co_text_all_org))]
|
||||
return org_contours_indexes, region_ids
|
||||
return org_contours_indexes
|
||||
else:
|
||||
region_ids = ['region_%04d' % i for i in range(len(co_text_all_org))]
|
||||
return ordered, region_ids
|
||||
return ordered
|
||||
|
||||
def return_start_and_end_of_common_text_of_textline_ocr(self,textline_image, ind_tot):
|
||||
width = np.shape(textline_image)[1]
|
||||
|
|
@ -4213,7 +4164,7 @@ class Eynollah:
|
|||
image_page, page_coord, cont_page = \
|
||||
self.get_regions_light_v_extract_only_images(img_res, is_image_enhanced, num_col_classifier)
|
||||
pcgts = self.writer.build_pagexml_no_full_layout(
|
||||
[], page_coord, [], [], [], [],
|
||||
[], page_coord, [], [], [],
|
||||
polygons_of_images, [], [], [], [], [], [], [], [], [],
|
||||
cont_page, [], [])
|
||||
if self.plotter:
|
||||
|
|
@ -4254,7 +4205,6 @@ class Eynollah:
|
|||
|
||||
order_text_new = [0]
|
||||
slopes =[0]
|
||||
id_of_texts_tot =['region_0001']
|
||||
conf_contours_textregions =[0]
|
||||
|
||||
if self.ocr and not self.tr:
|
||||
|
|
@ -4266,7 +4216,7 @@ class Eynollah:
|
|||
ocr_all_textlines = None
|
||||
|
||||
pcgts = self.writer.build_pagexml_no_full_layout(
|
||||
cont_page, page_coord, order_text_new, id_of_texts_tot,
|
||||
cont_page, page_coord, order_text_new,
|
||||
all_found_textline_polygons, page_coord, [],
|
||||
[], [], [], [], [], [],
|
||||
slopes, [], [],
|
||||
|
|
@ -4301,7 +4251,7 @@ class Eynollah:
|
|||
slope_deskew = self.run_deskew(textline_mask_tot_ea)
|
||||
#print("text region early -2,5 in %.1fs", time.time() - t0)
|
||||
#self.logger.info("Textregion detection took %.1fs ", time.time() - t1t)
|
||||
num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines, \
|
||||
num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_seps, \
|
||||
text_regions_p_1, cont_page, table_prediction, textline_mask_tot_ea, img_bin_light = \
|
||||
self.run_graphics_and_columns_light(text_regions_p_1, textline_mask_tot_ea,
|
||||
num_col_classifier, num_column_is_classified,
|
||||
|
|
@ -4318,7 +4268,7 @@ class Eynollah:
|
|||
confidence_matrix = np.zeros((text_regions_p_1.shape[:2]))
|
||||
|
||||
t1 = time.time()
|
||||
num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_lines, \
|
||||
num_col, num_col_classifier, img_only_regions, page_coord, image_page, mask_images, mask_seps, \
|
||||
text_regions_p_1, cont_page, table_prediction = \
|
||||
self.run_graphics_and_columns(text_regions_p_1, num_col_classifier, num_column_is_classified,
|
||||
erosion_hurts)
|
||||
|
|
@ -4332,7 +4282,7 @@ class Eynollah:
|
|||
self.logger.info("No columns detected - generating empty PAGE-XML")
|
||||
|
||||
pcgts = self.writer.build_pagexml_no_full_layout(
|
||||
[], page_coord, [], [], [], [], [], [], [], [], [], [], [], [], [], [],
|
||||
[], page_coord, [], [], [], [], [], [], [], [], [], [], [], [], [],
|
||||
cont_page, [], [])
|
||||
return pcgts
|
||||
|
||||
|
|
@ -4356,12 +4306,12 @@ class Eynollah:
|
|||
image_page = resize_image(image_page,img_h_new, img_w_new )
|
||||
textline_mask_tot_ea = resize_image(textline_mask_tot_ea,img_h_new, img_w_new )
|
||||
mask_images = resize_image(mask_images,img_h_new, img_w_new )
|
||||
mask_lines = resize_image(mask_lines,img_h_new, img_w_new )
|
||||
mask_seps = resize_image(mask_seps, img_h_new, img_w_new)
|
||||
text_regions_p_1 = resize_image(text_regions_p_1,img_h_new, img_w_new )
|
||||
table_prediction = resize_image(table_prediction,img_h_new, img_w_new )
|
||||
|
||||
textline_mask_tot, text_regions_p = \
|
||||
self.run_marginals(textline_mask_tot_ea, mask_images, mask_lines,
|
||||
self.run_marginals(textline_mask_tot_ea, mask_images, mask_seps,
|
||||
num_col_classifier, slope_deskew, text_regions_p_1, table_prediction)
|
||||
if self.plotter:
|
||||
self.plotter.save_plot_of_layout_main_all(text_regions_p, image_page)
|
||||
|
|
@ -4398,14 +4348,14 @@ class Eynollah:
|
|||
## birdan sora chock chakir
|
||||
t1 = time.time()
|
||||
if not self.full_layout:
|
||||
polygons_of_images, img_revised_tab, text_regions_p_1_n, \
|
||||
polygons_of_images, img_revised_tab, text_regions_p_d, \
|
||||
textline_mask_tot_d, regions_without_separators_d, \
|
||||
boxes, boxes_d, polygons_of_marginals, contours_tables = \
|
||||
self.run_boxes_no_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew,
|
||||
num_col_classifier, table_prediction, erosion_hurts)
|
||||
###polygons_of_marginals = dilate_textregion_contours(polygons_of_marginals)
|
||||
else:
|
||||
polygons_of_images, img_revised_tab, text_regions_p_1_n, \
|
||||
polygons_of_images, img_revised_tab, text_regions_p_d, \
|
||||
textline_mask_tot_d, regions_without_separators_d, \
|
||||
regions_fully, regions_without_separators, polygons_of_marginals, contours_tables = \
|
||||
self.run_boxes_full_layout(image_page, textline_mask_tot, text_regions_p, slope_deskew,
|
||||
|
|
@ -4419,7 +4369,7 @@ class Eynollah:
|
|||
|
||||
text_only = (img_revised_tab[:, :] == 1) * 1
|
||||
if np.abs(slope_deskew) >= SLOPE_THRESHOLD:
|
||||
text_only_d = (text_regions_p_1_n[:, :] == 1) * 1
|
||||
text_only_d = ((text_regions_p_d[:, :] == 1)) * 1
|
||||
|
||||
#print("text region early 2 in %.1fs", time.time() - t0)
|
||||
###min_con_area = 0.000005
|
||||
|
|
@ -4493,7 +4443,7 @@ class Eynollah:
|
|||
dists[i] = np.linalg.norm(centers[:, i:i + 1] - centers_d, axis=0)
|
||||
corresp = np.zeros(dists.shape, dtype=bool)
|
||||
# keep searching next-closest until at least one correspondence on each side
|
||||
while not np.all(corresp.sum(axis=1)) and not np.all(corresp.sum(axis=0)):
|
||||
while not np.all(corresp.sum(axis=1)) or not np.all(corresp.sum(axis=0)):
|
||||
idx = np.nanargmin(dists)
|
||||
i, j = np.unravel_index(idx, dists.shape)
|
||||
dists[i, j] = np.nan
|
||||
|
|
@ -4504,7 +4454,7 @@ class Eynollah:
|
|||
# img1 = np.zeros(text_only_d.shape[:2], dtype=np.uint8)
|
||||
# for i in range(len(contours_only_text_parent)):
|
||||
# cv2.fillPoly(img1, pts=[contours_only_text_parent_d_ordered[i]], color=i + 1)
|
||||
# plt.subplot(2, 2, 1, title="direct corresp contours")
|
||||
# plt.subplot(1, 4, 1, title="direct corresp contours")
|
||||
# plt.imshow(img1)
|
||||
# img2 = np.zeros(text_only_d.shape[:2], dtype=np.uint8)
|
||||
# join deskewed regions mapping to single original ones
|
||||
|
|
@ -4517,13 +4467,13 @@ class Eynollah:
|
|||
contour_d = polygon2contour(join_polygons(polygons_d))
|
||||
contours_only_text_parent_d_ordered[i] = contour_d
|
||||
# cv2.fillPoly(img2, pts=[contour_d], color=i + 1)
|
||||
# plt.subplot(2, 2, 3, title="joined contours")
|
||||
# plt.subplot(1, 4, 2, title="joined contours")
|
||||
# plt.imshow(img2)
|
||||
# img3 = np.zeros(text_only_d.shape[:2], dtype=np.uint8)
|
||||
# split deskewed regions mapping to multiple original ones
|
||||
def deskew(polygon):
|
||||
polygon = shapely.affinity.rotate(polygon, -slope_deskew, origin=center)
|
||||
polygon = shapely.affinity.translate(polygon, *offset.squeeze())
|
||||
#polygon = shapely.affinity.translate(polygon, *offset.squeeze())
|
||||
return polygon
|
||||
for j in range(len(contours_only_text_parent_d)):
|
||||
if np.count_nonzero(corresp[:, j]) > 1:
|
||||
|
|
@ -4541,21 +4491,45 @@ class Eynollah:
|
|||
if polygon_d]
|
||||
contours_only_text_parent_d_ordered[indices] = contours_d
|
||||
# cv2.fillPoly(img3, pts=contours_d, color=j + 1)
|
||||
# plt.subplot(2, 2, 4, title="split contours")
|
||||
# plt.subplot(1, 4, 3, title="split contours")
|
||||
# plt.imshow(img3)
|
||||
# img4 = np.zeros(text_only_d.shape[:2], dtype=np.uint8)
|
||||
# for i in range(len(contours_only_text_parent)):
|
||||
# cv2.fillPoly(img4, pts=[contours_only_text_parent_d_ordered[i]], color=i + 1)
|
||||
# plt.subplot(2, 2, 2, title="result contours")
|
||||
# plt.subplot(1, 4, 4, title="result contours")
|
||||
# plt.imshow(img4)
|
||||
# plt.show()
|
||||
# from matplotlib import patches as ptchs
|
||||
# plt.subplot(1, 2, 1, title="undeskewed")
|
||||
# plt.imshow(text_only)
|
||||
# centers = np.stack(find_center_of_contours(contours_only_text_parent)) # [2, N]
|
||||
# for i in range(len(contours_only_text_parent)):
|
||||
# cnt = contours_only_text_parent[i]
|
||||
# ctr = centers[:, i]
|
||||
# plt.gca().add_patch(ptchs.Polygon(cnt[:, 0], closed=False, fill=False, color='blue'))
|
||||
# plt.gca().scatter(ctr[0], ctr[1], 20, c='blue', marker='x')
|
||||
# plt.gca().text(ctr[0], ctr[1], str(i), c='blue')
|
||||
# plt.subplot(1, 2, 2, title="deskewed")
|
||||
# plt.imshow(text_only_d)
|
||||
# centers_d = np.stack(find_center_of_contours(contours_only_text_parent_d_ordered)) # [2, N]
|
||||
# for i in range(len(contours_only_text_parent)):
|
||||
# cnt = contours_only_text_parent[i]
|
||||
# cnt = polygon2contour(deskew(contour2polygon(cnt)))
|
||||
# plt.gca().add_patch(ptchs.Polygon(cnt[:, 0], closed=False, fill=False, color='blue'))
|
||||
# for i in range(len(contours_only_text_parent_d_ordered)):
|
||||
# cnt = contours_only_text_parent_d_ordered[i]
|
||||
# ctr = centers_d[:, i]
|
||||
# plt.gca().add_patch(ptchs.Polygon(cnt[:, 0], closed=False, fill=False, color='red'))
|
||||
# plt.gca().scatter(ctr[0], ctr[1], 20, c='red', marker='x')
|
||||
# plt.gca().text(ctr[0], ctr[1], str(i), c='red')
|
||||
# plt.show()
|
||||
|
||||
if not len(contours_only_text_parent):
|
||||
# stop early
|
||||
empty_marginals = [[]] * len(polygons_of_marginals)
|
||||
if self.full_layout:
|
||||
pcgts = self.writer.build_pagexml_full_layout(
|
||||
[], [], page_coord, [], [], [], [], [], [],
|
||||
[], [], page_coord, [], [], [], [], [],
|
||||
polygons_of_images, contours_tables, [],
|
||||
polygons_of_marginals, polygons_of_marginals,
|
||||
empty_marginals, empty_marginals,
|
||||
|
|
@ -4564,7 +4538,7 @@ class Eynollah:
|
|||
cont_page, polygons_seplines)
|
||||
else:
|
||||
pcgts = self.writer.build_pagexml_no_full_layout(
|
||||
[], page_coord, [], [], [], [],
|
||||
[], page_coord, [], [], [],
|
||||
polygons_of_images,
|
||||
polygons_of_marginals, polygons_of_marginals,
|
||||
empty_marginals, empty_marginals,
|
||||
|
|
@ -4695,18 +4669,18 @@ class Eynollah:
|
|||
label_seps = 6
|
||||
if not self.headers_off:
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
num_col, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
num_col, _, matrix_of_seps_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
text_regions_p, num_col_classifier, self.tables, label_seps, contours_only_text_parent_h)
|
||||
else:
|
||||
_, _, matrix_of_lines_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_1_n, num_col_classifier, self.tables, label_seps, contours_only_text_parent_h_d_ordered)
|
||||
_, _, matrix_of_seps_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_d, num_col_classifier, self.tables, label_seps, contours_only_text_parent_h_d_ordered)
|
||||
elif self.headers_off:
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
num_col, _, matrix_of_lines_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
num_col, _, matrix_of_seps_ch, splitter_y_new, _ = find_number_of_columns_in_document(
|
||||
text_regions_p, num_col_classifier, self.tables, label_seps)
|
||||
else:
|
||||
_, _, matrix_of_lines_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_1_n, num_col_classifier, self.tables, label_seps)
|
||||
_, _, matrix_of_seps_ch_d, splitter_y_new_d, _ = find_number_of_columns_in_document(
|
||||
text_regions_p_d, num_col_classifier, self.tables, label_seps)
|
||||
|
||||
if num_col_classifier >= 3:
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
|
|
@ -4717,13 +4691,13 @@ class Eynollah:
|
|||
regions_without_separators_d = cv2.erode(regions_without_separators_d[:, :], KERNEL, iterations=6)
|
||||
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
boxes, peaks_neg_tot_tables = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new, regions_without_separators, matrix_of_lines_ch,
|
||||
boxes, _ = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new, regions_without_separators, text_regions_p, matrix_of_seps_ch,
|
||||
num_col_classifier, erosion_hurts, self.tables, self.right2left,
|
||||
logger=self.logger)
|
||||
else:
|
||||
boxes_d, peaks_neg_tot_tables_d = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new_d, regions_without_separators_d, matrix_of_lines_ch_d,
|
||||
boxes_d, _ = return_boxes_of_images_by_order_of_reading_new(
|
||||
splitter_y_new_d, regions_without_separators_d, text_regions_p_d, matrix_of_seps_ch_d,
|
||||
num_col_classifier, erosion_hurts, self.tables, self.right2left,
|
||||
logger=self.logger)
|
||||
else:
|
||||
|
|
@ -4744,14 +4718,14 @@ class Eynollah:
|
|||
self.logger.info("Headers ignored in reading order")
|
||||
|
||||
if self.reading_order_machine_based:
|
||||
order_text_new, id_of_texts_tot = self.do_order_of_regions_with_model(
|
||||
order_text_new = self.do_order_of_regions_with_model(
|
||||
contours_only_text_parent, contours_only_text_parent_h, text_regions_p)
|
||||
else:
|
||||
if np.abs(slope_deskew) < SLOPE_THRESHOLD:
|
||||
order_text_new, id_of_texts_tot = self.do_order_of_regions(
|
||||
order_text_new = self.do_order_of_regions(
|
||||
contours_only_text_parent, contours_only_text_parent_h, boxes, textline_mask_tot)
|
||||
else:
|
||||
order_text_new, id_of_texts_tot = self.do_order_of_regions(
|
||||
order_text_new = self.do_order_of_regions(
|
||||
contours_only_text_parent_d_ordered, contours_only_text_parent_h_d_ordered,
|
||||
boxes_d, textline_mask_tot_d)
|
||||
self.logger.info(f"Detection of reading order took {time.time() - t_order:.1f}s")
|
||||
|
|
@ -4848,7 +4822,7 @@ class Eynollah:
|
|||
|
||||
if self.full_layout:
|
||||
pcgts = self.writer.build_pagexml_full_layout(
|
||||
contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new, id_of_texts_tot,
|
||||
contours_only_text_parent, contours_only_text_parent_h, page_coord, order_text_new,
|
||||
all_found_textline_polygons, all_found_textline_polygons_h, all_box_coord, all_box_coord_h,
|
||||
polygons_of_images, contours_tables, polygons_of_drop_capitals,
|
||||
polygons_of_marginals_left, polygons_of_marginals_right,
|
||||
|
|
@ -4861,7 +4835,7 @@ class Eynollah:
|
|||
conf_contours_textregions, conf_contours_textregions_h)
|
||||
else:
|
||||
pcgts = self.writer.build_pagexml_no_full_layout(
|
||||
contours_only_text_parent, page_coord, order_text_new, id_of_texts_tot,
|
||||
contours_only_text_parent, page_coord, order_text_new,
|
||||
all_found_textline_polygons, all_box_coord, polygons_of_images,
|
||||
polygons_of_marginals_left, polygons_of_marginals_right,
|
||||
all_found_textline_polygons_marginals_left, all_found_textline_polygons_marginals_right,
|
||||
|
|
|
|||
|
|
@ -70,7 +70,7 @@ class SbbBinarizeProcessor(Processor):
|
|||
|
||||
if oplevel == 'page':
|
||||
self.logger.info("Binarizing on 'page' level in page '%s'", page_id)
|
||||
page_image_bin = cv2pil(self.binarizer.run(image=pil2cv(page_image), use_patches=True))
|
||||
page_image_bin = cv2pil(self.binarizer.run_single(image=pil2cv(page_image), use_patches=True))
|
||||
# update PAGE (reference the image file):
|
||||
page_image_ref = AlternativeImageType(comments=page_xywh['features'] + ',binarized,clipped')
|
||||
page.add_AlternativeImage(page_image_ref)
|
||||
|
|
@ -83,7 +83,7 @@ class SbbBinarizeProcessor(Processor):
|
|||
for region in regions:
|
||||
region_image, region_xywh = self.workspace.image_from_segment(
|
||||
region, page_image, page_xywh, feature_filter='binarized')
|
||||
region_image_bin = cv2pil(self.binarizer.run(image=pil2cv(region_image), use_patches=True))
|
||||
region_image_bin = cv2pil(self.binarizer.run_single(image=pil2cv(region_image), use_patches=True))
|
||||
# update PAGE (reference the image file):
|
||||
region_image_ref = AlternativeImageType(comments=region_xywh['features'] + ',binarized')
|
||||
region.add_AlternativeImage(region_image_ref)
|
||||
|
|
@ -95,7 +95,7 @@ class SbbBinarizeProcessor(Processor):
|
|||
self.logger.warning("Page '%s' contains no text lines", page_id)
|
||||
for line in lines:
|
||||
line_image, line_xywh = self.workspace.image_from_segment(line, page_image, page_xywh, feature_filter='binarized')
|
||||
line_image_bin = cv2pil(self.binarizer.run(image=pil2cv(line_image), use_patches=True))
|
||||
line_image_bin = cv2pil(self.binarizer.run_single(image=pil2cv(line_image), use_patches=True))
|
||||
# update PAGE (reference the image file):
|
||||
line_image_ref = AlternativeImageType(comments=line_xywh['features'] + ',binarized')
|
||||
line.add_AlternativeImage(region_image_ref)
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ class SbbBinarizer:
|
|||
|
||||
def __init__(self, model_dir, logger=None):
|
||||
self.model_dir = model_dir
|
||||
self.log = logger if logger else logging.getLogger('SbbBinarizer')
|
||||
self.logger = logger if logger else logging.getLogger('SbbBinarizer')
|
||||
|
||||
self.start_new_session()
|
||||
|
||||
|
|
@ -315,47 +315,30 @@ class SbbBinarizer:
|
|||
prediction_true = prediction_true.astype(np.uint8)
|
||||
return prediction_true[:,:,0]
|
||||
|
||||
def run(self, image=None, image_path=None, output=None, use_patches=False, dir_in=None):
|
||||
# print(dir_in,'dir_in')
|
||||
if not dir_in:
|
||||
if (image is not None and image_path is not None) or \
|
||||
(image is None and image_path is None):
|
||||
raise ValueError("Must pass either a opencv2 image or an image_path")
|
||||
if image_path is not None:
|
||||
image = cv2.imread(image_path)
|
||||
img_last = 0
|
||||
for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
|
||||
self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
|
||||
|
||||
res = self.predict(model, image, use_patches)
|
||||
|
||||
img_fin = np.zeros((res.shape[0], res.shape[1], 3))
|
||||
res[:, :][res[:, :] == 0] = 2
|
||||
res = res - 1
|
||||
res = res * 255
|
||||
img_fin[:, :, 0] = res
|
||||
img_fin[:, :, 1] = res
|
||||
img_fin[:, :, 2] = res
|
||||
|
||||
img_fin = img_fin.astype(np.uint8)
|
||||
img_fin = (res[:, :] == 0) * 255
|
||||
img_last = img_last + img_fin
|
||||
|
||||
kernel = np.ones((5, 5), np.uint8)
|
||||
img_last[:, :][img_last[:, :] > 0] = 255
|
||||
img_last = (img_last[:, :] == 0) * 255
|
||||
if output:
|
||||
cv2.imwrite(output, img_last)
|
||||
return img_last
|
||||
def run(self, image_path=None, output=None, dir_in=None, use_patches=False, overwrite=False):
|
||||
if dir_in:
|
||||
ls_imgs = [(os.path.join(dir_in, image_filename),
|
||||
os.path.join(output, os.path.splitext(image_filename)[0] + '.png'))
|
||||
for image_filename in filter(is_image_filename,
|
||||
os.listdir(dir_in))]
|
||||
else:
|
||||
ls_imgs = list(filter(is_image_filename, os.listdir(dir_in)))
|
||||
for image_name in ls_imgs:
|
||||
image_stem = image_name.split('.')[0]
|
||||
print(image_name,'image_name')
|
||||
image = cv2.imread(os.path.join(dir_in,image_name) )
|
||||
ls_imgs = [(image_path, output)]
|
||||
|
||||
for input_path, output_path in ls_imgs:
|
||||
print(input_path, 'image_name')
|
||||
if os.path.exists(output_path):
|
||||
if overwrite:
|
||||
self.logger.warning("will overwrite existing output file '%s'", output_path)
|
||||
else:
|
||||
self.logger.warning("will skip input for existing output file '%s'", output_path)
|
||||
image = cv2.imread(input_path)
|
||||
result = self.run_single(image, use_patches)
|
||||
cv2.imwrite(output_path, result)
|
||||
|
||||
def run_single(self, image: np.ndarray, use_patches=False):
|
||||
img_last = 0
|
||||
for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
|
||||
self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
|
||||
self.logger.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
|
||||
|
||||
res = self.predict(model, image, use_patches)
|
||||
|
||||
|
|
@ -374,5 +357,4 @@ class SbbBinarizer:
|
|||
kernel = np.ones((5, 5), np.uint8)
|
||||
img_last[:, :][img_last[:, :] > 0] = 255
|
||||
img_last = (img_last[:, :] == 0) * 255
|
||||
|
||||
cv2.imwrite(os.path.join(output, image_stem + '.png'), img_last)
|
||||
return img_last
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -14,21 +14,16 @@ from shapely.ops import unary_union, nearest_points
|
|||
from .rotate import rotate_image, rotation_image_new
|
||||
|
||||
def contours_in_same_horizon(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)))
|
||||
|
||||
X1[0::1, :] = cy_main_hor[:]
|
||||
X2 = X1.T
|
||||
|
||||
X_dif = np.abs(X2 - X1)
|
||||
args_help = np.array(range(len(cy_main_hor)))
|
||||
all_args = []
|
||||
for i in range(len(cy_main_hor)):
|
||||
list_h = list(args_help[X_dif[i, :] <= 20])
|
||||
list_h.append(i)
|
||||
if len(list_h) > 1:
|
||||
all_args.append(list(set(list_h)))
|
||||
return np.unique(np.array(all_args, dtype=object))
|
||||
"""
|
||||
Takes an array of y coords, identifies all pairs among them
|
||||
which are close to each other, and returns all such pairs
|
||||
by index into the array.
|
||||
"""
|
||||
sort = np.argsort(cy_main_hor)
|
||||
same = np.diff(cy_main_hor[sort] <= 20)
|
||||
# groups = np.split(sort, np.arange(len(cy_main_hor) - 1)[~same] + 1)
|
||||
same = np.flatnonzero(same)
|
||||
return np.stack((sort[:-1][same], sort[1:][same])).T
|
||||
|
||||
def find_contours_mean_y_diff(contours_main):
|
||||
M_main = [cv2.moments(contours_main[j]) for j in range(len(contours_main))]
|
||||
|
|
|
|||
|
|
@ -89,7 +89,7 @@ class EynollahXmlWriter:
|
|||
|
||||
def build_pagexml_no_full_layout(
|
||||
self, found_polygons_text_region,
|
||||
page_coord, order_of_texts, id_of_texts,
|
||||
page_coord, order_of_texts,
|
||||
all_found_textline_polygons,
|
||||
all_box_coord,
|
||||
found_polygons_text_region_img,
|
||||
|
|
@ -102,7 +102,7 @@ class EynollahXmlWriter:
|
|||
**kwargs):
|
||||
return self.build_pagexml_full_layout(
|
||||
found_polygons_text_region, [],
|
||||
page_coord, order_of_texts, id_of_texts,
|
||||
page_coord, order_of_texts,
|
||||
all_found_textline_polygons, [],
|
||||
all_box_coord, [],
|
||||
found_polygons_text_region_img, found_polygons_tables, [],
|
||||
|
|
@ -116,7 +116,7 @@ class EynollahXmlWriter:
|
|||
def build_pagexml_full_layout(
|
||||
self,
|
||||
found_polygons_text_region, found_polygons_text_region_h,
|
||||
page_coord, order_of_texts, id_of_texts,
|
||||
page_coord, order_of_texts,
|
||||
all_found_textline_polygons, all_found_textline_polygons_h,
|
||||
all_box_coord, all_box_coord_h,
|
||||
found_polygons_text_region_img, found_polygons_tables, found_polygons_drop_capitals,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue