qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-12-15 15:44:13 +01:00
Code Issues Projects Releases Wiki Activity

Merge 9fdae72e96 into 38c028c6b5

Browse source
This commit is contained in:
Robert Sachunsky 2025-12-03 02:05:39 +00:00 • committed by GitHub
commit 92897c5f4b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 1327 additions and 1588 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/eynollah/cli.py
View file

@ -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()

483
src/eynollah/eynollah.py
View file

File diff suppressed because it is too large Load diff

6
src/eynollah/ocrd_cli_binarization.py
View file

@ -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)

94
src/eynollah/sbb_binarize.py
View file

@ -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()
@ -315,64 +315,46 @@ 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) )
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)))
ls_imgs = [(image_path, output)]
res = self.predict(model, image, use_patches)
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)
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
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.logger.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
img_fin = img_fin.astype(np.uint8)
img_fin = (res[:, :] == 0) * 255
img_last = img_last + img_fin
res = self.predict(model, image, use_patches)
kernel = np.ones((5, 5), np.uint8)
img_last[:, :][img_last[:, :] > 0] = 255
img_last = (img_last[:, :] == 0) * 255
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
cv2.imwrite(os.path.join(output, image_stem + '.png'), img_last)
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
return img_last

2053
src/eynollah/utils/__init__.py
View file

File diff suppressed because it is too large Load diff

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

@ -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))]

131
src/eynollah/utils/separate_lines.py
View file

@ -403,14 +403,14 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
point_down_rot3=point_down_rot3-y_help
point_down_rot4=point_down_rot4-y_help
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(point_up)],
[int(x_max), int(point_up)],
[int(x_max), int(point_down)],
[int(x_min), int(point_down)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(point_up)]],
[[int(x_max), int(point_up)]],
[[int(x_max), int(point_down)]],
[[int(x_min), int(point_down)]]]))
elif len(peaks) < 1:
pass
@ -462,14 +462,14 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
point_down_rot3=point_down_rot3-y_help
point_down_rot4=point_down_rot4-y_help
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(y_min)],
[int(x_max), int(y_min)],
[int(x_max), int(y_max)],
[int(x_min), int(y_max)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(y_min)]],
[[int(x_max), int(y_min)]],
[[int(x_max), int(y_max)]],
[[int(x_min), int(y_max)]]]))
elif len(peaks) == 2:
dis_to_next = np.abs(peaks[1] - peaks[0])
for jj in range(len(peaks)):
@ -530,14 +530,14 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
point_down_rot3=point_down_rot3-y_help
point_down_rot4=point_down_rot4-y_help
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(point_up)],
[int(x_max), int(point_up)],
[int(x_max), int(point_down)],
[int(x_min), int(point_down)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(point_up)]],
[[int(x_max), int(point_up)]],
[[int(x_max), int(point_down)]],
[[int(x_min), int(point_down)]]]))
else:
for jj in range(len(peaks)):
if jj == 0:
@ -606,14 +606,14 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
point_down_rot3=point_down_rot3-y_help
point_down_rot4=point_down_rot4-y_help
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(point_up)],
[int(x_max), int(point_up)],
[int(x_max), int(point_down)],
[int(x_min), int(point_down)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(point_up)]],
[[int(x_max), int(point_up)]],
[[int(x_max), int(point_down)]],
[[int(x_min), int(point_down)]]]))
return peaks, textline_boxes_rot
def separate_lines_vertical(img_patch, contour_text_interest, thetha):
@ -785,14 +785,14 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
if point_up_rot2 < 0:
point_up_rot2 = 0
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(point_up)],
[int(x_max), int(point_up)],
[int(x_max), int(point_down)],
[int(x_min), int(point_down)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(point_up)]],
[[int(x_max), int(point_up)]],
[[int(x_max), int(point_down)]],
[[int(x_min), int(point_down)]]]))
elif len(peaks) < 1:
pass
elif len(peaks) == 1:
@ -821,14 +821,14 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
if point_up_rot2 < 0:
point_up_rot2 = 0
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(y_min)],
[int(x_max), int(y_min)],
[int(x_max), int(y_max)],
[int(x_min), int(y_max)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(y_min)]],
[[int(x_max), int(y_min)]],
[[int(x_max), int(y_max)]],
[[int(x_min), int(y_max)]]]))
elif len(peaks) == 2:
dis_to_next = np.abs(peaks[1] - peaks[0])
for jj in range(len(peaks)):
@ -876,14 +876,14 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
if point_up_rot2 < 0:
point_up_rot2 = 0
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(point_up)],
[int(x_max), int(point_up)],
[int(x_max), int(point_down)],
[int(x_min), int(point_down)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(point_up)]],
[[int(x_max), int(point_up)]],
[[int(x_max), int(point_down)]],
[[int(x_min), int(point_down)]]]))
else:
for jj in range(len(peaks)):
if jj == 0:
@ -942,14 +942,14 @@ def separate_lines_vertical(img_patch, contour_text_interest, thetha):
if point_up_rot2 < 0:
point_up_rot2 = 0
textline_boxes_rot.append(np.array([[int(x_min_rot1), int(point_up_rot1)],
[int(x_max_rot2), int(point_up_rot2)],
[int(x_max_rot3), int(point_down_rot3)],
[int(x_min_rot4), int(point_down_rot4)]]))
textline_boxes.append(np.array([[int(x_min), int(point_up)],
[int(x_max), int(point_up)],
[int(x_max), int(point_down)],
[int(x_min), int(point_down)]]))
textline_boxes_rot.append(np.array([[[int(x_min_rot1), int(point_up_rot1)]],
[[int(x_max_rot2), int(point_up_rot2)]],
[[int(x_max_rot3), int(point_down_rot3)]],
[[int(x_min_rot4), int(point_down_rot4)]]]))
textline_boxes.append(np.array([[[int(x_min), int(point_up)]],
[[int(x_max), int(point_up)]],
[[int(x_max), int(point_down)]],
[[int(x_min), int(point_down)]]]))
return peaks, textline_boxes_rot
def separate_lines_new_inside_tiles2(img_patch, thetha):
@ -1564,6 +1564,9 @@ def return_deskew_slop(img_patch_org, sigma_des,n_tot_angles=100,
angle2, var2 = get_smallest_skew(img_resized, sigma_des, angles2, map=map, logger=logger, plotter=plotter)
if var2 > var:
angle = angle2
# precision stage:
angles = np.linspace(angle - 2.5, angle + 2.5, n_tot_angles // 2)
angle, _ = get_smallest_skew(img_resized, sigma_des, angles, map=map, logger=logger, plotter=plotter)
return angle
def get_smallest_skew(img, sigma_des, angles, logger=None, plotter=None, map=map):

4
src/eynollah/utils/utils_ocr.py
View file

@ -369,8 +369,8 @@ def break_curved_line_into_small_pieces_and_then_merge(img_curved, mask_curved,
return img_curved, img_bin_curved
def return_textline_contour_with_added_box_coordinate(textline_contour, box_ind):
textline_contour[:,0] = textline_contour[:,0] + box_ind[2]
textline_contour[:,1] = textline_contour[:,1] + box_ind[0]
textline_contour[:,:,0] += box_ind[2]
textline_contour[:,:,1] += box_ind[0]
return textline_contour

99
src/eynollah/writer.py
View file

@ -3,10 +3,10 @@
from pathlib import Path
import os.path
import xml.etree.ElementTree as ET
from .utils.xml import create_page_xml, xml_reading_order
from .utils.counter import EynollahIdCounter
import numpy as np
from shapely import affinity, clip_by_rect
from ocrd_utils import getLogger
from ocrd_utils import getLogger, points_from_polygon
from ocrd_models.ocrd_page import (
BorderType,
CoordsType,
@ -19,7 +19,10 @@ from ocrd_models.ocrd_page import (
SeparatorRegionType,
to_xml
)
import numpy as np
from .utils.xml import create_page_xml, xml_reading_order
from .utils.counter import EynollahIdCounter
from .utils.contour import contour2polygon, make_valid
class EynollahXmlWriter:
@ -41,20 +44,14 @@ class EynollahXmlWriter:
def image_filename_stem(self):
return Path(Path(self.image_filename).name).stem
def calculate_page_coords(self, cont_page):
self.logger.debug('enter calculate_page_coords')
points_page_print = ""
for _, contour in enumerate(cont_page[0]):
if len(contour) == 2:
points_page_print += str(int((contour[0]) / self.scale_x))
points_page_print += ','
points_page_print += str(int((contour[1]) / self.scale_y))
else:
points_page_print += str(int((contour[0][0]) / self.scale_x))
points_page_print += ','
points_page_print += str(int((contour[0][1] ) / self.scale_y))
points_page_print = points_page_print + ' '
return points_page_print[:-1]
def calculate_points(self, contour, offset=None):
self.logger.debug('enter calculate_points')
poly = contour2polygon(contour)
if offset is not None:
poly = affinity.translate(poly, *offset)
poly = affinity.scale(poly, xfact=1 / self.scale_x, yfact=1 / self.scale_y, origin=(0, 0))
poly = make_valid(clip_by_rect(poly, 0, 0, self.width_org, self.height_org))
return points_from_polygon(poly.exterior.coords[:-1])
def serialize_lines_in_region(self, text_region, all_found_textline_polygons, region_idx, page_coord, all_box_coord, slopes, counter, ocr_all_textlines_textregion):
self.logger.debug('enter serialize_lines_in_region')
@ -67,20 +64,12 @@ class EynollahXmlWriter:
text_region.add_TextLine(textline)
text_region.set_orientation(-slopes[region_idx])
region_bboxes = all_box_coord[region_idx]
points_co = ''
for point in polygon_textline:
if len(point) != 2:
point = point[0]
point_x = point[0] + page_coord[2]
point_y = point[1] + page_coord[0]
# FIXME: or actually... not self.textline_light and not self.curved_line or np.abs(slopes[region_idx]) > 45?
if not self.textline_light and not (self.curved_line and np.abs(slopes[region_idx]) <= 45):
point_x += region_bboxes[2]
point_y += region_bboxes[0]
point_x = max(0, int(point_x / self.scale_x))
point_y = max(0, int(point_y / self.scale_y))
points_co += str(point_x) + ',' + str(point_y) + ' '
coords.set_points(points_co[:-1])
offset = [page_coord[2], page_coord[0]]
# FIXME: or actually... not self.textline_light and not self.curved_line or np.abs(slopes[region_idx]) > 45?
if not self.textline_light and not (self.curved_line and np.abs(slopes[region_idx]) <= 45):
offset[0] += region_bboxes[2]
offset[1] += region_bboxes[0]
coords.set_points(self.calculate_points(polygon_textline, offset))
def write_pagexml(self, pcgts):
self.logger.info("output filename: '%s'", self.output_filename)
@ -89,7 +78,7 @@ 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 +91,7 @@ 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 +105,7 @@ 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,
@ -135,8 +124,13 @@ class EynollahXmlWriter:
# create the file structure
pcgts = self.pcgts if self.pcgts else create_page_xml(self.image_filename, self.height_org, self.width_org)
page = pcgts.get_Page()
page.set_Border(BorderType(Coords=CoordsType(points=self.calculate_page_coords(cont_page))))
if len(cont_page):
page.set_Border(BorderType(Coords=CoordsType(points=self.calculate_points(cont_page[0]))))
if skip_layout_reading_order:
offset = None
else:
offset = [page_coord[2], page_coord[0]]
counter = EynollahIdCounter()
if len(order_of_texts):
_counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts))
@ -149,8 +143,7 @@ class EynollahXmlWriter:
for mm, region_contour in enumerate(found_polygons_text_region):
textregion = TextRegionType(
id=counter.next_region_id, type_='paragraph',
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, page_coord,
skip_layout_reading_order))
Coords=CoordsType(points=self.calculate_points(region_contour, offset))
)
if conf_contours_textregions:
textregion.Coords.set_conf(conf_contours_textregions[mm])
@ -166,7 +159,7 @@ class EynollahXmlWriter:
for mm, region_contour in enumerate(found_polygons_text_region_h):
textregion = TextRegionType(
id=counter.next_region_id, type_='heading',
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, page_coord))
Coords=CoordsType(points=self.calculate_points(region_contour, offset))
)
if conf_contours_textregions_h:
textregion.Coords.set_conf(conf_contours_textregions_h[mm])
@ -181,7 +174,7 @@ class EynollahXmlWriter:
for mm, region_contour in enumerate(found_polygons_marginals_left):
marginal = TextRegionType(
id=counter.next_region_id, type_='marginalia',
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, page_coord))
Coords=CoordsType(points=self.calculate_points(region_contour, offset))
)
page.add_TextRegion(marginal)
if ocr_all_textlines_marginals_left:
@ -193,7 +186,7 @@ class EynollahXmlWriter:
for mm, region_contour in enumerate(found_polygons_marginals_right):
marginal = TextRegionType(
id=counter.next_region_id, type_='marginalia',
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, page_coord))
Coords=CoordsType(points=self.calculate_points(region_contour, offset))
)
page.add_TextRegion(marginal)
if ocr_all_textlines_marginals_right:
@ -206,7 +199,7 @@ class EynollahXmlWriter:
for mm, region_contour in enumerate(found_polygons_drop_capitals):
dropcapital = TextRegionType(
id=counter.next_region_id, type_='drop-capital',
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, page_coord))
Coords=CoordsType(points=self.calculate_points(region_contour, offset))
)
page.add_TextRegion(dropcapital)
all_box_coord_drop = [[0, 0, 0, 0]]
@ -221,33 +214,17 @@ class EynollahXmlWriter:
for region_contour in found_polygons_text_region_img:
page.add_ImageRegion(
ImageRegionType(id=counter.next_region_id,
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, page_coord))))
Coords=CoordsType(points=self.calculate_points(region_contour, offset))))
for region_contour in polygons_seplines:
page.add_SeparatorRegion(
SeparatorRegionType(id=counter.next_region_id,
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, [0, 0, 0, 0]))))
Coords=CoordsType(points=self.calculate_points(region_contour, None))))
for region_contour in found_polygons_tables:
page.add_TableRegion(
TableRegionType(id=counter.next_region_id,
Coords=CoordsType(points=self.calculate_polygon_coords(region_contour, page_coord))))
Coords=CoordsType(points=self.calculate_points(region_contour, offset))))
return pcgts
def calculate_polygon_coords(self, contour, page_coord, skip_layout_reading_order=False):
self.logger.debug('enter calculate_polygon_coords')
coords = ''
for point in contour:
if len(point) != 2:
point = point[0]
point_x = point[0]
point_y = point[1]
if not skip_layout_reading_order:
point_x += page_coord[2]
point_y += page_coord[0]
point_x = int(point_x / self.scale_x)
point_y = int(point_y / self.scale_y)
coords += str(point_x) + ',' + str(point_y) + ' '
return coords[:-1]