qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-07-27 03:40:03 +02:00
Code Issues Projects Releases Wiki Activity

refactor namespace to eynollah

Browse source
This commit is contained in:
cneud 2024-02-23 20:18:38 +01:00
parent 6018b354aa
commit 21a47c081a
27 changed files with 14 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

0
eynollah/.gitkeep Normal file
View file

1
eynollah/__init__.py Normal file
View file

@ -0,0 +1 @@
__import__("pkg_resources").declare_namespace(__name__)

1
eynollah/eynollah/__init__.py Normal file
View file

@ -0,0 +1 @@

206
eynollah/eynollah/cli.py Normal file
View file

@ -0,0 +1,206 @@
import sys
import click
from ocrd_utils import initLogging, setOverrideLogLevel
from eynollah.eynollah.eynollah import Eynollah
@click.command()
@click.option(
"--image",
"-i",
help="image filename",
type=click.Path(exists=True, dir_okay=False),
)
@click.option(
"--out",
"-o",
help="directory to write output xml data",
type=click.Path(exists=True, file_okay=False),
required=True,
)
@click.option(
"--dir_in",
"-di",
help="directory of images",
type=click.Path(exists=True, file_okay=False),
)
@click.option(
"--model",
"-m",
help="directory of models",
type=click.Path(exists=True, file_okay=False),
required=True,
)
@click.option(
"--save_images",
"-si",
help="if a directory is given, images in documents will be cropped and saved there",
type=click.Path(exists=True, file_okay=False),
)
@click.option(
"--save_layout",
"-sl",
help="if a directory is given, plot of layout will be saved there",
type=click.Path(exists=True, file_okay=False),
)
@click.option(
"--save_deskewed",
"-sd",
help="if a directory is given, deskewed image will be saved there",
type=click.Path(exists=True, file_okay=False),
)
@click.option(
"--save_all",
"-sa",
help="if a directory is given, all plots needed for documentation will be saved there",
type=click.Path(exists=True, file_okay=False),
)
@click.option(
"--save_page",
"-sp",
help="if a directory is given, page crop of image will be saved there",
type=click.Path(exists=True, file_okay=False),
)
@click.option(
"--enable-plotting/--disable-plotting",
"-ep/-noep",
is_flag=True,
help="If set, will plot intermediary files and images",
)
@click.option(
"--allow-enhancement/--no-allow-enhancement",
"-ae/-noae",
is_flag=True,
help="if this parameter set to true, this tool would check that input image need resizing and enhancement or not. If so output of resized and enhanced image and corresponding layout data will be written in out directory",
)
@click.option(
"--curved-line/--no-curvedline",
"-cl/-nocl",
is_flag=True,
help="if this parameter set to true, this tool will try to return contoure of textlines instead of rectangle bounding box of textline. This should be taken into account that with this option the tool need more time to do process.",
)
@click.option(
"--textline_light/--no-textline_light",
"-tll/-notll",
is_flag=True,
help="if this parameter set to true, this tool will try to return contoure of textlines instead of rectangle bounding box of textline with a faster method.",
)
@click.option(
"--full-layout/--no-full-layout",
"-fl/-nofl",
is_flag=True,
help="if this parameter set to true, this tool will try to return all elements of layout.",
)
@click.option(
"--tables/--no-tables",
"-tab/-notab",
is_flag=True,
help="if this parameter set to true, this tool will try to detect tables.",
)
@click.option(
"--right2left/--left2right",
"-r2l/-l2r",
is_flag=True,
help="if this parameter set to true, this tool will extract right-to-left reading order.",
)
@click.option(
"--input_binary/--input-RGB",
"-ib/-irgb",
is_flag=True,
help="in general, eynollah uses RGB as input but if the input document is strongly dark, bright or for any other reason you can turn binarized input on. This option does not mean that you have to provide a binary image, otherwise this means that the tool itself will binarized the RGB input document.",
)
@click.option(
"--allow_scaling/--no-allow-scaling",
"-as/-noas",
is_flag=True,
help="if this parameter set to true, this tool would check the scale and if needed it will scale it to perform better layout detection",
)
@click.option(
"--headers_off/--headers-on",
"-ho/-noho",
is_flag=True,
help="if this parameter set to true, this tool would ignore headers role in reading order",
)
@click.option(
"--light_version/--original",
"-light/-org",
is_flag=True,
help="if this parameter set to true, this tool would use lighter version",
)
@click.option(
"--ignore_page_extraction/--extract_page_included",
"-ipe/-epi",
is_flag=True,
help="if this parameter set to true, this tool would ignore page extraction",
)
@click.option(
"--log-level",
"-l",
type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
help="Override log level globally to this",
)
def main(
image,
out,
dir_in,
model,
save_images,
save_layout,
save_deskewed,
save_all,
save_page,
enable_plotting,
allow_enhancement,
curved_line,
textline_light,
full_layout,
tables,
right2left,
input_binary,
allow_scaling,
headers_off,
light_version,
ignore_page_extraction,
log_level
):
if log_level:
setOverrideLogLevel(log_level)
initLogging()
if not enable_plotting and (save_layout or save_deskewed or save_all or save_page or save_images or allow_enhancement):
print("Error: You used one of -sl, -sd, -sa, -sp, -si or -ae but did not enable plotting with -ep")
sys.exit(1)
elif enable_plotting and not (save_layout or save_deskewed or save_all or save_page or save_images or allow_enhancement):
print("Error: You used -ep to enable plotting but set none of -sl, -sd, -sa, -sp, -si or -ae")
sys.exit(1)
if textline_light and not light_version:
print('Error: You used -tll to enable light textline detection but -light is not enabled')
sys.exit(1)
eynollah = Eynollah(
image_filename=image,
dir_out=out,
dir_in=dir_in,
dir_models=model,
dir_of_cropped_images=save_images,
dir_of_layout=save_layout,
dir_of_deskewed=save_deskewed,
dir_of_all=save_all,
dir_save_page=save_page,
enable_plotting=enable_plotting,
allow_enhancement=allow_enhancement,
curved_line=curved_line,
textline_light=textline_light,
full_layout=full_layout,
tables=tables,
right2left=right2left,
input_binary=input_binary,
allow_scaling=allow_scaling,
headers_off=headers_off,
light_version=light_version,
ignore_page_extraction=ignore_page_extraction,
)
eynollah.run()
#pcgts = eynollah.run()
##eynollah.writer.write_pagexml(pcgts)
if __name__ == "__main__":
main()

3107
eynollah/eynollah/eynollah.py Normal file
View file

File diff suppressed because it is too large Load diff

65
eynollah/eynollah/ocrd-tool.json Normal file
View file

@ -0,0 +1,65 @@
{
"version": "0.3.0",
"git_url": "https://github.com/qurator-spk/eynollah",
"tools": {
"ocrd-eynollah-segment": {
"executable": "ocrd-eynollah-segment",
"categories": ["Layout analysis"],
"description": "Segment page into regions and lines and do reading order detection with eynollah",
"input_file_grp": ["OCR-D-IMG", "OCR-D-SEG-PAGE", "OCR-D-GT-SEG-PAGE"],
"output_file_grp": ["OCR-D-SEG-LINE"],
"steps": ["layout/segmentation/region", "layout/segmentation/line"],
"parameters": {
"models": {
"type": "string",
"format": "file",
"content-type": "text/directory",
"cacheable": true,
"description": "Path to directory containing models to be used (See https://qurator-data.de/eynollah)",
"required": true
},
"dpi": {
"type": "number",
"format": "float",
"description": "pixel density in dots per inch (overrides any meta-data in the images); ignored if <= 0 (with fall-back 230)",
"default": 0
},
"full_layout": {
"type": "boolean",
"default": true,
"description": "Try to detect all element subtypes, including drop-caps and headings"
},
"tables": {
"type": "boolean",
"default": false,
"description": "Try to detect table regions"
},
"curved_line": {
"type": "boolean",
"default": false,
"description": "try to return contour of textlines instead of just rectangle bounding box. Needs more processing time"
},
"allow_scaling": {
"type": "boolean",
"default": false,
"description": "check the resolution against the number of detected columns and if needed, scale the image up or down during layout detection (heuristic to improve quality and performance)"
},
"headers_off": {
"type": "boolean",
"default": false,
"description": "ignore the special role of headings during reading order detection"
}
},
"resources": [
{
"description": "models for eynollah (TensorFlow format)",
"url": "https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz",
"name": "default",
"size": 1761991295,
"type": "archive",
"path_in_archive": "models_eynollah"
}
]
}
}
}

11
eynollah/eynollah/ocrd_cli.py Normal file
View file

@ -0,0 +1,11 @@
from .processor import EynollahProcessor
from click import command
from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
@command()
@ocrd_cli_options
def main(*args, **kwargs):
return ocrd_cli_wrap_processor(EynollahProcessor, *args, **kwargs)
if __name__ == '__main__':
main()

175
eynollah/eynollah/plot.py Normal file
View file

@ -0,0 +1,175 @@
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
import numpy as np
import os.path
import cv2
from scipy.ndimage import gaussian_filter1d
from .utils import crop_image_inside_box
from .utils.rotate import rotate_image_different
from .utils.resize import resize_image
class EynollahPlotter():
"""
Class collecting all the plotting and image writing methods
"""
def __init__(
self,
*,
dir_out,
dir_of_all,
dir_save_page,
dir_of_deskewed,
dir_of_layout,
dir_of_cropped_images,
image_filename_stem,
image_org=None,
scale_x=1,
scale_y=1,
):
self.dir_out = dir_out
self.dir_of_all = dir_of_all
self.dir_save_page = dir_save_page
self.dir_of_layout = dir_of_layout
self.dir_of_cropped_images = dir_of_cropped_images
self.dir_of_deskewed = dir_of_deskewed
self.image_filename_stem = image_filename_stem
# XXX TODO hacky these cannot be set at init time
self.image_org = image_org
self.scale_x = scale_x
self.scale_y = scale_y
def save_plot_of_layout_main(self, text_regions_p, image_page):
if self.dir_of_layout is not None:
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels=['Background' , 'Main text' , 'Image' , 'Separator','Marginalia']
values_indexes = [0, 1, 2, 3, 4]
plt.figure(figsize=(40, 40))
plt.rcParams["font.size"] = "40"
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=40)
plt.savefig(os.path.join(self.dir_of_layout, self.image_filename_stem + "_layout_main.png"))
def save_plot_of_layout_main_all(self, text_regions_p, image_page):
if self.dir_of_all is not None:
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels=['Background' , 'Main text' , 'Image' , 'Separator','Marginalia']
values_indexes = [0, 1, 2, 3, 4]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_layout_main_and_page.png"))
def save_plot_of_layout(self, text_regions_p, image_page):
if self.dir_of_layout is not None:
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels = ["Background", "Main text", "Header", "Marginalia", "Drop capital", "Image", "Separator", "Tables"]
values_indexes = [0, 1, 2, 8, 4, 5, 6, 10]
plt.figure(figsize=(40, 40))
plt.rcParams["font.size"] = "40"
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=40)
plt.savefig(os.path.join(self.dir_of_layout, self.image_filename_stem + "_layout.png"))
def save_plot_of_layout_all(self, text_regions_p, image_page):
if self.dir_of_all is not None:
values = np.unique(text_regions_p[:, :])
# pixels=['Background' , 'Main text' , 'Heading' , 'Marginalia' ,'Drop capitals' , 'Images' , 'Seperators' , 'Tables', 'Graphics']
pixels = ["Background", "Main text", "Header", "Marginalia", "Drop capital", "Image", "Separator", "Tables"]
values_indexes = [0, 1, 2, 8, 4, 5, 6, 10]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(text_regions_p[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_layout_and_page.png"))
def save_plot_of_textlines(self, textline_mask_tot_ea, image_page):
if self.dir_of_all is not None:
values = np.unique(textline_mask_tot_ea[:, :])
pixels = ["Background", "Textlines"]
values_indexes = [0, 1]
plt.figure(figsize=(80, 40))
plt.rcParams["font.size"] = "40"
plt.subplot(1, 2, 1)
plt.imshow(image_page)
plt.subplot(1, 2, 2)
im = plt.imshow(textline_mask_tot_ea[:, :])
colors = [im.cmap(im.norm(value)) for value in values]
patches = [mpatches.Patch(color=colors[np.where(values == i)[0][0]], label="{l}".format(l=pixels[int(np.where(values_indexes == i)[0][0])])) for i in values]
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.0, fontsize=60)
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem + "_textline_and_page.png"))
def save_deskewed_image(self, slope_deskew):
if self.dir_of_all is not None:
cv2.imwrite(os.path.join(self.dir_of_all, self.image_filename_stem + "_org.png"), self.image_org)
if self.dir_of_deskewed is not None:
img_rotated = rotate_image_different(self.image_org, slope_deskew)
cv2.imwrite(os.path.join(self.dir_of_deskewed, self.image_filename_stem + "_deskewed.png"), img_rotated)
def save_page_image(self, image_page):
if self.dir_of_all is not None:
cv2.imwrite(os.path.join(self.dir_of_all, self.image_filename_stem + "_page.png"), image_page)
if self.dir_save_page is not None:
cv2.imwrite(os.path.join(self.dir_save_page, self.image_filename_stem + "_page.png"), image_page)
def save_enhanced_image(self, img_res):
cv2.imwrite(os.path.join(self.dir_out, self.image_filename_stem + "_enhanced.png"), img_res)
def save_plot_of_textline_density(self, img_patch_org):
if self.dir_of_all is not None:
plt.figure(figsize=(80,40))
plt.rcParams['font.size']='50'
plt.subplot(1,2,1)
plt.imshow(img_patch_org)
plt.subplot(1,2,2)
plt.plot(gaussian_filter1d(img_patch_org.sum(axis=1), 3),np.array(range(len(gaussian_filter1d(img_patch_org.sum(axis=1), 3)))),linewidth=8)
plt.xlabel('Density of textline prediction in direction of X axis',fontsize=60)
plt.ylabel('Height',fontsize=60)
plt.yticks([0,len(gaussian_filter1d(img_patch_org.sum(axis=1), 3))])
plt.gca().invert_yaxis()
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem+'_density_of_textline.png'))
def save_plot_of_rotation_angle(self, angels, var_res):
if self.dir_of_all is not None:
plt.figure(figsize=(60,30))
plt.rcParams['font.size']='50'
plt.plot(angels,np.array(var_res),'-o',markersize=25,linewidth=4)
plt.xlabel('angle',fontsize=50)
plt.ylabel('variance of sum of rotated textline in direction of x axis',fontsize=50)
plt.plot(angels[np.argmax(var_res)],var_res[np.argmax(np.array(var_res))] ,'*',markersize=50,label='Angle of deskewing=' +str("{:.2f}".format(angels[np.argmax(var_res)]))+r'$\degree$')
plt.legend(loc='best')
plt.savefig(os.path.join(self.dir_of_all, self.image_filename_stem+'_rotation_angle.png'))
def write_images_into_directory(self, img_contours, image_page):
if self.dir_of_cropped_images is not None:
index = 0
for cont_ind in img_contours:
x, y, w, h = cv2.boundingRect(cont_ind)
box = [x, y, w, h]
croped_page, page_coord = crop_image_inside_box(box, image_page)
croped_page = resize_image(croped_page, int(croped_page.shape[0] / self.scale_y), int(croped_page.shape[1] / self.scale_x))
path = os.path.join(self.dir_of_cropped_images, self.image_filename_stem + "_" + str(index) + ".jpg")
cv2.imwrite(path, croped_page)
index += 1

68
eynollah/eynollah/processor.py Normal file
View file

@ -0,0 +1,68 @@
from json import loads
from pkg_resources import resource_string
from tempfile import NamedTemporaryFile
from pathlib import Path
from os.path import join
from PIL import Image
from ocrd import Processor
from ocrd_modelfactory import page_from_file, exif_from_filename
from ocrd_models import OcrdFile, OcrdExif
from ocrd_models.ocrd_page import to_xml
from ocrd_utils import (
getLogger,
MIMETYPE_PAGE,
assert_file_grp_cardinality,
make_file_id
)
from .eynollah import Eynollah
from .utils.pil_cv2 import pil2cv
OCRD_TOOL = loads(resource_string(__name__, 'ocrd-tool.json').decode('utf8'))
class EynollahProcessor(Processor):
def __init__(self, *args, **kwargs):
kwargs['ocrd_tool'] = OCRD_TOOL['tools']['ocrd-eynollah-segment']
kwargs['version'] = OCRD_TOOL['version']
super().__init__(*args, **kwargs)
def process(self):
LOG = getLogger('eynollah')
assert_file_grp_cardinality(self.input_file_grp, 1)
assert_file_grp_cardinality(self.output_file_grp, 1)
for n, input_file in enumerate(self.input_files):
page_id = input_file.pageId or input_file.ID
LOG.info("INPUT FILE %s (%d/%d) ", page_id, n + 1, len(self.input_files))
pcgts = page_from_file(self.workspace.download_file(input_file))
LOG.debug('width %s height %s', pcgts.get_Page().imageWidth, pcgts.get_Page().imageHeight)
self.add_metadata(pcgts)
page = pcgts.get_Page()
# XXX loses DPI information
# page_image, _, _ = self.workspace.image_from_page(page, page_id, feature_filter='binarized')
image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(url=page.imageFilename))).local_filename
eynollah_kwargs = {
'dir_models': self.resolve_resource(self.parameter['models']),
'allow_enhancement': False,
'curved_line': self.parameter['curved_line'],
'full_layout': self.parameter['full_layout'],
'allow_scaling': self.parameter['allow_scaling'],
'headers_off': self.parameter['headers_off'],
'tables': self.parameter['tables'],
'override_dpi': self.parameter['dpi'],
'logger': LOG,
'pcgts': pcgts,
'image_filename': image_filename
}
Eynollah(**eynollah_kwargs).run()
file_id = make_file_id(input_file, self.output_file_grp)
pcgts.set_pcGtsId(file_id)
self.workspace.add_file(
ID=file_id,
file_grp=self.output_file_grp,
pageId=page_id,
mimetype=MIMETYPE_PAGE,
local_filename=join(self.output_file_grp, file_id) + '.xml',
content=to_xml(pcgts))

2365
eynollah/eynollah/utils/__init__.py Normal file
View file

File diff suppressed because it is too large Load diff

370
eynollah/eynollah/utils/contour.py Normal file
View file

@ -0,0 +1,370 @@
import cv2
import numpy as np
from shapely import geometry
from .rotate import rotate_image, rotation_image_new
from multiprocessing import Process, Queue, cpu_count
from multiprocessing import Pool
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))
def find_contours_mean_y_diff(contours_main):
M_main = [cv2.moments(contours_main[j]) for j in range(len(contours_main))]
cy_main = [(M_main[j]["m01"] / (M_main[j]["m00"] + 1e-32)) for j in range(len(M_main))]
return np.mean(np.diff(np.sort(np.array(cy_main))))
def get_text_region_boxes_by_given_contours(contours):
kernel = np.ones((5, 5), np.uint8)
boxes = []
contours_new = []
for jj in range(len(contours)):
x, y, w, h = cv2.boundingRect(contours[jj])
boxes.append([x, y, w, h])
contours_new.append(contours[jj])
del contours
return boxes, contours_new
def filter_contours_area_of_image(image, contours, hierarchy, max_area, min_area):
found_polygons_early = list()
for jv,c in enumerate(contours):
if len(c) < 3: # A polygon cannot have less than 3 points
continue
polygon = geometry.Polygon([point[0] for point in c])
area = polygon.area
if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(image.shape[:2]) and hierarchy[0][jv][3] == -1: # and hierarchy[0][jv][3]==-1 :
found_polygons_early.append(np.array([[point] for point in polygon.exterior.coords], dtype=np.uint))
return found_polygons_early
def filter_contours_area_of_image_tables(image, contours, hierarchy, max_area, min_area):
found_polygons_early = list()
for jv,c in enumerate(contours):
if len(c) < 3: # A polygon cannot have less than 3 points
continue
polygon = geometry.Polygon([point[0] for point in c])
# area = cv2.contourArea(c)
area = polygon.area
##print(np.prod(thresh.shape[:2]))
# Check that polygon has area greater than minimal area
# print(hierarchy[0][jv][3],hierarchy )
if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(image.shape[:2]): # and hierarchy[0][jv][3]==-1 :
# print(c[0][0][1])
found_polygons_early.append(np.array([[point] for point in polygon.exterior.coords], dtype=np.int32))
return found_polygons_early
def find_new_features_of_contours(contours_main):
areas_main = np.array([cv2.contourArea(contours_main[j]) for j in range(len(contours_main))])
M_main = [cv2.moments(contours_main[j]) for j in range(len(contours_main))]
cx_main = [(M_main[j]["m10"] / (M_main[j]["m00"] + 1e-32)) for j in range(len(M_main))]
cy_main = [(M_main[j]["m01"] / (M_main[j]["m00"] + 1e-32)) for j in range(len(M_main))]
try:
x_min_main = np.array([np.min(contours_main[j][:, 0, 0]) for j in range(len(contours_main))])
argmin_x_main = np.array([np.argmin(contours_main[j][:, 0, 0]) for j in range(len(contours_main))])
x_min_from_argmin = np.array([contours_main[j][argmin_x_main[j], 0, 0] for j in range(len(contours_main))])
y_corr_x_min_from_argmin = np.array([contours_main[j][argmin_x_main[j], 0, 1] for j in range(len(contours_main))])
x_max_main = np.array([np.max(contours_main[j][:, 0, 0]) for j in range(len(contours_main))])
y_min_main = np.array([np.min(contours_main[j][:, 0, 1]) for j in range(len(contours_main))])
y_max_main = np.array([np.max(contours_main[j][:, 0, 1]) for j in range(len(contours_main))])
except:
x_min_main = np.array([np.min(contours_main[j][:, 0]) for j in range(len(contours_main))])
argmin_x_main = np.array([np.argmin(contours_main[j][:, 0]) for j in range(len(contours_main))])
x_min_from_argmin = np.array([contours_main[j][argmin_x_main[j], 0] for j in range(len(contours_main))])
y_corr_x_min_from_argmin = np.array([contours_main[j][argmin_x_main[j], 1] for j in range(len(contours_main))])
x_max_main = np.array([np.max(contours_main[j][:, 0]) for j in range(len(contours_main))])
y_min_main = np.array([np.min(contours_main[j][:, 1]) for j in range(len(contours_main))])
y_max_main = np.array([np.max(contours_main[j][:, 1]) for j in range(len(contours_main))])
# dis_x=np.abs(x_max_main-x_min_main)
return cx_main, cy_main, x_min_main, x_max_main, y_min_main, y_max_main, y_corr_x_min_from_argmin
def find_features_of_contours(contours_main):
areas_main=np.array([cv2.contourArea(contours_main[j]) for j in range(len(contours_main))])
M_main=[cv2.moments(contours_main[j]) for j in range(len(contours_main))]
cx_main=[(M_main[j]['m10']/(M_main[j]['m00']+1e-32)) for j in range(len(M_main))]
cy_main=[(M_main[j]['m01']/(M_main[j]['m00']+1e-32)) for j in range(len(M_main))]
x_min_main=np.array([np.min(contours_main[j][:,0,0]) for j in range(len(contours_main))])
x_max_main=np.array([np.max(contours_main[j][:,0,0]) for j in range(len(contours_main))])
y_min_main=np.array([np.min(contours_main[j][:,0,1]) for j in range(len(contours_main))])
y_max_main=np.array([np.max(contours_main[j][:,0,1]) for j in range(len(contours_main))])
return y_min_main, y_max_main
def return_parent_contours(contours, hierarchy):
contours_parent = [contours[i] for i in range(len(contours)) if hierarchy[0][i][3] == -1]
return contours_parent
def return_contours_of_interested_region(region_pre_p, pixel, min_area=0.0002):
# pixels of images are identified by 5
if len(region_pre_p.shape) == 3:
cnts_images = (region_pre_p[:, :, 0] == pixel) * 1
else:
cnts_images = (region_pre_p[:, :] == pixel) * 1
cnts_images = cnts_images.astype(np.uint8)
cnts_images = np.repeat(cnts_images[:, :, np.newaxis], 3, axis=2)
imgray = cv2.cvtColor(cnts_images, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_imgs, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_imgs = return_parent_contours(contours_imgs, hierarchy)
contours_imgs = filter_contours_area_of_image_tables(thresh, contours_imgs, hierarchy, max_area=1, min_area=min_area)
return contours_imgs
def do_work_of_contours_in_image(queue_of_all_params, contours_per_process, indexes_r_con_per_pro, img, slope_first):
cnts_org_per_each_subprocess = []
index_by_text_region_contours = []
for mv in range(len(contours_per_process)):
index_by_text_region_contours.append(indexes_r_con_per_pro[mv])
img_copy = np.zeros(img.shape)
img_copy = cv2.fillPoly(img_copy, pts=[contours_per_process[mv]], color=(1, 1, 1))
img_copy = rotation_image_new(img_copy, -slope_first)
img_copy = img_copy.astype(np.uint8)
imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1])
cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0])
cnts_org_per_each_subprocess.append(cont_int[0])
queue_of_all_params.put([ cnts_org_per_each_subprocess, index_by_text_region_contours])
def get_textregion_contours_in_org_image_multi(cnts, img, slope_first):
num_cores = cpu_count()
queue_of_all_params = Queue()
processes = []
nh = np.linspace(0, len(cnts), num_cores + 1)
indexes_by_text_con = np.array(range(len(cnts)))
for i in range(num_cores):
contours_per_process = cnts[int(nh[i]) : int(nh[i + 1])]
indexes_text_con_per_process = indexes_by_text_con[int(nh[i]) : int(nh[i + 1])]
processes.append(Process(target=do_work_of_contours_in_image, args=(queue_of_all_params, contours_per_process, indexes_text_con_per_process, img,slope_first )))
for i in range(num_cores):
processes[i].start()
cnts_org = []
all_index_text_con = []
for i in range(num_cores):
list_all_par = queue_of_all_params.get(True)
contours_for_sub_process = list_all_par[0]
indexes_for_sub_process = list_all_par[1]
for j in range(len(contours_for_sub_process)):
cnts_org.append(contours_for_sub_process[j])
all_index_text_con.append(indexes_for_sub_process[j])
for i in range(num_cores):
processes[i].join()
print(all_index_text_con)
return cnts_org
def loop_contour_image(index_l, cnts,img, slope_first):
img_copy = np.zeros(img.shape)
img_copy = cv2.fillPoly(img_copy, pts=[cnts[index_l]], color=(1, 1, 1))
# plt.imshow(img_copy)
# plt.show()
# print(img.shape,'img')
img_copy = rotation_image_new(img_copy, -slope_first)
##print(img_copy.shape,'img_copy')
# plt.imshow(img_copy)
# plt.show()
img_copy = img_copy.astype(np.uint8)
imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1])
cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0])
# print(np.shape(cont_int[0]))
return cont_int[0]
def get_textregion_contours_in_org_image_multi2(cnts, img, slope_first):
cnts_org = []
# print(cnts,'cnts')
with Pool(cpu_count()) as p:
cnts_org = p.starmap(loop_contour_image, [(index_l,cnts, img,slope_first) for index_l in range(len(cnts))])
return cnts_org
def get_textregion_contours_in_org_image(cnts, img, slope_first):
cnts_org = []
# print(cnts,'cnts')
for i in range(len(cnts)):
img_copy = np.zeros(img.shape)
img_copy = cv2.fillPoly(img_copy, pts=[cnts[i]], color=(1, 1, 1))
# plt.imshow(img_copy)
# plt.show()
# print(img.shape,'img')
img_copy = rotation_image_new(img_copy, -slope_first)
##print(img_copy.shape,'img_copy')
# plt.imshow(img_copy)
# plt.show()
img_copy = img_copy.astype(np.uint8)
imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1])
cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0])
# print(np.shape(cont_int[0]))
cnts_org.append(cont_int[0])
return cnts_org
def get_textregion_contours_in_org_image_light(cnts, img, slope_first):
h_o = img.shape[0]
w_o = img.shape[1]
img = cv2.resize(img, (int(img.shape[1]/3.), int(img.shape[0]/3.)), interpolation=cv2.INTER_NEAREST)
##cnts = list( (np.array(cnts)/2).astype(np.int16) )
#cnts = cnts/2
cnts = [(i/ 3).astype(np.int32) for i in cnts]
cnts_org = []
#print(cnts,'cnts')
for i in range(len(cnts)):
img_copy = np.zeros(img.shape)
img_copy = cv2.fillPoly(img_copy, pts=[cnts[i]], color=(1, 1, 1))
# plt.imshow(img_copy)
# plt.show()
# print(img.shape,'img')
img_copy = rotation_image_new(img_copy, -slope_first)
##print(img_copy.shape,'img_copy')
# plt.imshow(img_copy)
# plt.show()
img_copy = img_copy.astype(np.uint8)
imgray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
cont_int, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cont_int[0][:, 0, 0] = cont_int[0][:, 0, 0] + np.abs(img_copy.shape[1] - img.shape[1])
cont_int[0][:, 0, 1] = cont_int[0][:, 0, 1] + np.abs(img_copy.shape[0] - img.shape[0])
# print(np.shape(cont_int[0]))
cnts_org.append(cont_int[0]*3)
return cnts_org
def return_contours_of_interested_textline(region_pre_p, pixel):
# pixels of images are identified by 5
if len(region_pre_p.shape) == 3:
cnts_images = (region_pre_p[:, :, 0] == pixel) * 1
else:
cnts_images = (region_pre_p[:, :] == pixel) * 1
cnts_images = cnts_images.astype(np.uint8)
cnts_images = np.repeat(cnts_images[:, :, np.newaxis], 3, axis=2)
imgray = cv2.cvtColor(cnts_images, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_imgs, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_imgs = return_parent_contours(contours_imgs, hierarchy)
contours_imgs = filter_contours_area_of_image_tables(thresh, contours_imgs, hierarchy, max_area=1, min_area=0.000000003)
return contours_imgs
def return_contours_of_image(image):
if len(image.shape) == 2:
image = np.repeat(image[:, :, np.newaxis], 3, axis=2)
image = image.astype(np.uint8)
else:
image = image.astype(np.uint8)
imgray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
return contours, hierarchy
def return_contours_of_interested_region_by_min_size(region_pre_p, pixel, min_size=0.00003):
# pixels of images are identified by 5
if len(region_pre_p.shape) == 3:
cnts_images = (region_pre_p[:, :, 0] == pixel) * 1
else:
cnts_images = (region_pre_p[:, :] == pixel) * 1
cnts_images = cnts_images.astype(np.uint8)
cnts_images = np.repeat(cnts_images[:, :, np.newaxis], 3, axis=2)
imgray = cv2.cvtColor(cnts_images, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_imgs, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_imgs = return_parent_contours(contours_imgs, hierarchy)
contours_imgs = filter_contours_area_of_image_tables(thresh, contours_imgs, hierarchy, max_area=1, min_area=min_size)
return contours_imgs
def return_contours_of_interested_region_by_size(region_pre_p, pixel, min_area, max_area):
# pixels of images are identified by 5
if len(region_pre_p.shape) == 3:
cnts_images = (region_pre_p[:, :, 0] == pixel) * 1
else:
cnts_images = (region_pre_p[:, :] == pixel) * 1
cnts_images = cnts_images.astype(np.uint8)
cnts_images = np.repeat(cnts_images[:, :, np.newaxis], 3, axis=2)
imgray = cv2.cvtColor(cnts_images, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_imgs, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_imgs = return_parent_contours(contours_imgs, hierarchy)
contours_imgs = filter_contours_area_of_image_tables(thresh, contours_imgs, hierarchy, max_area=max_area, min_area=min_area)
img_ret = np.zeros((region_pre_p.shape[0], region_pre_p.shape[1], 3))
img_ret = cv2.fillPoly(img_ret, pts=contours_imgs, color=(1, 1, 1))
return img_ret[:, :, 0]

48
eynollah/eynollah/utils/counter.py Normal file
View file

@ -0,0 +1,48 @@
from collections import Counter
REGION_ID_TEMPLATE = 'region_%04d'
LINE_ID_TEMPLATE = 'region_%04d_line_%04d'
class EynollahIdCounter():
def __init__(self, region_idx=0, line_idx=0):
self._counter = Counter()
self._initial_region_idx = region_idx
self._initial_line_idx = line_idx
self.reset()
def reset(self):
self.set('region', self._initial_region_idx)
self.set('line', self._initial_line_idx)
def inc(self, name, val=1):
self._counter.update({name: val})
def get(self, name):
return self._counter[name]
def set(self, name, val):
self._counter[name] = val
def region_id(self, region_idx=None):
if region_idx is None:
region_idx = self._counter['region']
return REGION_ID_TEMPLATE % region_idx
def line_id(self, region_idx=None, line_idx=None):
if region_idx is None:
region_idx = self._counter['region']
if line_idx is None:
line_idx = self._counter['line']
return LINE_ID_TEMPLATE % (region_idx, line_idx)
@property
def next_region_id(self):
self.inc('region')
self.set('line', 0)
return self.region_id()
@property
def next_line_id(self):
self.inc('line')
return self.line_id()

502
eynollah/eynollah/utils/drop_capitals.py Normal file
View file

@ -0,0 +1,502 @@
import numpy as np
import cv2
from .contour import (
find_new_features_of_contours,
return_contours_of_image,
return_parent_contours,
)
def adhere_drop_capital_region_into_corresponding_textline(
text_regions_p,
polygons_of_drop_capitals,
contours_only_text_parent,
contours_only_text_parent_h,
all_box_coord,
all_box_coord_h,
all_found_textline_polygons,
all_found_textline_polygons_h,
kernel=None,
curved_line=False,
):
# print(np.shape(all_found_textline_polygons),np.shape(all_found_textline_polygons[3]),'all_found_textline_polygonsshape')
# print(all_found_textline_polygons[3])
cx_m, cy_m, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent)
cx_h, cy_h, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent_h)
cx_d, cy_d, _, _, y_min_d, y_max_d, _ = find_new_features_of_contours(polygons_of_drop_capitals)
img_con_all = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
for j_cont in range(len(contours_only_text_parent)):
img_con_all[all_box_coord[j_cont][0] : all_box_coord[j_cont][1], all_box_coord[j_cont][2] : all_box_coord[j_cont][3], 0] = (j_cont + 1) * 3
# img_con_all=cv2.fillPoly(img_con_all,pts=[contours_only_text_parent[j_cont]],color=((j_cont+1)*3,(j_cont+1)*3,(j_cont+1)*3))
# plt.imshow(img_con_all[:,:,0])
# plt.show()
# img_con_all=cv2.dilate(img_con_all, kernel, iterations=3)
# plt.imshow(img_con_all[:,:,0])
# plt.show()
# print(np.unique(img_con_all[:,:,0]))
for i_drop in range(len(polygons_of_drop_capitals)):
# print(i_drop,'i_drop')
img_con_all_copy = np.copy(img_con_all)
img_con = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_con = cv2.fillPoly(img_con, pts=[polygons_of_drop_capitals[i_drop]], color=(1, 1, 1))
# plt.imshow(img_con[:,:,0])
# plt.show()
##img_con=cv2.dilate(img_con, kernel, iterations=30)
# plt.imshow(img_con[:,:,0])
# plt.show()
# print(np.unique(img_con[:,:,0]))
img_con_all_copy[:, :, 0] = img_con_all_copy[:, :, 0] + img_con[:, :, 0]
img_con_all_copy[:, :, 0][img_con_all_copy[:, :, 0] == 1] = 0
kherej_ghesmat = np.unique(img_con_all_copy[:, :, 0]) / 3
res_summed_pixels = np.unique(img_con_all_copy[:, :, 0]) % 3
region_with_intersected_drop = kherej_ghesmat[res_summed_pixels == 1]
# region_with_intersected_drop=region_with_intersected_drop/3
region_with_intersected_drop = region_with_intersected_drop.astype(np.uint8)
# print(len(region_with_intersected_drop),'region_with_intersected_drop1')
if len(region_with_intersected_drop) == 0:
img_con_all_copy = np.copy(img_con_all)
img_con = cv2.dilate(img_con, kernel, iterations=4)
img_con_all_copy[:, :, 0] = img_con_all_copy[:, :, 0] + img_con[:, :, 0]
img_con_all_copy[:, :, 0][img_con_all_copy[:, :, 0] == 1] = 0
kherej_ghesmat = np.unique(img_con_all_copy[:, :, 0]) / 3
res_summed_pixels = np.unique(img_con_all_copy[:, :, 0]) % 3
region_with_intersected_drop = kherej_ghesmat[res_summed_pixels == 1]
# region_with_intersected_drop=region_with_intersected_drop/3
region_with_intersected_drop = region_with_intersected_drop.astype(np.uint8)
# print(np.unique(img_con_all_copy[:,:,0]))
if curved_line:
if len(region_with_intersected_drop) > 1:
sum_pixels_of_intersection = []
for i in range(len(region_with_intersected_drop)):
# print((region_with_intersected_drop[i]*3+1))
sum_pixels_of_intersection.append(((img_con_all_copy[:, :, 0] == (region_with_intersected_drop[i] * 3 + 1)) * 1).sum())
# print(sum_pixels_of_intersection)
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = np.array(cy_t) # all_box_coord[int(region_final)][0]+np.array(cy_t)
# print(y_lines)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_textline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_textline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_textline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
contours_biggest = contours_combined[np.argmax(areas_cnt_text)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
# contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
# contours_biggest[:,0,1]=contours_biggest[:,0,1]#-all_box_coord[int(region_final)][0]
# contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
except:
# print('gordun1')
pass
elif len(region_with_intersected_drop) == 1:
region_final = region_with_intersected_drop[0] - 1
# areas_main=np.array([cv2.contourArea(all_found_textline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_textline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = np.array(cy_t) # all_box_coord[int(region_final)][0]+np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_textline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_textline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_textline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
# plt.imshow(img_textlines)
# plt.show()
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
contours_biggest = contours_combined[np.argmax(areas_cnt_text)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
# contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
# contours_biggest[:,0,1]=contours_biggest[:,0,1]#-all_box_coord[int(region_final)][0]
# print(np.shape(contours_biggest),'contours_biggest')
# print(np.shape(all_found_textline_polygons[int(region_final)][arg_min]))
##contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
except:
pass
try:
# print(all_found_textline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_textline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0, 0] = all_found_textline_polygons[int(region_final)][arg_min][:, 0, 0] # +all_box_coord[int(region_final)][2]
cnt_nearest[:, 0, 1] = all_found_textline_polygons[int(region_final)][arg_min][:, 0, 1] # +all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
contours_biggest = contours_combined[np.argmax(areas_cnt_text)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] # -all_box_coord[int(region_final)][2]
contours_biggest[:, 0, 1] = contours_biggest[:, 0, 1] # -all_box_coord[int(region_final)][0]
##contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
# all_found_textline_polygons[int(region_final)][arg_min]=contours_biggest
except:
pass
else:
pass
##cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
###print(all_box_coord[j_cont])
###print(cx_t)
###print(cy_t)
###print(cx_d[i_drop])
###print(cy_d[i_drop])
##y_lines=all_box_coord[int(region_final)][0]+np.array(cy_t)
##y_lines[y_lines<y_min_d[i_drop]]=0
###print(y_lines)
##arg_min=np.argmin(np.abs(y_lines-y_min_d[i_drop]) )
###print(arg_min)
##cnt_nearest=np.copy(all_found_textline_polygons[int(region_final)][arg_min])
##cnt_nearest[:,0,0]=all_found_textline_polygons[int(region_final)][arg_min][:,0,0]#+all_box_coord[int(region_final)][2]
##cnt_nearest[:,0,1]=all_found_textline_polygons[int(region_final)][arg_min][:,0,1]#+all_box_coord[int(region_final)][0]
##img_textlines=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
##img_textlines=cv2.fillPoly(img_textlines,pts=[cnt_nearest],color=(255,255,255))
##img_textlines=cv2.fillPoly(img_textlines,pts=[polygons_of_drop_capitals[i_drop] ],color=(255,255,255))
##img_textlines=img_textlines.astype(np.uint8)
##plt.imshow(img_textlines)
##plt.show()
##imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
##ret, thresh = cv2.threshold(imgray, 0, 255, 0)
##contours_combined,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
##print(len(contours_combined),'len textlines mixed')
##areas_cnt_text=np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
##contours_biggest=contours_combined[np.argmax(areas_cnt_text)]
###print(np.shape(contours_biggest))
###print(contours_biggest[:])
##contours_biggest[:,0,0]=contours_biggest[:,0,0]#-all_box_coord[int(region_final)][2]
##contours_biggest[:,0,1]=contours_biggest[:,0,1]#-all_box_coord[int(region_final)][0]
##contours_biggest=contours_biggest.reshape(np.shape(contours_biggest)[0],np.shape(contours_biggest)[2])
##all_found_textline_polygons[int(region_final)][arg_min]=contours_biggest
else:
if len(region_with_intersected_drop) > 1:
sum_pixels_of_intersection = []
for i in range(len(region_with_intersected_drop)):
# print((region_with_intersected_drop[i]*3+1))
sum_pixels_of_intersection.append(((img_con_all_copy[:, :, 0] == (region_with_intersected_drop[i] * 3 + 1)) * 1).sum())
# print(sum_pixels_of_intersection)
region_final = region_with_intersected_drop[np.argmax(sum_pixels_of_intersection)] - 1
# print(region_final,'region_final')
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
try:
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
# print(y_lines)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_textline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0] = all_found_textline_polygons[int(region_final)][arg_min][:, 0] + all_box_coord[int(region_final)][2]
cnt_nearest[:, 1] = all_found_textline_polygons[int(region_final)][arg_min][:, 1] + all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
contours_biggest = contours_combined[np.argmax(areas_cnt_text)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] - all_box_coord[int(region_final)][2]
contours_biggest[:, 0, 1] = contours_biggest[:, 0, 1] - all_box_coord[int(region_final)][0]
contours_biggest = contours_biggest.reshape(np.shape(contours_biggest)[0], np.shape(contours_biggest)[2])
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
except:
# print('gordun1')
pass
elif len(region_with_intersected_drop) == 1:
region_final = region_with_intersected_drop[0] - 1
# areas_main=np.array([cv2.contourArea(all_found_textline_polygons[int(region_final)][0][j] ) for j in range(len(all_found_textline_polygons[int(region_final)]))])
# cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
# print(cx_t,'print')
try:
# print(all_found_textline_polygons[j_cont][0])
cx_t, cy_t, _, _, _, _, _ = find_new_features_of_contours(all_found_textline_polygons[int(region_final)])
# print(all_box_coord[j_cont])
# print(cx_t)
# print(cy_t)
# print(cx_d[i_drop])
# print(cy_d[i_drop])
y_lines = all_box_coord[int(region_final)][0] + np.array(cy_t)
y_lines[y_lines < y_min_d[i_drop]] = 0
# print(y_lines)
arg_min = np.argmin(np.abs(y_lines - y_min_d[i_drop]))
# print(arg_min)
cnt_nearest = np.copy(all_found_textline_polygons[int(region_final)][arg_min])
cnt_nearest[:, 0] = all_found_textline_polygons[int(region_final)][arg_min][:, 0] + all_box_coord[int(region_final)][2]
cnt_nearest[:, 1] = all_found_textline_polygons[int(region_final)][arg_min][:, 1] + all_box_coord[int(region_final)][0]
img_textlines = np.zeros((text_regions_p.shape[0], text_regions_p.shape[1], 3))
img_textlines = cv2.fillPoly(img_textlines, pts=[cnt_nearest], color=(255, 255, 255))
img_textlines = cv2.fillPoly(img_textlines, pts=[polygons_of_drop_capitals[i_drop]], color=(255, 255, 255))
img_textlines = img_textlines.astype(np.uint8)
imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 0, 255, 0)
contours_combined, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# print(len(contours_combined),'len textlines mixed')
areas_cnt_text = np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
contours_biggest = contours_combined[np.argmax(areas_cnt_text)]
# print(np.shape(contours_biggest))
# print(contours_biggest[:])
contours_biggest[:, 0, 0] = contours_biggest[:, 0, 0] - all_box_coord[int(region_final)][2]
contours_biggest[:, 0, 1] = contours_biggest[:, 0, 1] - all_box_coord[int(region_final)][0]
contours_biggest = contours_biggest.reshape(np.shape(contours_biggest)[0], np.shape(contours_biggest)[2])
all_found_textline_polygons[int(region_final)][arg_min] = contours_biggest
# all_found_textline_polygons[int(region_final)][arg_min]=contours_biggest
except:
pass
else:
pass
#####for i_drop in range(len(polygons_of_drop_capitals)):
#####for j_cont in range(len(contours_only_text_parent)):
#####img_con=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
#####img_con=cv2.fillPoly(img_con,pts=[polygons_of_drop_capitals[i_drop] ],color=(255,255,255))
#####img_con=cv2.fillPoly(img_con,pts=[contours_only_text_parent[j_cont]],color=(255,255,255))
#####img_con=img_con.astype(np.uint8)
######imgray = cv2.cvtColor(img_con, cv2.COLOR_BGR2GRAY)
######ret, thresh = cv2.threshold(imgray, 0, 255, 0)
######contours_new,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
#####contours_new,hir_new=return_contours_of_image(img_con)
#####contours_new_parent=return_parent_contours( contours_new,hir_new)
######plt.imshow(img_con)
######plt.show()
#####try:
#####if len(contours_new_parent)==1:
######print(all_found_textline_polygons[j_cont][0])
#####cx_t,cy_t ,_, _, _ ,_,_= find_new_features_of_contours(all_found_textline_polygons[j_cont])
######print(all_box_coord[j_cont])
######print(cx_t)
######print(cy_t)
######print(cx_d[i_drop])
######print(cy_d[i_drop])
#####y_lines=all_box_coord[j_cont][0]+np.array(cy_t)
######print(y_lines)
#####arg_min=np.argmin(np.abs(y_lines-y_min_d[i_drop]) )
######print(arg_min)
#####cnt_nearest=np.copy(all_found_textline_polygons[j_cont][arg_min])
#####cnt_nearest[:,0]=all_found_textline_polygons[j_cont][arg_min][:,0]+all_box_coord[j_cont][2]
#####cnt_nearest[:,1]=all_found_textline_polygons[j_cont][arg_min][:,1]+all_box_coord[j_cont][0]
#####img_textlines=np.zeros((text_regions_p.shape[0],text_regions_p.shape[1],3))
#####img_textlines=cv2.fillPoly(img_textlines,pts=[cnt_nearest],color=(255,255,255))
#####img_textlines=cv2.fillPoly(img_textlines,pts=[polygons_of_drop_capitals[i_drop] ],color=(255,255,255))
#####img_textlines=img_textlines.astype(np.uint8)
#####imgray = cv2.cvtColor(img_textlines, cv2.COLOR_BGR2GRAY)
#####ret, thresh = cv2.threshold(imgray, 0, 255, 0)
#####contours_combined,hierarchy=cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
#####areas_cnt_text=np.array([cv2.contourArea(contours_combined[j]) for j in range(len(contours_combined))])
#####contours_biggest=contours_combined[np.argmax(areas_cnt_text)]
######print(np.shape(contours_biggest))
######print(contours_biggest[:])
#####contours_biggest[:,0,0]=contours_biggest[:,0,0]-all_box_coord[j_cont][2]
#####contours_biggest[:,0,1]=contours_biggest[:,0,1]-all_box_coord[j_cont][0]
#####all_found_textline_polygons[j_cont][arg_min]=contours_biggest
######print(contours_biggest)
######plt.imshow(img_textlines[:,:,0])
######plt.show()
#####else:
#####pass
#####except:
#####pass
return all_found_textline_polygons
def filter_small_drop_capitals_from_no_patch_layout(layout_no_patch, layout1):
drop_only = (layout_no_patch[:, :, 0] == 4) * 1
contours_drop, hir_on_drop = return_contours_of_image(drop_only)
contours_drop_parent = return_parent_contours(contours_drop, hir_on_drop)
areas_cnt_text = np.array([cv2.contourArea(contours_drop_parent[j]) for j in range(len(contours_drop_parent))])
areas_cnt_text = areas_cnt_text / float(drop_only.shape[0] * drop_only.shape[1])
contours_drop_parent = [contours_drop_parent[jz] for jz in range(len(contours_drop_parent)) if areas_cnt_text[jz] > 0.001]
areas_cnt_text = [areas_cnt_text[jz] for jz in range(len(areas_cnt_text)) if areas_cnt_text[jz] > 0.001]
contours_drop_parent_final = []
for jj in range(len(contours_drop_parent)):
x, y, w, h = cv2.boundingRect(contours_drop_parent[jj])
# boxes.append([int(x), int(y), int(w), int(h)])
iou_of_box_and_contoure = float(drop_only.shape[0] * drop_only.shape[1]) * areas_cnt_text[jj] / float(w * h) * 100
height_to_weight_ratio = h / float(w)
weigh_to_height_ratio = w / float(h)
if iou_of_box_and_contoure > 60 and weigh_to_height_ratio < 1.2 and height_to_weight_ratio < 2:
map_of_drop_contour_bb = np.zeros((layout1.shape[0], layout1.shape[1]))
map_of_drop_contour_bb[y : y + h, x : x + w] = layout1[y : y + h, x : x + w]
if (((map_of_drop_contour_bb == 1) * 1).sum() / float(((map_of_drop_contour_bb == 5) * 1).sum()) * 100) >= 15:
contours_drop_parent_final.append(contours_drop_parent[jj])
layout_no_patch[:, :, 0][layout_no_patch[:, :, 0] == 4] = 0
layout_no_patch = cv2.fillPoly(layout_no_patch, pts=contours_drop_parent_final, color=(4, 4, 4))
return layout_no_patch

3
eynollah/eynollah/utils/is_nan.py Normal file
View file

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

252
eynollah/eynollah/utils/marginals.py Normal file
View file

@ -0,0 +1,252 @@
import numpy as np
import cv2
from scipy.signal import find_peaks
from scipy.ndimage import gaussian_filter1d
from .contour import find_new_features_of_contours, return_contours_of_interested_region
from .resize import resize_image
from .rotate import rotate_image
def get_marginals(text_with_lines, text_regions, num_col, slope_deskew, kernel=None):
mask_marginals=np.zeros((text_with_lines.shape[0],text_with_lines.shape[1]))
mask_marginals=mask_marginals.astype(np.uint8)
text_with_lines=text_with_lines.astype(np.uint8)
##text_with_lines=cv2.erode(text_with_lines,self.kernel,iterations=3)
text_with_lines_eroded=cv2.erode(text_with_lines,kernel,iterations=5)
if text_with_lines.shape[0]<=1500:
pass
elif text_with_lines.shape[0]>1500 and text_with_lines.shape[0]<=1800:
text_with_lines=resize_image(text_with_lines,int(text_with_lines.shape[0]*1.5),text_with_lines.shape[1])
text_with_lines=cv2.erode(text_with_lines,kernel,iterations=5)
text_with_lines=resize_image(text_with_lines,text_with_lines_eroded.shape[0],text_with_lines_eroded.shape[1])
else:
text_with_lines=resize_image(text_with_lines,int(text_with_lines.shape[0]*1.8),text_with_lines.shape[1])
text_with_lines=cv2.erode(text_with_lines,kernel,iterations=7)
text_with_lines=resize_image(text_with_lines,text_with_lines_eroded.shape[0],text_with_lines_eroded.shape[1])
text_with_lines_y=text_with_lines.sum(axis=0)
text_with_lines_y_eroded=text_with_lines_eroded.sum(axis=0)
thickness_along_y_percent=text_with_lines_y_eroded.max()/(float(text_with_lines.shape[0]))*100
#print(thickness_along_y_percent,'thickness_along_y_percent')
if thickness_along_y_percent<30:
min_textline_thickness=8
elif thickness_along_y_percent>=30 and thickness_along_y_percent<50:
min_textline_thickness=20
else:
min_textline_thickness=40
if thickness_along_y_percent>=14:
text_with_lines_y_rev=-1*text_with_lines_y[:]
#print(text_with_lines_y)
#print(text_with_lines_y_rev)
#plt.plot(text_with_lines_y)
#plt.show()
text_with_lines_y_rev=text_with_lines_y_rev-np.min(text_with_lines_y_rev)
#plt.plot(text_with_lines_y_rev)
#plt.show()
sigma_gaus=1
region_sum_0= gaussian_filter1d(text_with_lines_y, sigma_gaus)
region_sum_0_rev=gaussian_filter1d(text_with_lines_y_rev, sigma_gaus)
#plt.plot(region_sum_0_rev)
#plt.show()
region_sum_0_updown=region_sum_0[len(region_sum_0)::-1]
first_nonzero=(next((i for i, x in enumerate(region_sum_0) if x), None))
last_nonzero=(next((i for i, x in enumerate(region_sum_0_updown) if x), None))
last_nonzero=len(region_sum_0)-last_nonzero
##img_sum_0_smooth_rev=-region_sum_0
mid_point=(last_nonzero+first_nonzero)/2.
one_third_right=(last_nonzero-mid_point)/3.0
one_third_left=(mid_point-first_nonzero)/3.0
#img_sum_0_smooth_rev=img_sum_0_smooth_rev-np.min(img_sum_0_smooth_rev)
peaks, _ = find_peaks(text_with_lines_y_rev, height=0)
peaks=np.array(peaks)
#print(region_sum_0[peaks])
##plt.plot(region_sum_0)
##plt.plot(peaks,region_sum_0[peaks],'*')
##plt.show()
#print(first_nonzero,last_nonzero,peaks)
peaks=peaks[(peaks>first_nonzero) & ((peaks<last_nonzero))]
#print(first_nonzero,last_nonzero,peaks)
#print(region_sum_0[peaks]<10)
####peaks=peaks[region_sum_0[peaks]<25 ]
#print(region_sum_0[peaks])
peaks=peaks[region_sum_0[peaks]<min_textline_thickness ]
#print(peaks)
#print(first_nonzero,last_nonzero,one_third_right,one_third_left)
if num_col==1:
peaks_right=peaks[peaks>mid_point]
peaks_left=peaks[peaks<mid_point]
if num_col==2:
peaks_right=peaks[peaks>(mid_point+one_third_right)]
peaks_left=peaks[peaks<(mid_point-one_third_left)]
try:
point_right=np.min(peaks_right)
except:
point_right=last_nonzero
try:
point_left=np.max(peaks_left)
except:
point_left=first_nonzero
#print(point_left,point_right)
#print(text_regions.shape)
if point_right>=mask_marginals.shape[1]:
point_right=mask_marginals.shape[1]-1
try:
mask_marginals[:,point_left:point_right]=1
except:
mask_marginals[:,:]=1
#print(mask_marginals.shape,point_left,point_right,'nadosh')
mask_marginals_rotated=rotate_image(mask_marginals,-slope_deskew)
#print(mask_marginals_rotated.shape,'nadosh')
mask_marginals_rotated_sum=mask_marginals_rotated.sum(axis=0)
mask_marginals_rotated_sum[mask_marginals_rotated_sum!=0]=1
index_x=np.array(range(len(mask_marginals_rotated_sum)))+1
index_x_interest=index_x[mask_marginals_rotated_sum==1]
min_point_of_left_marginal=np.min(index_x_interest)-16
max_point_of_right_marginal=np.max(index_x_interest)+16
if min_point_of_left_marginal<0:
min_point_of_left_marginal=0
if max_point_of_right_marginal>=text_regions.shape[1]:
max_point_of_right_marginal=text_regions.shape[1]-1
#print(np.min(index_x_interest) ,np.max(index_x_interest),'minmaxnew')
#print(mask_marginals_rotated.shape,text_regions.shape,'mask_marginals_rotated')
#plt.imshow(mask_marginals)
#plt.show()
#plt.imshow(mask_marginals_rotated)
#plt.show()
text_regions[(mask_marginals_rotated[:,:]!=1) & (text_regions[:,:]==1)]=4
#plt.imshow(text_regions)
#plt.show()
pixel_img=4
min_area_text=0.00001
polygons_of_marginals=return_contours_of_interested_region(text_regions,pixel_img,min_area_text)
cx_text_only,cy_text_only ,x_min_text_only,x_max_text_only, y_min_text_only ,y_max_text_only,y_cor_x_min_main=find_new_features_of_contours(polygons_of_marginals)
text_regions[(text_regions[:,:]==4)]=1
marginlas_should_be_main_text=[]
x_min_marginals_left=[]
x_min_marginals_right=[]
for i in range(len(cx_text_only)):
x_width_mar=abs(x_min_text_only[i]-x_max_text_only[i])
y_height_mar=abs(y_min_text_only[i]-y_max_text_only[i])
#print(x_width_mar,y_height_mar,y_height_mar/x_width_mar,'y_height_mar')
if x_width_mar>16 and y_height_mar/x_width_mar<18:
marginlas_should_be_main_text.append(polygons_of_marginals[i])
if x_min_text_only[i]<(mid_point-one_third_left):
x_min_marginals_left_new=x_min_text_only[i]
if len(x_min_marginals_left)==0:
x_min_marginals_left.append(x_min_marginals_left_new)
else:
x_min_marginals_left[0]=min(x_min_marginals_left[0],x_min_marginals_left_new)
else:
x_min_marginals_right_new=x_min_text_only[i]
if len(x_min_marginals_right)==0:
x_min_marginals_right.append(x_min_marginals_right_new)
else:
x_min_marginals_right[0]=min(x_min_marginals_right[0],x_min_marginals_right_new)
if len(x_min_marginals_left)==0:
x_min_marginals_left=[0]
if len(x_min_marginals_right)==0:
x_min_marginals_right=[text_regions.shape[1]-1]
#print(x_min_marginals_left[0],x_min_marginals_right[0],'margo')
#print(marginlas_should_be_main_text,'marginlas_should_be_main_text')
text_regions=cv2.fillPoly(text_regions, pts =marginlas_should_be_main_text, color=(4,4))
#print(np.unique(text_regions))
#text_regions[:,:int(x_min_marginals_left[0])][text_regions[:,:int(x_min_marginals_left[0])]==1]=0
#text_regions[:,int(x_min_marginals_right[0]):][text_regions[:,int(x_min_marginals_right[0]):]==1]=0
text_regions[:,:int(min_point_of_left_marginal)][text_regions[:,:int(min_point_of_left_marginal)]==1]=0
text_regions[:,int(max_point_of_right_marginal):][text_regions[:,int(max_point_of_right_marginal):]==1]=0
###text_regions[:,0:point_left][text_regions[:,0:point_left]==1]=4
###text_regions[:,point_right:][ text_regions[:,point_right:]==1]=4
#plt.plot(region_sum_0)
#plt.plot(peaks,region_sum_0[peaks],'*')
#plt.show()
#plt.imshow(text_regions)
#plt.show()
#sys.exit()
else:
pass
return text_regions

34
eynollah/eynollah/utils/pil_cv2.py Normal file
View file

@ -0,0 +1,34 @@
from PIL import Image
import numpy as np
from ocrd_models import OcrdExif
from cv2 import COLOR_GRAY2BGR, COLOR_RGB2BGR, COLOR_BGR2RGB, cvtColor, imread
# from sbb_binarization
def cv2pil(img):
return Image.fromarray(np.array(cvtColor(img, COLOR_BGR2RGB)))
def pil2cv(img):
# from ocrd/workspace.py
color_conversion = COLOR_GRAY2BGR if img.mode in ('1', 'L') else COLOR_RGB2BGR
pil_as_np_array = np.array(img).astype('uint8') if img.mode == '1' else np.array(img)
return cvtColor(pil_as_np_array, color_conversion)
def check_dpi(img):
try:
if isinstance(img, Image.Image):
pil_image = img
elif isinstance(img, str):
pil_image = Image.open(img)
else:
pil_image = cv2pil(img)
exif = OcrdExif(pil_image)
resolution = exif.resolution
if resolution == 1:
raise Exception()
if exif.resolutionUnit == 'cm':
resolution /= 2.54
return int(resolution)
except Exception as e:
print(e)
return 230

4
eynollah/eynollah/utils/resize.py Normal file
View file

@ -0,0 +1,4 @@
import cv2
def resize_image(img_in, input_height, input_width):
return cv2.resize(img_in, (input_width, input_height), interpolation=cv2.INTER_NEAREST)

86
eynollah/eynollah/utils/rotate.py Normal file
View file

@ -0,0 +1,86 @@
import math
import imutils
import cv2
def rotatedRectWithMaxArea(w, h, angle):
if w <= 0 or h <= 0:
return 0, 0
width_is_longer = w >= h
side_long, side_short = (w, h) if width_is_longer else (h, w)
# since the solutions for angle, -angle and 180-angle are all the same,
# if suffices to look at the first quadrant and the absolute values of sin,cos:
sin_a, cos_a = abs(math.sin(angle)), abs(math.cos(angle))
if side_short <= 2.0 * sin_a * cos_a * side_long or abs(sin_a - cos_a) < 1e-10:
# half constrained case: two crop corners touch the longer side,
# the other two corners are on the mid-line parallel to the longer line
x = 0.5 * side_short
wr, hr = (x / sin_a, x / cos_a) if width_is_longer else (x / cos_a, x / sin_a)
else:
# fully constrained case: crop touches all 4 sides
cos_2a = cos_a * cos_a - sin_a * sin_a
wr, hr = (w * cos_a - h * sin_a) / cos_2a, (h * cos_a - w * sin_a) / cos_2a
return wr, hr
def rotate_max_area_new(image, rotated, angle):
wr, hr = rotatedRectWithMaxArea(image.shape[1], image.shape[0], math.radians(angle))
h, w, _ = rotated.shape
y1 = h // 2 - int(hr / 2)
y2 = y1 + int(hr)
x1 = w // 2 - int(wr / 2)
x2 = x1 + int(wr)
return rotated[y1:y2, x1:x2]
def rotation_image_new(img, thetha):
rotated = imutils.rotate(img, thetha)
return rotate_max_area_new(img, rotated, thetha)
def rotate_image(img_patch, slope):
(h, w) = img_patch.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, slope, 1.0)
return cv2.warpAffine(img_patch, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
def rotate_image_different( img, slope):
# img = cv2.imread('images/input.jpg')
num_rows, num_cols = img.shape[:2]
rotation_matrix = cv2.getRotationMatrix2D((num_cols / 2, num_rows / 2), slope, 1)
img_rotation = cv2.warpAffine(img, rotation_matrix, (num_cols, num_rows))
return img_rotation
def rotate_max_area(image, rotated, rotated_textline, rotated_layout, rotated_table_prediction, angle):
wr, hr = rotatedRectWithMaxArea(image.shape[1], image.shape[0], math.radians(angle))
h, w, _ = rotated.shape
y1 = h // 2 - int(hr / 2)
y2 = y1 + int(hr)
x1 = w // 2 - int(wr / 2)
x2 = x1 + int(wr)
return rotated[y1:y2, x1:x2], rotated_textline[y1:y2, x1:x2], rotated_layout[y1:y2, x1:x2], rotated_table_prediction[y1:y2, x1:x2]
def rotation_not_90_func(img, textline, text_regions_p_1, table_prediction, thetha):
rotated = imutils.rotate(img, thetha)
rotated_textline = imutils.rotate(textline, thetha)
rotated_layout = imutils.rotate(text_regions_p_1, thetha)
rotated_table_prediction = imutils.rotate(table_prediction, thetha)
return rotate_max_area(img, rotated, rotated_textline, rotated_layout, rotated_table_prediction, thetha)
def rotation_not_90_func_full_layout(img, textline, text_regions_p_1, text_regions_p_fully, thetha):
rotated = imutils.rotate(img, thetha)
rotated_textline = imutils.rotate(textline, thetha)
rotated_layout = imutils.rotate(text_regions_p_1, thetha)
rotated_layout_full = imutils.rotate(text_regions_p_fully, thetha)
return rotate_max_area_full_layout(img, rotated, rotated_textline, rotated_layout, rotated_layout_full, thetha)
def rotate_max_area_full_layout(image, rotated, rotated_textline, rotated_layout, rotated_layout_full, angle):
wr, hr = rotatedRectWithMaxArea(image.shape[1], image.shape[0], math.radians(angle))
h, w, _ = rotated.shape
y1 = h // 2 - int(hr / 2)
y2 = y1 + int(hr)
x1 = w // 2 - int(wr / 2)
x2 = x1 + int(wr)
return rotated[y1:y2, x1:x2], rotated_textline[y1:y2, x1:x2], rotated_layout[y1:y2, x1:x2], rotated_layout_full[y1:y2, x1:x2]

1799
eynollah/eynollah/utils/separate_lines.py Normal file
View file

File diff suppressed because it is too large Load diff

88
eynollah/eynollah/utils/xml.py Normal file
View file

@ -0,0 +1,88 @@
# pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements,chained-comparison,fixme,broad-except,c-extension-no-member
# pylint: disable=invalid-name
from .counter import EynollahIdCounter
import numpy as np
from datetime import datetime
from ocrd_models.ocrd_page import (
CoordsType,
GlyphType,
ImageRegionType,
MathsRegionType,
MetadataType,
MetadataItemType,
NoiseRegionType,
OrderedGroupIndexedType,
OrderedGroupType,
PcGtsType,
PageType,
ReadingOrderType,
RegionRefIndexedType,
RegionRefType,
SeparatorRegionType,
TableRegionType,
TextLineType,
TextRegionType,
UnorderedGroupIndexedType,
UnorderedGroupType,
WordType,
to_xml)
def create_page_xml(imageFilename, height, width):
now = datetime.now()
pcgts = PcGtsType(
Metadata=MetadataType(
Creator='SBB_QURATOR',
Created=now,
LastChange=now
),
Page=PageType(
imageWidth=str(width),
imageHeight=str(height),
imageFilename=imageFilename,
readingDirection='left-to-right',
textLineOrder='top-to-bottom'
))
return pcgts
def xml_reading_order(page, order_of_texts, id_of_marginalia):
region_order = ReadingOrderType()
og = OrderedGroupType(id="ro357564684568544579089")
page.set_ReadingOrder(region_order)
region_order.set_OrderedGroup(og)
region_counter = EynollahIdCounter()
for idx_textregion, _ in enumerate(order_of_texts):
og.add_RegionRefIndexed(RegionRefIndexedType(index=str(region_counter.get('region')), regionRef=region_counter.region_id(order_of_texts[idx_textregion] + 1)))
region_counter.inc('region')
for id_marginal in id_of_marginalia:
og.add_RegionRefIndexed(RegionRefIndexedType(index=str(region_counter.get('region')), regionRef=id_marginal))
region_counter.inc('region')
def order_and_id_of_texts(found_polygons_text_region, found_polygons_text_region_h, matrix_of_orders, indexes_sorted, index_of_types, kind_of_texts, ref_point):
indexes_sorted = np.array(indexes_sorted)
index_of_types = np.array(index_of_types)
kind_of_texts = np.array(kind_of_texts)
id_of_texts = []
order_of_texts = []
index_of_types_1 = index_of_types[kind_of_texts == 1]
indexes_sorted_1 = indexes_sorted[kind_of_texts == 1]
index_of_types_2 = index_of_types[kind_of_texts == 2]
indexes_sorted_2 = indexes_sorted[kind_of_texts == 2]
counter = EynollahIdCounter(region_idx=ref_point)
for idx_textregion, _ in enumerate(found_polygons_text_region):
id_of_texts.append(counter.next_region_id)
interest = indexes_sorted_1[indexes_sorted_1 == index_of_types_1[idx_textregion]]
if len(interest) > 0:
order_of_texts.append(interest[0])
for idx_headerregion, _ in enumerate(found_polygons_text_region_h):
id_of_texts.append(counter.next_region_id)
interest = indexes_sorted_2[index_of_types_2[idx_headerregion]]
order_of_texts.append(interest)
return order_of_texts, id_of_texts

265
eynollah/eynollah/writer.py Normal file
View file

@ -0,0 +1,265 @@
# pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements,chained-comparison,fixme,broad-except,c-extension-no-member
# pylint: disable=import-error
from pathlib import Path
import os.path
from .utils.xml import create_page_xml, xml_reading_order
from .utils.counter import EynollahIdCounter
from ocrd_utils import getLogger
from ocrd_models.ocrd_page import (
BorderType,
CoordsType,
PcGtsType,
TextLineType,
TextRegionType,
ImageRegionType,
TableRegionType,
SeparatorRegionType,
to_xml
)
import numpy as np
class EynollahXmlWriter():
def __init__(self, *, dir_out, image_filename, curved_line,textline_light, pcgts=None):
self.logger = getLogger('eynollah.writer')
self.counter = EynollahIdCounter()
self.dir_out = dir_out
self.image_filename = image_filename
self.curved_line = curved_line
self.textline_light = textline_light
self.pcgts = pcgts
self.scale_x = None # XXX set outside __init__
self.scale_y = None # XXX set outside __init__
self.height_org = None # XXX set outside __init__
self.width_org = None # XXX set outside __init__
@property
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 serialize_lines_in_marginal(self, marginal_region, all_found_textline_polygons_marginals, marginal_idx, page_coord, all_box_coord_marginals, slopes_marginals, counter):
for j in range(len(all_found_textline_polygons_marginals[marginal_idx])):
coords = CoordsType()
textline = TextLineType(id=counter.next_line_id, Coords=coords)
marginal_region.add_TextLine(textline)
points_co = ''
for l in range(len(all_found_textline_polygons_marginals[marginal_idx][j])):
if not (self.curved_line or self.textline_light):
if len(all_found_textline_polygons_marginals[marginal_idx][j][l]) == 2:
textline_x_coord = max(0, int((all_found_textline_polygons_marginals[marginal_idx][j][l][0] + all_box_coord_marginals[marginal_idx][2] + page_coord[2]) / self.scale_x) )
textline_y_coord = max(0, int((all_found_textline_polygons_marginals[marginal_idx][j][l][1] + all_box_coord_marginals[marginal_idx][0] + page_coord[0]) / self.scale_y) )
else:
textline_x_coord = max(0, int((all_found_textline_polygons_marginals[marginal_idx][j][l][0][0] + all_box_coord_marginals[marginal_idx][2] + page_coord[2]) / self.scale_x) )
textline_y_coord = max(0, int((all_found_textline_polygons_marginals[marginal_idx][j][l][0][1] + all_box_coord_marginals[marginal_idx][0] + page_coord[0]) / self.scale_y) )
points_co += str(textline_x_coord)
points_co += ','
points_co += str(textline_y_coord)
if (self.curved_line or self.textline_light) and np.abs(slopes_marginals[marginal_idx]) <= 45:
if len(all_found_textline_polygons_marginals[marginal_idx][j][l]) == 2:
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][1] + page_coord[0]) / self.scale_y))
else:
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][0][0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][0][1] + page_coord[0]) / self.scale_y))
elif (self.curved_line or self.textline_light) and np.abs(slopes_marginals[marginal_idx]) > 45:
if len(all_found_textline_polygons_marginals[marginal_idx][j][l]) == 2:
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][0] + all_box_coord_marginals[marginal_idx][2] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][1] + all_box_coord_marginals[marginal_idx][0] + page_coord[0]) / self.scale_y))
else:
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][0][0] + all_box_coord_marginals[marginal_idx][2] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((all_found_textline_polygons_marginals[marginal_idx][j][l][0][1] + all_box_coord_marginals[marginal_idx][0] + page_coord[0]) / self.scale_y))
points_co += ' '
coords.set_points(points_co[:-1])
def serialize_lines_in_region(self, text_region, all_found_textline_polygons, region_idx, page_coord, all_box_coord, slopes, counter):
self.logger.debug('enter serialize_lines_in_region')
for j in range(len(all_found_textline_polygons[region_idx])):
coords = CoordsType()
textline = TextLineType(id=counter.next_line_id, Coords=coords)
text_region.add_TextLine(textline)
region_bboxes = all_box_coord[region_idx]
points_co = ''
for idx_contour_textline, contour_textline in enumerate(all_found_textline_polygons[region_idx][j]):
if not (self.curved_line or self.textline_light):
if len(contour_textline) == 2:
textline_x_coord = max(0, int((contour_textline[0] + region_bboxes[2] + page_coord[2]) / self.scale_x))
textline_y_coord = max(0, int((contour_textline[1] + region_bboxes[0] + page_coord[0]) / self.scale_y))
else:
textline_x_coord = max(0, int((contour_textline[0][0] + region_bboxes[2] + page_coord[2]) / self.scale_x))
textline_y_coord = max(0, int((contour_textline[0][1] + region_bboxes[0] + page_coord[0]) / self.scale_y))
points_co += str(textline_x_coord)
points_co += ','
points_co += str(textline_y_coord)
if (self.curved_line or self.textline_light) and np.abs(slopes[region_idx]) <= 45:
if len(contour_textline) == 2:
points_co += str(int((contour_textline[0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((contour_textline[1] + page_coord[0]) / self.scale_y))
else:
points_co += str(int((contour_textline[0][0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((contour_textline[0][1] + page_coord[0])/self.scale_y))
elif (self.curved_line or self.textline_light) and np.abs(slopes[region_idx]) > 45:
if len(contour_textline)==2:
points_co += str(int((contour_textline[0] + region_bboxes[2] + page_coord[2])/self.scale_x))
points_co += ','
points_co += str(int((contour_textline[1] + region_bboxes[0] + page_coord[0])/self.scale_y))
else:
points_co += str(int((contour_textline[0][0] + region_bboxes[2]+page_coord[2])/self.scale_x))
points_co += ','
points_co += str(int((contour_textline[0][1] + region_bboxes[0]+page_coord[0])/self.scale_y))
points_co += ' '
coords.set_points(points_co[:-1])
def write_pagexml(self, pcgts):
out_fname = os.path.join(self.dir_out, self.image_filename_stem) + ".xml"
self.logger.info("output filename: '%s'", out_fname)
with open(out_fname, 'w') as f:
f.write(to_xml(pcgts))
def build_pagexml_no_full_layout(self, found_polygons_text_region, page_coord, order_of_texts, id_of_texts, all_found_textline_polygons, all_box_coord, found_polygons_text_region_img, found_polygons_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_marginals, cont_page, polygons_lines_to_be_written_in_xml, found_polygons_tables):
self.logger.debug('enter build_pagexml_no_full_layout')
# 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))))
counter = EynollahIdCounter()
if len(found_polygons_text_region) > 0:
_counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts))
id_of_marginalia = [_counter_marginals.next_region_id for _ in found_polygons_marginals]
xml_reading_order(page, order_of_texts, id_of_marginalia)
for mm in range(len(found_polygons_text_region)):
textregion = TextRegionType(id=counter.next_region_id, type_='paragraph',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord)),
)
page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_textline_polygons, mm, page_coord, all_box_coord, slopes, counter)
for mm in range(len(found_polygons_marginals)):
marginal = TextRegionType(id=counter.next_region_id, type_='marginalia',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord)))
page.add_TextRegion(marginal)
self.serialize_lines_in_marginal(marginal, all_found_textline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter)
for mm in range(len(found_polygons_text_region_img)):
img_region = ImageRegionType(id=counter.next_region_id, Coords=CoordsType())
page.add_ImageRegion(img_region)
points_co = ''
for lmm in range(len(found_polygons_text_region_img[mm])):
points_co += str(int((found_polygons_text_region_img[mm][lmm,0,0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((found_polygons_text_region_img[mm][lmm,0,1] + page_coord[0]) / self.scale_y))
points_co += ' '
img_region.get_Coords().set_points(points_co[:-1])
for mm in range(len(polygons_lines_to_be_written_in_xml)):
sep_hor = SeparatorRegionType(id=counter.next_region_id, Coords=CoordsType())
page.add_SeparatorRegion(sep_hor)
points_co = ''
for lmm in range(len(polygons_lines_to_be_written_in_xml[mm])):
points_co += str(int((polygons_lines_to_be_written_in_xml[mm][lmm,0,0] ) / self.scale_x))
points_co += ','
points_co += str(int((polygons_lines_to_be_written_in_xml[mm][lmm,0,1] ) / self.scale_y))
points_co += ' '
sep_hor.get_Coords().set_points(points_co[:-1])
for mm in range(len(found_polygons_tables)):
tab_region = TableRegionType(id=counter.next_region_id, Coords=CoordsType())
page.add_TableRegion(tab_region)
points_co = ''
for lmm in range(len(found_polygons_tables[mm])):
points_co += str(int((found_polygons_tables[mm][lmm,0,0] + page_coord[2]) / self.scale_x))
points_co += ','
points_co += str(int((found_polygons_tables[mm][lmm,0,1] + page_coord[0]) / self.scale_y))
points_co += ' '
tab_region.get_Coords().set_points(points_co[:-1])
return pcgts
def build_pagexml_full_layout(self, found_polygons_text_region, found_polygons_text_region_h, page_coord, order_of_texts, id_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, found_polygons_marginals, all_found_textline_polygons_marginals, all_box_coord_marginals, slopes, slopes_h, slopes_marginals, cont_page, polygons_lines_to_be_written_in_xml):
self.logger.debug('enter build_pagexml_full_layout')
# 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))))
counter = EynollahIdCounter()
_counter_marginals = EynollahIdCounter(region_idx=len(order_of_texts))
id_of_marginalia = [_counter_marginals.next_region_id for _ in found_polygons_marginals]
xml_reading_order(page, order_of_texts, id_of_marginalia)
for mm in range(len(found_polygons_text_region)):
textregion = TextRegionType(id=counter.next_region_id, type_='paragraph',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region[mm], page_coord)))
page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_textline_polygons, mm, page_coord, all_box_coord, slopes, counter)
self.logger.debug('len(found_polygons_text_region_h) %s', len(found_polygons_text_region_h))
for mm in range(len(found_polygons_text_region_h)):
textregion = TextRegionType(id=counter.next_region_id, type_='header',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region_h[mm], page_coord)))
page.add_TextRegion(textregion)
self.serialize_lines_in_region(textregion, all_found_textline_polygons_h, mm, page_coord, all_box_coord_h, slopes_h, counter)
for mm in range(len(found_polygons_marginals)):
marginal = TextRegionType(id=counter.next_region_id, type_='marginalia',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_marginals[mm], page_coord)))
page.add_TextRegion(marginal)
self.serialize_lines_in_marginal(marginal, all_found_textline_polygons_marginals, mm, page_coord, all_box_coord_marginals, slopes_marginals, counter)
for mm in range(len(found_polygons_drop_capitals)):
page.add_TextRegion(TextRegionType(id=counter.next_region_id, type_='drop-capital',
Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_drop_capitals[mm], page_coord))))
for mm in range(len(found_polygons_text_region_img)):
page.add_ImageRegion(ImageRegionType(id=counter.next_region_id, Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_text_region_img[mm], page_coord))))
for mm in range(len(polygons_lines_to_be_written_in_xml)):
page.add_SeparatorRegion(ImageRegionType(id=counter.next_region_id, Coords=CoordsType(points=self.calculate_polygon_coords(polygons_lines_to_be_written_in_xml[mm], [0 , 0, 0, 0]))))
for mm in range(len(found_polygons_tables)):
page.add_TableRegion(TableRegionType(id=counter.next_region_id, Coords=CoordsType(points=self.calculate_polygon_coords(found_polygons_tables[mm], page_coord))))
return pcgts
def calculate_polygon_coords(self, contour, page_coord):
self.logger.debug('enter calculate_polygon_coords')
coords = ''
for value_bbox in contour:
if len(value_bbox) == 2:
coords += str(int((value_bbox[0] + page_coord[2]) / self.scale_x))
coords += ','
coords += str(int((value_bbox[1] + page_coord[0]) / self.scale_y))
else:
coords += str(int((value_bbox[0][0] + page_coord[2]) / self.scale_x))
coords += ','
coords += str(int((value_bbox[0][1] + page_coord[0]) / self.scale_y))
coords=coords + ' '
return coords[:-1]