qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-12-11 05:34:15 +01:00
Code Issues Projects Releases Wiki Activity

Restored correct functionality of the extract_only_images mode and cleaned up the argument handling

Browse source
This commit is contained in:
vahidrezanezhad 2025-12-03 12:01:42 +01:00
parent 51abe9617a
commit d687d862d6
2 changed files with 32 additions and 90 deletions
Download patch file Download diff file Expand all files Collapse all files

69
src/eynollah/cli/cli_extract_images.py
View file

@ -33,30 +33,6 @@ import click
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",
@ -75,12 +51,6 @@ import click
is_flag=True,
help="if this parameter set to true, this tool would ignore page extraction",
)
@click.option(
"--reading_order_machine_based/--heuristic_reading_order",
"-romb/-hro",
is_flag=True,
help="if this parameter set to true, this tool would apply machine based reading order detection",
)
@click.option(
"--num_col_upper",
"-ncu",
@ -91,22 +61,6 @@ import click
"-ncl",
help="upper limit of columns in document image",
)
@click.option(
"--threshold_art_class_layout",
"-tharl",
help="threshold of artifical class in the case of layout detection. The default value is 0.1",
)
@click.option(
"--threshold_art_class_textline",
"-thart",
help="threshold of artifical class in the case of textline detection. The default value is 0.1",
)
@click.option(
"--skip_layout_and_reading_order",
"-slro/-noslro",
is_flag=True,
help="if this parameter set to true, this tool will ignore layout detection and reading order. It means that textline detection will be done within printspace and contours of textline will be written in xml output file.",
)
@click.pass_context
def extract_images_cli(
ctx,
@ -115,30 +69,17 @@ def extract_images_cli(
overwrite,
dir_in,
save_images,
save_layout,
save_deskewed,
save_all,
save_page,
enable_plotting,
input_binary,
reading_order_machine_based,
num_col_upper,
num_col_lower,
threshold_art_class_textline,
threshold_art_class_layout,
skip_layout_and_reading_order,
ignore_page_extraction,
):
"""
Detect Layout (with optional image enhancement and reading order detection)
"""
assert enable_plotting or not save_layout, "Plotting with -sl also requires -ep"
assert enable_plotting or not save_deskewed, "Plotting with -sd also requires -ep"
assert enable_plotting or not save_all, "Plotting with -sa also requires -ep"
assert enable_plotting or not save_page, "Plotting with -sp also requires -ep"
assert enable_plotting or not save_images, "Plotting with -si also requires -ep"
assert not enable_plotting or save_layout or save_deskewed or save_all or save_page or save_images, \
"Plotting with -ep also requires -sl, -sd, -sa, -sp, -si or -ae"
assert not enable_plotting or save_images, "Plotting with -ep also requires -si"
assert bool(image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
from ..extract_images import EynollahImageExtractor
@ -147,21 +88,13 @@ def extract_images_cli(
enable_plotting=enable_plotting,
input_binary=input_binary,
ignore_page_extraction=ignore_page_extraction,
reading_order_machine_based=reading_order_machine_based,
num_col_upper=num_col_upper,
num_col_lower=num_col_lower,
skip_layout_and_reading_order=skip_layout_and_reading_order,
threshold_art_class_textline=threshold_art_class_textline,
threshold_art_class_layout=threshold_art_class_layout,
)
extractor.run(overwrite=overwrite,
image_filename=image,
dir_in=dir_in,
dir_out=out,
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,
)

53
src/eynollah/extract_images.py
View file

@ -30,23 +30,26 @@ class EynollahImageExtractor(Eynollah):
enable_plotting : bool = False,
input_binary : bool = False,
ignore_page_extraction : bool = False,
reading_order_machine_based : bool = False,
num_col_upper : Optional[int] = None,
num_col_lower : Optional[int] = None,
threshold_art_class_layout: Optional[float] = None,
threshold_art_class_textline: Optional[float] = None,
skip_layout_and_reading_order : bool = False,
full_layout : bool = False,
tables : bool = False,
curved_line : bool = False,
allow_enhancement : bool = False,
):
self.logger = logging.getLogger('eynollah.extract_images')
self.model_zoo = model_zoo
self.plotter = None
self.reading_order_machine_based = reading_order_machine_based
self.tables = tables
self.curved_line = curved_line
self.allow_enhancement = allow_enhancement
self.enable_plotting = enable_plotting
# --input-binary sensible if image is very dark, if layout is not working.
self.input_binary = input_binary
self.ignore_page_extraction = ignore_page_extraction
self.skip_layout_and_reading_order = skip_layout_and_reading_order
self.full_layout = full_layout
if num_col_upper:
self.num_col_upper = int(num_col_upper)
else:
@ -58,16 +61,6 @@ class EynollahImageExtractor(Eynollah):
# for parallelization of CPU-intensive tasks:
self.executor = ProcessPoolExecutor(max_workers=cpu_count())
if threshold_art_class_layout:
self.threshold_art_class_layout = float(threshold_art_class_layout)
else:
self.threshold_art_class_layout = 0.1
if threshold_art_class_textline:
self.threshold_art_class_textline = float(threshold_art_class_textline)
else:
self.threshold_art_class_textline = 0.1
t_start = time.time()
@ -115,7 +108,7 @@ class EynollahImageExtractor(Eynollah):
img_h_new = int(img.shape[0] / float(img.shape[1]) * img_w_new)
img_resized = resize_image(img,img_h_new, img_w_new )
prediction_regions_org, _ = self.do_prediction_new_concept(True, img_resized, self.model_zoo.get("region"))
prediction_regions_org, _ = self.do_prediction_new_concept(True, img_resized, self.model_zoo.get("extract_images"))
prediction_regions_org = resize_image(prediction_regions_org,img_height_h, img_width_h )
image_page, page_coord, cont_page = self.extract_page()
@ -183,7 +176,6 @@ class EynollahImageExtractor(Eynollah):
"""
self.logger.debug("enter run")
t0_tot = time.time()
# Log enabled features directly
enabled_modes = []
if self.full_layout:
@ -261,10 +253,27 @@ class EynollahImageExtractor(Eynollah):
_, _, _, polygons_of_images, \
image_page, page_coord, cont_page = \
self.get_regions_light_v_extract_only_images(img_res, num_col_classifier)
pcgts = self.writer.build_pagexml_no_full_layout(
[], page_coord, [], [], [], [],
polygons_of_images, [], [], [], [], [], [], [], [], [],
cont_page, [], [])
found_polygons_text_region=[],
page_coord=page_coord,
order_of_texts=[],
all_found_textline_polygons=[],
all_box_coord=[],
found_polygons_text_region_img=polygons_of_images,
found_polygons_marginals_left=[],
found_polygons_marginals_right=[],
all_found_textline_polygons_marginals_left=[],
all_found_textline_polygons_marginals_right=[],
all_box_coord_marginals_left=[],
all_box_coord_marginals_right=[],
slopes=[],
slopes_marginals_left=[],
slopes_marginals_right=[],
cont_page=cont_page,
polygons_seplines=[],
found_polygons_tables=[],
)
if self.plotter:
self.plotter.write_images_into_directory(polygons_of_images, image_page)