qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-09 12:19:54 +02:00
Code Issues Projects Releases Wiki Activity

machine based reading order as an argument

Browse source
This commit is contained in:
vahidrezanezhad 2023-12-13 01:44:51 +01:00
parent 941d87328a
commit eac18c553d
2 changed files with 11 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
qurator/eynollah/cli.py
View file

@ -133,6 +133,12 @@ from qurator.eynollah.eynollah import Eynollah
is_flag=True, is_flag=True,
help="if this parameter set to true, this tool would ignore page extraction", 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( @click.option(
"--log-level", "--log-level",
"-l", "-l",
@ -160,6 +166,7 @@ def main(
allow_scaling, allow_scaling,
headers_off, headers_off,
light_version, light_version,
reading_order_machine_based,
ignore_page_extraction, ignore_page_extraction,
log_level log_level
): ):
@ -197,6 +204,7 @@ def main(
headers_off=headers_off, headers_off=headers_off,
light_version=light_version, light_version=light_version,
ignore_page_extraction=ignore_page_extraction, ignore_page_extraction=ignore_page_extraction,
reading_order_machine_based=reading_order_machine_based,
) )
eynollah.run() eynollah.run()
#pcgts = eynollah.run() #pcgts = eynollah.run()

6
qurator/eynollah/eynollah.py
View file

@ -165,6 +165,7 @@ class Eynollah:
headers_off=False, headers_off=False,
light_version=False, light_version=False,
ignore_page_extraction=False, ignore_page_extraction=False,
reading_order_machine_based=False,
override_dpi=None, override_dpi=None,
logger=None, logger=None,
pcgts=None, pcgts=None,
@ -181,6 +182,7 @@ class Eynollah:
self.dir_in = dir_in self.dir_in = dir_in
self.dir_of_all = dir_of_all self.dir_of_all = dir_of_all
self.dir_save_page = dir_save_page self.dir_save_page = dir_save_page
self.reading_order_machine_based = reading_order_machine_based
self.dir_of_deskewed = dir_of_deskewed self.dir_of_deskewed = dir_of_deskewed
self.dir_of_deskewed = dir_of_deskewed self.dir_of_deskewed = dir_of_deskewed
self.dir_of_cropped_images=dir_of_cropped_images self.dir_of_cropped_images=dir_of_cropped_images
@ -226,7 +228,7 @@ class Eynollah:
self.model_page_dir = dir_models + "/eynollah-page-extraction_20210425" self.model_page_dir = dir_models + "/eynollah-page-extraction_20210425"
self.model_region_dir_p_ens = dir_models + "/eynollah-main-regions-ensembled_20210425" self.model_region_dir_p_ens = dir_models + "/eynollah-main-regions-ensembled_20210425"
self.model_region_dir_p_ens_light = dir_models + "/eynollah-main-regions_20220314" self.model_region_dir_p_ens_light = dir_models + "/eynollah-main-regions_20220314"
self.model_reading_order_machine_dir = dir_models + "/model_6_reading_order_machine_based" self.model_reading_order_machine_dir = dir_models + "/model_ens_reading_order_machine_based"
if self.textline_light: if self.textline_light:
self.model_textline_dir = dir_models + "/eynollah-textline_light_20210425" self.model_textline_dir = dir_models + "/eynollah-textline_light_20210425"
else: else:
@ -3139,8 +3141,6 @@ class Eynollah:
Get image and scales, then extract the page of scanned image Get image and scales, then extract the page of scanned image
""" """
self.logger.debug("enter run") self.logger.debug("enter run")
self.reading_order_machine_based = True#False#True#True
t0_tot = time.time() t0_tot = time.time()