qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-07 19:35:01 +02:00
Code Issues Projects Releases Wiki Activity

light version as option

Browse source
This commit is contained in:
vahid 2022-03-14 11:37:32 -04:00
parent b8a532180a
commit cf5ef8f5ae
2 changed files with 15 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

10
qurator/eynollah/cli.py
View file

@ -92,11 +92,17 @@ from qurator.eynollah.eynollah import Eynollah
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", 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( @click.option(
"--headers-off/--headers-on", "--headers_off/--headers-on",
"-ho/-noho", "-ho/-noho",
is_flag=True, is_flag=True,
help="if this parameter set to true, this tool would ignore headers role in reading order", 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( @click.option(
"--log-level", "--log-level",
"-l", "-l",
@ -119,6 +125,7 @@ def main(
input_binary, input_binary,
allow_scaling, allow_scaling,
headers_off, headers_off,
light_version,
log_level log_level
): ):
if log_level: if log_level:
@ -146,6 +153,7 @@ def main(
input_binary=input_binary, input_binary=input_binary,
allow_scaling=allow_scaling, allow_scaling=allow_scaling,
headers_off=headers_off, headers_off=headers_off,
light_version=light_version,
) )
pcgts = eynollah.run() pcgts = eynollah.run()
eynollah.writer.write_pagexml(pcgts) eynollah.writer.write_pagexml(pcgts)

11
qurator/eynollah/eynollah.py
View file

@ -100,6 +100,7 @@ class Eynollah:
input_binary=False, input_binary=False,
allow_scaling=False, allow_scaling=False,
headers_off=False, headers_off=False,
light_version=False,
override_dpi=None, override_dpi=None,
logger=None, logger=None,
pcgts=None, pcgts=None,
@ -119,6 +120,7 @@ class Eynollah:
self.input_binary = input_binary self.input_binary = input_binary
self.allow_scaling = allow_scaling self.allow_scaling = allow_scaling
self.headers_off = headers_off self.headers_off = headers_off
self.light_version = light_version
self.plotter = None if not enable_plotting else EynollahPlotter( self.plotter = None if not enable_plotting else EynollahPlotter(
dir_out=self.dir_out, dir_out=self.dir_out,
dir_of_all=dir_of_all, dir_of_all=dir_of_all,
@ -2778,16 +2780,15 @@ class Eynollah:
""" """
Get image and scales, then extract the page of scanned image Get image and scales, then extract the page of scanned image
""" """
light_version = True
self.logger.debug("enter run") self.logger.debug("enter run")
t0 = time.time() t0 = time.time()
img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement(light_version) img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement(self.light_version)
self.logger.info("Enhancing took %.1fs ", time.time() - t0) self.logger.info("Enhancing took %.1fs ", time.time() - t0)
t1 = time.time() t1 = time.time()
if light_version: if self.light_version:
text_regions_p_1 ,erosion_hurts, polygons_lines_xml, textline_mask_tot_ea = self.get_regions_from_xy_2models_light(img_res, is_image_enhanced, num_col_classifier) text_regions_p_1 ,erosion_hurts, polygons_lines_xml, textline_mask_tot_ea = self.get_regions_from_xy_2models_light(img_res, is_image_enhanced, num_col_classifier)
slope_deskew, slope_first = self.run_deskew(textline_mask_tot_ea) slope_deskew, slope_first = self.run_deskew(textline_mask_tot_ea)
@ -2811,7 +2812,7 @@ class Eynollah:
return pcgts return pcgts
t1 = time.time() t1 = time.time()
if not light_version: if not self.light_version:
textline_mask_tot_ea = self.run_textline(image_page) textline_mask_tot_ea = self.run_textline(image_page)
self.logger.info("textline detection took %.1fs", time.time() - t1) self.logger.info("textline detection took %.1fs", time.time() - t1)
@ -2942,7 +2943,7 @@ class Eynollah:
boxes_marginals, _ = get_text_region_boxes_by_given_contours(polygons_of_marginals) boxes_marginals, _ = get_text_region_boxes_by_given_contours(polygons_of_marginals)
if not self.curved_line: if not self.curved_line:
if light_version: if self.light_version:
slopes, all_found_texline_polygons, boxes_text, txt_con_org, contours_only_text_parent, all_box_coord, index_by_text_par_con = self.get_slopes_and_deskew_new_light(txt_con_org, contours_only_text_parent, textline_mask_tot_ea, image_page_rotated, boxes_text, slope_deskew) slopes, all_found_texline_polygons, boxes_text, txt_con_org, contours_only_text_parent, all_box_coord, index_by_text_par_con = self.get_slopes_and_deskew_new_light(txt_con_org, contours_only_text_parent, textline_mask_tot_ea, image_page_rotated, boxes_text, slope_deskew)
slopes_marginals, all_found_texline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, all_box_coord_marginals, _ = self.get_slopes_and_deskew_new_light(polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea, image_page_rotated, boxes_marginals, slope_deskew) slopes_marginals, all_found_texline_polygons_marginals, boxes_marginals, _, polygons_of_marginals, all_box_coord_marginals, _ = self.get_slopes_and_deskew_new_light(polygons_of_marginals, polygons_of_marginals, textline_mask_tot_ea, image_page_rotated, boxes_marginals, slope_deskew)
else: else: