mirror of
https://github.com/qurator-spk/sbb_binarization.git
synced 2025-06-08 11:50:03 +02:00
implement region/line binarization
This commit is contained in:
parent
5909f94fab
commit
ee26ebd7d8
2 changed files with 55 additions and 15 deletions
|
@ -14,7 +14,7 @@
|
||||||
"type": "string",
|
"type": "string",
|
||||||
"enum": ["page", "region", "line"],
|
"enum": ["page", "region", "line"],
|
||||||
"default": "page",
|
"default": "page",
|
||||||
"description": "PAGE XML hierarchy level to operate on (currently only page supported"
|
"description": "PAGE XML hierarchy level to operate on"
|
||||||
},
|
},
|
||||||
"patches": {
|
"patches": {
|
||||||
"description": "by setting this parameter to true you let the model to see the image in patches.",
|
"description": "by setting this parameter to true you let the model to see the image in patches.",
|
||||||
|
|
|
@ -1,3 +1,5 @@
|
||||||
|
# TODO: AlternativeImage 'binarized' comment should be additive
|
||||||
|
|
||||||
import os.path
|
import os.path
|
||||||
from pkg_resources import resource_string
|
from pkg_resources import resource_string
|
||||||
from json import loads
|
from json import loads
|
||||||
|
@ -9,13 +11,7 @@ from ocrd_utils import (
|
||||||
MIMETYPE_PAGE
|
MIMETYPE_PAGE
|
||||||
)
|
)
|
||||||
from ocrd_modelfactory import page_from_file
|
from ocrd_modelfactory import page_from_file
|
||||||
from ocrd_models.ocrd_page import (
|
from ocrd_models.ocrd_page import AlternativeImageType, to_xml
|
||||||
MetadataItemType,
|
|
||||||
LabelsType, LabelType,
|
|
||||||
AlternativeImageType,
|
|
||||||
TextRegionType,
|
|
||||||
to_xml
|
|
||||||
)
|
|
||||||
from ocrd import Processor
|
from ocrd import Processor
|
||||||
|
|
||||||
from .sbb_binarize import SbbBinarizer
|
from .sbb_binarize import SbbBinarizer
|
||||||
|
@ -48,24 +44,68 @@ class SbbBinarizeProcessor(Processor):
|
||||||
LOG.info("INPUT FILE %i / %s", n, page_id)
|
LOG.info("INPUT FILE %i / %s", n, page_id)
|
||||||
pcgts = page_from_file(self.workspace.download_file(input_file))
|
pcgts = page_from_file(self.workspace.download_file(input_file))
|
||||||
self.add_metadata(pcgts)
|
self.add_metadata(pcgts)
|
||||||
|
pcgts.set_pcGtsId(file_id)
|
||||||
page = pcgts.get_Page()
|
page = pcgts.get_Page()
|
||||||
|
|
||||||
if oplevel == 'page':
|
if oplevel == 'page':
|
||||||
LOG.info("Binarizing on 'page' level in page '%s'", page_id)
|
LOG.info("Binarizing on 'page' level in page '%s'", page_id)
|
||||||
page_image, page_xywh, _ = self.workspace.image_from_page(page, page_id)
|
page_image, page_xywh, _ = self.workspace.image_from_page(page, page_id)
|
||||||
binarizer = SbbBinarizer(image=page_image, model=model_path, patches=use_patches, save=None)
|
bin_image = SbbBinarizer(
|
||||||
bin_image = binarizer.run()
|
image=page_image,
|
||||||
|
model=model_path,
|
||||||
|
patches=use_patches,
|
||||||
|
save=None
|
||||||
|
).run()
|
||||||
# update METS (add the image file):
|
# update METS (add the image file):
|
||||||
bin_image_path = self.workspace.save_image_file(bin_image,
|
bin_image_path = self.workspace.save_image_file(bin_image,
|
||||||
file_id + '.IMG-BIN',
|
file_id + '.IMG-BIN',
|
||||||
page_id=page_id,
|
page_id=page_id,
|
||||||
file_grp=self.output_file_grp)
|
file_grp=self.output_file_grp)
|
||||||
page.add_AlternativeImage(filename=bin_image_path, comment="binarized")
|
page.add_AlternativeImage(AlternativeImageType(filename=bin_image_path, comment="binarized"))
|
||||||
else:
|
|
||||||
raise NotImplementedError("Binarization below page level not implemented yet")
|
else:
|
||||||
|
regions = page.get_AllRegions(['Text', 'Table'])
|
||||||
|
if not regions:
|
||||||
|
LOG.warning("Page '%s' contains no text/table regions", page_id)
|
||||||
|
|
||||||
|
for region in regions:
|
||||||
|
region_image, region_xywh = self.workspace.image_from_segment(region, page_image, page_xywh)
|
||||||
|
|
||||||
|
if oplevel == 'region':
|
||||||
|
region_image_bin = SbbBinarizer(
|
||||||
|
image=region_image,
|
||||||
|
model=model_path,
|
||||||
|
patches=use_patches,
|
||||||
|
save=None
|
||||||
|
).run()
|
||||||
|
region_image_bin_path = self.workspace.save_image_file(
|
||||||
|
region_image_bin,
|
||||||
|
"%s_%s.IMG-BIN" % (file_id, region.id),
|
||||||
|
page_id=page_id,
|
||||||
|
file_grp=self.output_file_grp)
|
||||||
|
region.add_AlternativeImage(
|
||||||
|
AlternativeImageType(filename=region_image_bin_path, comments='binarized'))
|
||||||
|
|
||||||
|
elif oplevel == 'line':
|
||||||
|
lines = region.get_TextLine()
|
||||||
|
if not lines:
|
||||||
|
LOG.warning("Page '%s' region '%s' contains no text lines", page_id, region.id)
|
||||||
|
for line in lines:
|
||||||
|
line_image, line_xywh = self.workspace.image_from_segment(line, page_image, page_xywh)
|
||||||
|
line_image_bin = SbbBinarizer(
|
||||||
|
image=line_image,
|
||||||
|
model=model_path,
|
||||||
|
patches=use_patches,
|
||||||
|
save=None
|
||||||
|
).run()
|
||||||
|
line_image_bin_path = self.workspace.save_image_file(
|
||||||
|
line_image_bin,
|
||||||
|
"%s_%s_%s.IMG-BIN" % (file_id, region.id, line.id),
|
||||||
|
page_id=page_id,
|
||||||
|
file_grp=self.output_file_grp)
|
||||||
|
line.add_AlternativeImage(
|
||||||
|
AlternativeImageType(filename=line_image_bin_path, comments='binarized'))
|
||||||
|
|
||||||
file_id = make_file_id(input_file, self.output_file_grp)
|
|
||||||
pcgts.set_pcGtsId(file_id)
|
|
||||||
self.workspace.add_file(
|
self.workspace.add_file(
|
||||||
ID=file_id,
|
ID=file_id,
|
||||||
file_grp=self.output_file_grp,
|
file_grp=self.output_file_grp,
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue