qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-14 22:59:53 +02:00
Code Issues Projects Releases Wiki Activity

OCR-D: ensure page image gets replaced in result as well if not the original file

Browse source
This commit is contained in:
Robert Sachunsky 2025-03-31 01:17:14 +02:00
parent 55969b0173
commit 4338259ca1
1 changed files with 9 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/eynollah/processor.py
View file

@ -41,18 +41,20 @@ class EynollahProcessor(Processor):
assert input_pcgts[0]
assert self.parameter
pcgts = input_pcgts[0]
result = OcrdPageResult(pcgts)
page = pcgts.get_Page()
# if not('://' in page.imageFilename):
# image_filename = next(self.workspace.mets.find_files(local_filename=page.imageFilename)).local_filename
# else:
# # could be a URL with file:// or truly remote
# image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(url=page.imageFilename))).local_filename
page_image, _, _ = self.workspace.image_from_page(
page, page_id,
# avoid any features that would change the coordinate system: cropped,deskewed
# (the PAGE builder merely adds regions, so afterwards we would not know which to transform)
# also avoid binarization as models usually fare better on grayscale/RGB
feature_filter='cropped,deskewed,binarized')
if hasattr(page_image, 'filename'):
image_filename = page_image.filename
else:
image_filename = "dummy" # will be replaced by ocrd.Processor.process_page_file
result.images.append(OcrdPageResultImage(page_image, '.IMG', page)) # mark as new original
# FIXME: mask out already existing regions (incremental segmentation)
eynollah = Eynollah(
self.resolve_resource(self.parameter['models']),
logger=self.logger,
@ -68,7 +70,7 @@ class EynollahProcessor(Processor):
tables=self.parameter['tables'],
override_dpi=self.parameter['dpi'],
pcgts=pcgts,
image_filename=page.imageFilename,
image_filename=image_filename,
image_pil=page_image
)
if self.models is not None:
@ -76,4 +78,4 @@ class EynollahProcessor(Processor):
eynollah.models = self.models
eynollah.run()
self.models = eynollah.models
return OcrdPageResult(pcgts)
return result