qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-09 20:29:55 +02:00
Code Issues Projects Releases Wiki Activity

OCR-D CLI: remove allow_enhancement parameter

Browse source 
It does not toggle enhancement (eynollah does that internally anyway)
but setting it to true will base the coordinate calculations on that
enhanced (different-sized) image instead of the original. That is never
sensible in the OCR-D context.
This commit is contained in:
Konstantin Baierer 2021-05-18 18:58:18 +02:00
parent 5d2fe79822
commit 45939abdff
2 changed files with 2 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

5
qurator/eynollah/ocrd-tool.json
View file

@ -33,11 +33,6 @@
"default": false, "default": false,
"description": "try to return contour of textlines instead of just rectangle bounding box. Needs more processing time" "description": "try to return contour of textlines instead of just rectangle bounding box. Needs more processing time"
}, },
"allow_enhancement": {
"type": "boolean",
"default": true,
"description": "if the input image has less than 300 DPI, then upscale and enhance"
},
"allow_scaling": { "allow_scaling": {
"type": "boolean", "type": "boolean",
"default": false, "default": false,

3
qurator/eynollah/processor.py
View file

@ -37,6 +37,7 @@ class EynollahProcessor(Processor):
page_id = input_file.pageId or input_file.ID page_id = input_file.pageId or input_file.ID
LOG.info("INPUT FILE %s (%d/%d) ", page_id, n + 1, len(self.input_files)) LOG.info("INPUT FILE %s (%d/%d) ", page_id, n + 1, len(self.input_files))
pcgts = page_from_file(self.workspace.download_file(input_file)) pcgts = page_from_file(self.workspace.download_file(input_file))
print('width %s height %s' % (pcgts.get_Page().imageWidth, pcgts.get_Page().imageHeight))
self.add_metadata(pcgts) self.add_metadata(pcgts)
page = pcgts.get_Page() page = pcgts.get_Page()
# XXX loses DPI information # XXX loses DPI information
@ -44,7 +45,7 @@ class EynollahProcessor(Processor):
image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(url=page.imageFilename))).local_filename image_filename = self.workspace.download_file(next(self.workspace.mets.find_files(url=page.imageFilename))).local_filename
eynollah_kwargs = { eynollah_kwargs = {
'dir_models': self.resolve_resource(self.parameter['models']), 'dir_models': self.resolve_resource(self.parameter['models']),
'allow_enhancement': self.parameter['allow_enhancement'], 'allow_enhancement': False,
'curved_line': self.parameter['curved_line'], 'curved_line': self.parameter['curved_line'],
'full_layout': self.parameter['full_layout'], 'full_layout': self.parameter['full_layout'],
'allow_scaling': self.parameter['allow_scaling'], 'allow_scaling': self.parameter['allow_scaling'],