qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-07-06 11:39:52 +02:00
Code Issues Projects Releases Wiki Activity

Add OCR step

Browse source
This commit is contained in:
Gerber, Mike 2019-06-19 13:02:54 +02:00
parent a64b9cf5c8
commit 9bd3853c78
1 changed files with 9 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

9
my_ocrd_workflow
View file

@ -38,9 +38,18 @@ do_linesegmentation() {
#ocrd workspace validate mets.xml #ocrd workspace validate mets.xml
} }
do_ocr() {
ocrd_tesserocr_recognize_parameters='{ "model": "eng" }' # TODO mods:language + fontident → model
remove_filegrp OCR-D-OCR-TESS mets.xml
ocrd-tesserocr-recognize -l DEBUG \
-m mets.xml -I OCR-D-SEG-LINE -O OCR-D-OCR-TESS \
-p <(echo $ocrd_tesserocr_recognize_parameters)
#ocrd workspace validate mets.xml
}
do_fontident do_fontident
do_linesegmentation do_linesegmentation
do_ocr
# XXX Multiple calls create multiple identical mets:agent elements # XXX Multiple calls create multiple identical mets:agent elements