qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-10-31 19:24:12 +01:00
Code Issues Projects Releases Wiki Activity

Use ocrd-tesserocr-segment-*

Browse source
This commit is contained in:
Gerber, Mike 2019-06-24 12:13:49 +02:00
parent e30f03699c
commit 5e1ece4877
1 changed files with 14 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

22
my_ocrd_workflow
View file

@ -40,18 +40,24 @@ do_fontident() {
} }
do_linesegmentation() { do_linesegmentation() {
remove_filegrp OCR-D-SEG-REGION mets.xml
remove_filegrp OCR-D-SEG-LINE mets.xml remove_filegrp OCR-D-SEG-LINE mets.xml
ocrd-ocropy-segment -l $LOG_LEVEL \ #ocrd-ocropy-segment -l $LOG_LEVEL \
-m mets.xml -I OCR-D-IMG -O OCR-D-SEG-LINE # -m mets.xml -I OCR-D-IMG -O OCR-D-SEG-LINE
# XXX ocrd-ocropy-segment throws an exception for buerger_gedichte_1778.ocrd
#ocrd workspace validate mets.xml #ocrd workspace validate mets.xml
# XXX This leaves copies of the images at the top level of the workspace, because it "downloads" the "remote" files. ocrd-tesserocr-segment-region -l $LOG_LEVEL \
# Clean it up. -m mets.xml -I OCR-D-IMG -O OCR-D-SEG-REGION
find . -maxdepth 1 -name "OCR-D-IMG*" -type f -exec rm -v {} \; #ocrd workspace validate mets.xml
ocrd-tesserocr-segment-line -l $LOG_LEVEL \
-m mets.xml -I OCR-D-SEG-REGION -O OCR-D-SEG-LINE
#ocrd workspace validate mets.xml
# XXX compare ocrd-tesserocr-segment* vs tesseract native
# XXX ocrd-tesserocr-segment-line does not seem to produce any line segmentation # XXX This leaves copies of the images at the top level of the workspace, because it "downloads" the "remote" files.
# XXX mv {ocrd-ocropy-segment,-line} # Clean it up. (Maybe only affects ocrd-ocropy-segment)
# XXX ocrd-ocropy-segment throws an exception for buerger_gedichte_1778.ocrd find . -maxdepth 1 -name "OCR-D-IMG*" -type f -exec rm -v {} \;
} }
do_ocr() { do_ocr() {