qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-10-30 18:54:14 +01:00
Code Issues Projects Releases Wiki Activity

🔧 Evaluate both Tesseract and Calamari results

Browse source
This commit is contained in:
Gerber, Mike 2019-08-21 13:07:27 +02:00
parent 0bc06c2fad
commit 343a3fbf82
1 changed files with 22 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

37
my_ocrd_workflow
View file

@ -149,25 +149,32 @@ page_validate_xml OCR-D-SEG-REGION
page_validate_xml OCR-D-SEG-LINE
do_validate
do_ocr_calamari
do_ocr
page_validate_xml OCR-D-OCR-TESS
page_workaround_remove_conf OCR-D-OCR-TESS
do_validate
page_fix_image_references OCR-D-OCR-TESS
page_validate_xml OCR-D-OCR-TESS
do_validate
# As a last step, downgrade to PAGE 2018 to support PAGE Viewer
page_downgrade_to_2018 OCR-D-OCR-TESS
do_validate
if ocrd workspace list-group | grep -q OCR-D-GT-PAGE; then
remove_filegrp OCR-D-OCR-TESS-EVAL mets.xml
ocrd-dinglehopper -m mets.xml -I OCR-D-GT-PAGE,OCR-D-OCR-TESS -O OCR-D-OCR-TESS-EVAL
fi
for ocr_filegrp in OCR-D-OCR-CALAMARI OCR-D-OCR-TESS; do
page_validate_xml $ocr_filegrp
page_workaround_remove_conf $ocr_filegrp
do_validate
page_fix_image_references $ocr_filegrp
page_validate_xml $ocr_filegrp
do_validate
# As a last step, downgrade to PAGE 2018 to support PAGE Viewer
page_downgrade_to_2018 $ocr_filegrp
do_validate
if ocrd workspace list-group | grep -q OCR-D-GT-PAGE; then
remove_filegrp $ocr_filegrp-EVAL mets.xml
ocrd-dinglehopper -m mets.xml -I OCR-D-GT-PAGE,$ocr_filegrp -O $ocr_filegrp-EVAL
fi
done
# vim:tw=120: