qurator-spk/ocrd-galley
1
0
Fork 0
mirror of https://github.com/qurator-spk/ocrd-galley.git synced 2025-06-09 06:39:53 +02:00
Code Issues Projects Releases Wiki Activity

🧹 Update/move some XXXs/TODOs

Browse source
This commit is contained in:
Gerber, Mike 2020-02-07 18:01:26 +01:00
parent 98aee51801
commit 6b83d5ae1e
2 changed files with 2 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

5
my_ocrd_workflow
View file

@ -17,7 +17,6 @@ do_validate() {
--page-coordinate-consistency off"
ocrd workspace validate $validate_options
# XXX ocrd-tesserocr INCONSISTENCY in TextRegion → use "--page-strictness lax" for now
# XXX INVALIDITY in Glyph ID etc. in GT → --page-coordinate-consistency off
}
do_binarization() {
@ -40,8 +39,6 @@ do_linesegmentation_tesserocr() {
-I OCR-D-IMG-BINPAGE -O OCR-D-SEG-REGION
ocrd-tesserocr-segment-line \
-I OCR-D-SEG-REGION -O OCR-D-SEG-LINE
# XXX compare ocrd-tesserocr-segment* vs tesseract native
}
do_linesegmentation_sbb() {
@ -58,7 +55,7 @@ do_linesegmentation_sbb() {
do_ocr() {
# Perform OCR on the segmented lines
ocrd_tesserocr_recognize_parameters='{ "model": "GT4HistOCR_2000000" }' # TODO mods:language + fontident → model
ocrd_tesserocr_recognize_parameters='{ "model": "GT4HistOCR_2000000" }'
ocrd workspace remove-group -rf OCR-D-OCR-TESS
ocrd-tesserocr-recognize \
-I OCR-D-SEG-LINE -O OCR-D-OCR-TESS \