You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
94 lines
2.7 KiB
Bash
94 lines
2.7 KiB
Bash
#!/bin/bash
|
|
|
|
set -e # Abort on error
|
|
|
|
# Configuration
|
|
export LOG_LEVEL=${LOG_LEVEL:-INFO} # /etc/ocrd_logging.py uses this to set level for all OCR-D modules
|
|
export TEXTEQUIV_LEVEL=glyph
|
|
|
|
# Command line parameters
|
|
OPTS=`getopt -o I: --long input-file-grp:,skip-validation -- "$@"`
|
|
eval set -- "$OPTS"
|
|
INPUT_FILE_GRP=OCR-D-IMG
|
|
SKIP_VALIDATION=false
|
|
while true; do
|
|
case "$1" in
|
|
-I|--input-file-grp) INPUT_FILE_GRP=$2; shift 2;;
|
|
--skip-validation) SKIP_VALIDATION=true; shift;;
|
|
|
|
--) shift; break;;
|
|
*) break;;
|
|
esac
|
|
done
|
|
|
|
# Set up logging
|
|
if [ "$LOG_LEVEL" = "DEBUG" -o "$LOG_LEVEL" = "TRACE" ]; then
|
|
set -x
|
|
fi
|
|
|
|
|
|
do_validate() {
|
|
# Validate the workspace
|
|
|
|
# Both ocrd_tesserocr + ocrd_calamari produce segment coordinates that are not strictly within their parent's
|
|
# coordinates:
|
|
#
|
|
# INCONSISTENCY in [...] coords [...] not within parent coords
|
|
#
|
|
# → --page-coordinate-consistency off
|
|
#
|
|
# ocrd_tesserocr sometimes produces segment text results that aren't concatenating as expected by the validator:
|
|
#
|
|
# INCONSISTENCY in [...]: text results '[...]' != concatenated '[...]'
|
|
#
|
|
# → --page-strictness lax
|
|
#
|
|
validate_options='
|
|
--skip dimension
|
|
--skip pixel_density
|
|
--page-strictness lax
|
|
--page-coordinate-consistency off'
|
|
if [ "$SKIP_VALIDATION" = false ]; then
|
|
ocrd workspace validate $validate_options
|
|
fi
|
|
}
|
|
|
|
|
|
main() {
|
|
do_validate
|
|
|
|
|
|
#ocrd-sbb-binarize --overwrite -I $INPUT_FILE_GRP -O OCR-D-IMG-BIN -P model "/var/lib/sbb_binarization"
|
|
ocrd-olena-binarize --overwrite -I $INPUT_FILE_GRP -O OCR-D-IMG-BIN -P impl "sauvola-ms-split"
|
|
do_validate
|
|
|
|
|
|
#ocrd-tesserocr-segment-region --overwrite -I OCR-D-IMG-BIN -O OCR-D-SEG-REGION
|
|
#ocrd-tesserocr-segment-line --overwrite -I OCR-D-SEG-REGION -O OCR-D-SEG-LINE
|
|
#ocrd-cis-ocropy-segment --overwrite -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE -P level-of-operation page
|
|
ocrd-sbb-textline-detector --overwrite -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE -P model "/var/lib/textline_detection"
|
|
do_validate
|
|
|
|
|
|
ocrd-calamari-recognize --overwrite -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI -P checkpoint "/var/lib/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/*.ckpt.json" -P textequiv_level "$TEXTEQUIV_LEVEL"
|
|
ocrd-tesserocr-recognize --overwrite -I OCR-D-SEG-LINE -O OCR-D-OCR-TESS -P model "GT4HistOCR_2000000" -P textequiv_level "$TEXTEQUIV_LEVEL"
|
|
do_validate
|
|
|
|
|
|
for ocr_filegrp in OCR-D-OCR-CALAMARI OCR-D-OCR-TESS; do
|
|
if ocrd workspace list-group | grep -q OCR-D-GT-PAGE; then
|
|
ocrd-dinglehopper --overwrite -I OCR-D-GT-PAGE,$ocr_filegrp -O $ocr_filegrp-EVAL
|
|
fi
|
|
#ocrd-fileformat-transform -I $ocr_filegrp -O ${ocr_filegrp}-ALTO
|
|
done
|
|
}
|
|
|
|
|
|
if [ "$LOG_LEVEL" = "DEBUG" -o "$LOG_LEVEL" = "TRACE" ]; then
|
|
pip list || true
|
|
fi
|
|
main
|
|
|
|
|
|
# vim:tw=120:
|