mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-12-03 00:49:01 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Merge pull request #2494 from Shreeshrii/master

Browse Source 
Allow saving of box/tiff pairs during legacy tesseract training
This commit is contained in:
zdenop 2019-06-14 20:44:49 +02:00 committed by GitHub
commit fad96db497
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
src/training/tesstrain_utils.sh
View File

@ -259,7 +259,7 @@ generate_font_image() {
common_args+=" --char_spacing=${CHAR_SPACING} --exposure=${EXPOSURE}"
common_args+=" --outputbase=${outbase} --max_pages=${MAX_PAGES}"
if $DISTORT_IMAGE; then
common_args+=" --distort_image "
common_args+=" --distort_image --invert=false"
fi
# add --writing_mode=vertical-upright to common_args if the font is
@ -326,6 +326,17 @@ phase_I_generate_image() {
check_file_readable ${outbase}.box ${outbase}.tif
done
done
if $SAVE_BOX_TIFF && ( ! $LINEDATA ) ; then
tlog "\n=== Saving box/tiff pairs for training data ==="
for f in "${TRAINING_DIR}/${LANG_CODE}".*.box; do
tlog "Moving ${f} to ${OUTPUT_DIR}"
cp "${f}" "${OUTPUT_DIR}"
done
for f in "${TRAINING_DIR}/${LANG_CODE}".*.tif; do
tlog "Moving ${f} to ${OUTPUT_DIR}"
cp "${f}" "${OUTPUT_DIR}"
done
fi
}
# Phase UP : Generate (U)nicharset and (P)roperties file.
@ -573,6 +584,7 @@ make__lstmdata() {
mv "${f}" "${OUTPUT_DIR}"
done
fi
tlog "\n=== Moving lstmf files for training data ==="
for f in "${TRAINING_DIR}/${LANG_CODE}".*.lstmf; do
tlog "Moving ${f} to ${OUTPUT_DIR}"