diff options
Diffstat (limited to 'local/bin/ocrthis.sh')
| -rwxr-xr-x | local/bin/ocrthis.sh | 20 |
1 files changed, 0 insertions, 20 deletions
diff --git a/local/bin/ocrthis.sh b/local/bin/ocrthis.sh deleted file mode 100755 index 3010a6a..0000000 --- a/local/bin/ocrthis.sh +++ /dev/null @@ -1,20 +0,0 @@ -#!/bin/bash - -# Creates and OCR PDF out of an image -# (OCR limited to printed characters (handwriting or photograph OCR is bad, if -# any) -# -# Alternatively use `tesseract FILE text` - -if [ $# -ne 1 ]; then - echo "Usage: $(basename "$0") input_file" - # (there is `basename` and `dirname`) - exit 1 -fi - -b="$(basename "$1")" -convert "$1" "${b}.pdf" -# TODO: some contrast enhancement step would help. If text has low contrast -# with background (e.g., blue on black, green on black), then OCR fails. -ocrmypdf "${b}.pdf" "${b}.ocr.pdf" -mv -f "${b}.ocr.pdf" "${b}.pdf" |
