root/hodgestar/Scripts/ocr-book

# scan pages
for i in $(seq --format=%003.f 1 150); do
  echo Prepare page $i and press Enter
  read
  scanimage --device 'brother2:bus1;dev1' --format=pnm --mode 'True Gray' --resolution 300 -l 90 -t 0 -x 210 -y 200 --brightness -20 --contrast 15 >scan-$i.pnm
done

# unpaper scans
for i in $(seq --format=%003.f 1 150); do
  echo preparing page $i
  unpaper scan-$i.pnm unpapered-$i
  convert unpapered-$i.pnm prepared-$i.tif && rm unpapered-$i.pnm
done

# tesseract
# (GOCR and Ocrad are crap)
for i in $(seq --format=%003.f 1 150); do
  echo doing OCR on page $i
  tesseract prepared-$i.tif tesseract-$i -l eng
done

# remove page numbers
for i in $(seq --format=%003.f 1 150); do
  tail -n +2 tesseract-$i.txt >text-$i.txt
done

# newlines to spaces
tr '\n' ' '
# only one space character at a time
sed 's/[[:blank:]]{2,}/ /'