OCR Scan

#!/bin/sh

SOURCE=""

if [ $# -gt 1 ]
then

SOURCE="--source ADF -l 3"
outname=$2
pbreak=$1

echo "$pbreak" | egrep "[^0-9,]+"
if [ $? -ne 1 ]
then
echo "Check Sequnence List !"
exit 1
fi
else

pbreak=99
outname=$1
SOURCE="--batch-count=1"

fi

startdir=$(pwd)
tmpdir=scan-$RANDOM

cd /tmp
mkdir $tmpdir
cd $tmpdir
echo "################## Scanning ###################"
scanimage -x 210 -y 297 --batch=out%02d.tif --format=tiff --mode Gray --resolution 300 $SOURCE

start=1
cnt=1
sc=$(echo "$pbreak" | cut -d"," -f1-99 --output-delimiter=" " | wc -w)
for pb in $(echo "$pbreak" | cut -d "," -f1-99 --output-delimiter=" ")
do
ende=$(expr $start + $pb - 1)
pnr=0
i=1
echo "############ Page-Sequence ($cnt), Pages: $pb, Start: $start, End: $ende ############"
tpages=""
for page in $(ls out*.tif); do
pnr=$(expr $pnr + 1)
if [ $pnr -ge $start -a $pnr -le $ende ]
then
echo "... Converting"
# increase contrast and reduce colordepth
convert $page -level 15%,85% -depth 2 "b$page"
echo "... OCRing"
tpages="$tpages b$page"
i=$(expr $i + 1)
echo -n " "
tesseract $page $page -l deu
if [ $sc -gt 1 ]
then
cnts=`printf %02d $cnt`
cat $page.txt >> $outname.$cnts.txt
else
cat $page.txt >> $outname.txt
fi

fi
done

echo "... Converting to PDF"
#Use tiffcp to combine output tiffs to a single mult-page tiff
tiffcp $tpages output.tif
#Convert the tiff to PDF
if [ $sc -gt 1 ]
then
cnts=`printf %02d $cnt`
tiff2pdf -z output.tif > $startdir/$outname.$cnts.pdf
mv $outname.$cnts.txt $startdir
else
tiff2pdf -z output.tif > $startdir/$outname.pdf
mv $outname.txt $startdir
fi

start=$(expr $start + $pb)
cnt=$(expr $cnt + 1)

done

cd ..
echo "################ Cleaning Up ################"
rm -rf $tmpdir
cd $startdir

for more that 10 pages change
--batch=out%02d.tif
for
--batch=out%03d.tif