tesseract_pdftk.sh

pdftk infile.pdf burst output $tmpdir/page_%03d.pdf
page=0
imagetype="png"

for file in $tmpdir/*.pdf
do 
    image=$file.$imagetype
    convert -density $density -depth $depth $file $image
    rm $file
    page=`expr $page + 1`
    tessoptions="--tessdata-dir "$tessdatadir" -l "$language" pdf"
    tesseract $image $image $tessoptions
    rm $image
done

pdftk $tmpdir/*.pdf cat output $tmpdir/tmp.pdf