USB 스캐너에서 페이지를 스캔하십시오. PDF로 OCR에 tesseract를 사용하십시오. 여러 페이지를 하나의 PDF로 병합합니다. 사용법 : scan2PDF outputfilename number_of_pages
#!/bin/bash
#scan2PDF
#Requires: tesseract 3.03 for OCR to PDF
# scanimage for scanning, I use 1.0.24
# pdfunite to merge multiple PDF into one, I use 0.26.5
#
# Use scanimage -L to get a list of devices.
# e.g. device `genesys:libusb:006:003' is a Canon LiDE 210 flatbed scanner
# then copy/paste genesys:libusb:006:003 into SCANNER below.
# play with CONTRAST to get good images
DPI=300
TESS_LANG=nor #Language that Tesseract uses for OCR
SCANNER=genesys:libusb:006:003 #My USB scanner
CONTRAST=35 #Contrast to remove paper look
FILENAME=$1 #Agrument 1,filename
PAGES=$2 #Argument 2, number of pages
re='^[0-9]+$' #Check if second argument is a number
if ! [[ ${PAGES} =~ $re ]] ; then
echo "error: Usage: $0 filename number_of_pages" >&2; exit 1
fi
SCRIPT_NAME=`basename "$0" .sh` #Directory to store temporary files
TMP_DIR=${SCRIPT_NAME}-tmp
if [ -d ${TMP_DIR} ] #Check if it exists a directory already
then
echo Error: The directory ${TMP_DIR} exists.
exit 2
fi
mkdir ${TMP_DIR} #Make and go to temp dir
cd ${TMP_DIR}
echo Starts Scanimage...
scanimage -d ${SCANNER} --format=tiff --mode Color --resolution ${DPI} -p --contrast ${CONTRAST} --batch-start=1 --batch-count=${PAGES} --batch-prompt
echo Starts Tesseract OCR
for file in *.tif #Goes through every tif file in temp dir
do
tesseract $file ${file%.tif} -l ${TESS_LANG} pdf
done
if [ "$PAGES" = "1" ] #How many pages
then
cp out1.pdf ../${FILENAME}.pdf #Only one page, just copy the PDF back
else
for file in *.pdf #More pages, merge the pages into one PDF and copy back
do
pdfuniteargs+=${file}
pdfuniteargs+=" "
done
pdfunite $pdfuniteargs ../${FILENAME}.pdf
fi
echo ${FILENAME}.pdf done
rm * #Done, clean up
cd ..
rmdir ${TMP_DIR}
