OS X bash script that turns a collection of images into an OCR'd PDF

img2pdf

#!/bin/sh
#
# img2pdf
#
# OS X bash script that turns a collection of images into an OCR'd PDF
#
# Adapted from http://apple.stackexchange.com/questions/128384/ocr-on-pdfs-in-os-x-with-free-open-source-tools, 
# where it was in turn adapted from
# http://www.morethantechnical.com/2013/11/21/creating-a-searchable-pdf-with-opensource-tools-ghostscript-hocr2pdf-and-tesseract-ocr/
# from http://www.ehow.com/how_6874571_merge-pdf-files-ghostscript.html
# bash tut: http://linuxconfig.org/bash-scripting-tutorial
# Linux PDF,OCR: http://blog.konradvoelkel.de/2013/03/scan-to-pdfa/
# Dealing w/ alpha: http://stackoverflow.com/questions/5083492/problem-with-tesseract-and-tiff-format
#
# Install
#   brew install tesseract --HEAD
#   brew install imagemagick
#   brew install ghostscript
#   chmod +x img2pdf
#
# Usage
#   ./img2pdf *.gif
#
# If you have a mix of extensions:
#   ./img2pdf *.{gif,jpeg}
#

y="`pwd`/$1"
echo Creating a searchable PDF for $y

x=`basename "$y"`
name=${x%.*}

# process each page
for f in $@; do
  echo $f
  echo "\tConverting to TIFF..."
  convert $f -background white -flatten +matte $f.tiff
  echo "\tTesseract OCR..."
  # echo "tesseract -l eng -psm 3 $f.tiff ${f%.*} pdf"
  tesseract -l eng -psm 3 $f.tiff ${f%.*} pdf 1>/dev/null 2>&1
  echo "\tCleanup..."
  rm $f.tiff
  rm ${f%.*}.txt
  mv ${f%.*}.pdf $f.tmp.pdf
done

echo "Combining all pages into a single PDF..."
gs -dCompatibilityLevel=1.4 -dNOPAUSE -dQUIET -dBATCH -dNOPAUSE -q -sDEVICE=pdfwrite -sOutputFile=${name}.searchable.pdf *.tmp.pdf
rm *.tmp.pdf
echo "Created $name.searchable.pdf"