Install/configure tesseract for EC2 instance

install_ec2_tesseract.sh

#!/bin/bash

# for Ubuntu 12.04/12.10

sudo apt-get update
sudo apt-get -y install autoconf automake make buildessential
sudo apt-get -y install tesseract-ocr tesseract-ocr-eng imagemagick
# install parallel
(wget -O - pi.dk/3 || curl pi.dk/3/ || fetch -o - http://pi.dk/3) | bash
# convert PDF to TIFF
find . -name '*.pdf' | /home/ubuntu/bin/parallel --gnu -j $NUMCORES convert  -background white +matte -depth 8 -density 200 {}[0-19] {}.tif

find . -name '*.tif' | /home/ubuntu/bin/parallel --gnu -j $NUMCORES tesseract -l eng {} {}