De-duplicate JPG Files

dedup.sh

#!/bin/bash

PATH_TO_PROCESS="./"
if [ $# -ge 1 ]; then
    PATH_TO_PROCESS=${1}
fi

JPEG_QUALITY=80
if [ $# -ge 2 ]; then
    JPEG_QUALITY=${2}
fi

IMPROVEMENT_THRESHOLD=1
if [ $# -ge 3 ]; then
    IMPROVEMENT_THRESHOLD=${3}
fi

find $PATH_TO_PROCESS -type f -iname '*.jpg' -exec jpegoptim -p -P --max=$JPEG_QUALITY --threshold=$IMPROVEMENT_THRESHOLD --strip-all {} +
fdupes -rn1 $PATH_TO_PROCESS | sed -e 's/\(\w\) /\1|/g' -e 's/|$//' > files
while read line; do
        IFS='|' read -a arr <<< "$line"
        orig=${arr[0]}
        for ((i = 1; i < ${#arr[@]}; i++)); do
                file="${arr[$i]}"
                ln -sf "$orig" "$file"
        done 
done < files