#!/bin/bash
#
# Developed by Fred Weinhaus 8/9/2019 .......... revised 12/21/2023
#
# ------------------------------------------------------------------------------
# 
# Licensing:
# 
# Copyright © Fred Weinhaus
# 
# My scripts are available free of charge for non-commercial use, ONLY.
# 
# For use of my scripts in commercial (for-profit) environments or 
# non-free applications, please contact me (Fred Weinhaus) for 
# licensing arrangements. My email address is fmw at alink dot net.
# 
# If you: 1) redistribute, 2) incorporate any of these scripts into other 
# free applications or 3) reprogram them in another scripting language, 
# then you must contact me for permission, especially if the result might 
# be used in a commercial or for-profit environment.
# 
# My scripts are also subject, in a subordinate manner, to the ImageMagick 
# license, which can be found at: http://www.imagemagick.org/script/license.php
# 
# ------------------------------------------------------------------------------
# 
####
#
# USAGE: shapecompare [-m metric] [-t type] [-T thresh] [-e edgemode] [-i invert] 
# infile1 infile2
#
# USAGE: shapecompare [-h or -help]
# 
# OPTIONS:
# 
# -m     metric       compare difference metric; choices are: sad, said, sand, rssd, all; 
#                     default=sad
# -t     type         type of image to convert input images for compare processing; 
#                     choices are: grayscale (g), binary (b) or outline (o); 
#                     default=grayscale
# -T     thresh       threshold for converting to binary; 0<=thresh<=100 (percent); 
#                     default=50
# -e     edgemode     mode of morphologic edge processing; choices are: edge, edgin or 
#                     edgeout; default=edge
# -i     invert       invert (negate) colors in input image; choices are: yes (y) or 
#                     no (n); default=no
# 
###
# 
# NAME: SHAPECOMPARE 
# 
# PURPOSE: To compares two images' shapes using metrics computed from Hu image moments.
# 
# DESCRIPTION: SHAPECOMPARE compares two images' shapes using metrics computed from 
# Hu Image Moments. Several metrics are available. The image will first be converted 
# to grayscale and can then be converted to binary or an edge outline. The script is 
# designed to work with primarily binary or outline shapes on black backgrounds. 
# However, grayscale shapes on black background or antialiased black/white shapes on 
# black backgrounds should work, also. My analysis (see chart) indicates that outline 
# mode does not work as well as the other two modes.
# 
# 
# ARGUMENTS: 
# 
# -m metric ... METRIC is the compare metric to compute the difference between the two 
# images. Smaller is better than larger. The choices are: sad (sum absolute difference), 
# said (sum absolute inverse difference), sand (sum absolute normalized difference), 
# rssd (root sum squared difference) or all (report all of them). The default=sad.
# 
# The equations for the metrics are:
# SAD = sum( abs(Hu1 - Hu2) )
# SAID = sum( abs(1/Hu1 - 1/Hu2) )
# SAND = sum( abs(Hu1 - Hu2) / sqrt( abs(Hu1*Hu2) ) )
# RSSD = sqrt( sum( (Hu1 - Hu2)^2 ) )
# where there are 7 different (log) Hu image moments that are summed
#
# -t type ... TYPE of image to convert the input images for processing. The choices are: 
# grayscale (g), binary (b) or outline (o). The default=grayscale.
# 
# -T thresh ... THRESH is the threshold for converting to binary. Values are: 
# 0<=thresh<=100 (percent). The default=50.
# 
# -e edgemode. EDGEMODE is the mode of morphologic edge processing. The choices are: 
# edge, edgin or edgeout. Edge will be 2 pixels thick. The other two will be only 
# 1 pixel thick. All 3 use a diamond shaped kernel. The edgein will be on the white 
# side and the edgeout will be on the black side. The default=edge.
# 
# -i invert ... INVERT (negate) the colors in input image as preprocessing. Choices are: 
# yes (y) or no (n). The default=no
# 
# REFERENCE:
# https://www.learnopencv.com/shape-matching-using-hu-moments-c-python/
# 
# CAVEAT: No guarantee that this script will work on all platforms, 
# nor that trapping of inconsistent parameters is complete and 
# foolproof. Use At Your Own Risk. 
# 
######
# 

# set default values
metric="sad"		# sad (sum abs diff), said (sum abs inverse diff), sand (sum abs normalized diff), rssd (root sum squared diff) or all
type="grayscale"	# grayscale (g), binary (b), outline (o)
threshold=50		# threshold percent for binarizing 
edgemode="edge"		# edge mode: edge (e), in (i), out (o)
invert="no"			# invert white <--> black in binary
precision=3         # output score precision (decimal digits)

# set directory for temporary files
dir="."    # suggestions are dir="." or dir="/tmp"
tmpdir="."    # suggestions are tmpdir="." or tmpdir="/tmp"


# set up functions to report Usage and Usage with Description
PROGNAME=`type $0 | awk '{print $3}'`  # search for executable on path
PROGDIR=`dirname $PROGNAME`            # extract directory of program
PROGNAME=`basename $PROGNAME`          # base name of program
usage1() 
	{
	echo >&2 ""
	echo >&2 "$PROGNAME:" "$@"
	sed >&2 -e '1,/^####/d;  /^###/g;  /^#/!q;  s/^#//;  s/^ //;  4,$p' "$PROGDIR/$PROGNAME"
	}
usage2() 
	{
	echo >&2 ""
	echo >&2 "$PROGNAME:" "$@"
	sed >&2 -e '1,/^####/d;  /^######/g;  /^#/!q;  s/^#*//;  s/^ //;  4,$p' "$PROGDIR/$PROGNAME"
	}

# function to report error messages
errMsg()
	{
	echo ""
	echo $1
	echo ""
	usage1
	exit 1
	}


# function to test for minus at start of value of second part of option 1 or 2
checkMinus()
	{
	test=`echo "$1" | grep -c '^-.*$'`   # returns 1 if match; 0 otherwise
    [ $test -eq 1 ] && errMsg "$errorMsg"
	}

# test for correct number of arguments and get values
if [ $# -eq 0 ]
	then
	# help information
   echo ""
   usage2
   exit 0
elif [ $# -gt 12 ]
	then
	errMsg "--- TOO MANY ARGUMENTS WERE PROVIDED ---"
else

metric="sad"		# sad (sum abs diff), said (sum abs inverse diff), sand (sum abs normalized diff), rssd (root sum squared diff) or all
type="grayscale"	# grayscale (g), binary (b), outline (o)
threshold=50		# threshold percent for binarizing 
edgemode="edge"		# edge mode: edge (e), in (i), out (o)
invert="no"			# invert white <--> black in binary


	while [ $# -gt 0 ]
		do
			# get parameter values
			case "$1" in
		  -h|-help)    # help information
					   echo ""
					   usage2
					   exit 0
					   ;;
				-m)    # get  metric
					   shift  # to get the next parameter
					   # test if parameter starts with minus sign 
					   errorMsg="--- INVALID METRIC SPECIFICATION ---"
					   checkMinus "$1"
					   metric=`echo "$1" | tr '[A-Z]' '[a-z]'`
					   case "$metric" in 
					   		sad) ;;
					   		said) ;;
					   		sand) ;;
					   		rssd) ;;
					   		all) ;;
					   		*) errMsg "--- MODE=$metric IS AN INVALID VALUE ---"  ;;
					   esac
					   ;;
				-t)    # get type
					   shift  # to get the next parameter
					   # test if parameter starts with minus sign 
					   errorMsg="--- INVALID TYPE SPECIFICATION ---"
					   checkMinus "$1"
					   type=`echo "$1" | tr '[A-Z]' '[a-z]'`
					   case "$type" in 
					   		grayscale|g) type=grayscale;;
					   		binary|b) type=binary;;
					   		outline|o) type=outline;;
					   		*) errMsg "--- TYPE=$type IS AN INVALID VALUE ---"  ;;
					   esac
					   ;;
				-T)    # get thresh
					   shift  # to get the next parameter
					   # test if parameter starts with minus sign 
					   errorMsg="--- INVALID THRESH SPECIFICATION ---"
					   checkMinus "$1"
					   thresh=`expr "$1" : '\([0-9]*\)'`
					   [ "$thresh" = "" ] && errMsg "--- THRESH=$thresh MUST BE A NON-NEGATIVE INTEGER VALUE (with no sign) ---"
					   test1=`echo "$thresh < 0" | bc`
					   test2=`echo "$thresh > 100" | bc`
					   [ $test1 -eq 1 -o $test2 -eq 1 ] && errMsg "--- THRESH=$thresh MUST BE AN INTEGER BETWEEN 0 AND 100 ---"
					   ;;
				-e)    # get edgemode
					   shift  # to get the next parameter
					   # test if parameter starts with minus sign 
					   errorMsg="--- INVALID EDGEMODE SPECIFICATION ---"
					   checkMinus "$1"
					   edgemode=`echo "$1" | tr '[A-Z]' '[a-z]'`
					   case "$edgemode" in 
					   		edge) ;;
					   		edgein)  ;;
					   		edgeout)  ;;
					   		*) errMsg "--- EDGEMODE=$edgemode IS AN INVALID VALUE ---"  ;;
					   esac
					   ;;
				-i)    # get invert
					   shift  # to get the next parameter
					   # test if parameter starts with minus sign 
					   errorMsg="--- INVALID INVERT SPECIFICATION ---"
					   checkMinus "$1"
					   type=`echo "$1" | tr '[A-Z]' '[a-z]'`
					   case "$invert" in 
					   		yes|y) invert=yes;;
					   		no|n) invert=no;;
					   		*) errMsg "--- INVERT=$invert IS AN INVALID VALUE ---"  ;;
					   esac
					   ;;
				 -)    # STDIN and end of arguments
					   break
					   ;;
				-*)    # any other - argument
					   errMsg "--- UNKNOWN OPTION ---"
					   ;;
		     	 *)    # end of arguments
					   break
					   ;;
			esac
			shift   # next option
	done
	#
	# get infile
	infile1="$1"
	infile2="$2"
fi

# test that infile1 provided
[ "$infile1" = "" ] && errMsg "--- NO INPUT FILE 1 SPECIFIED ---"

# test that infile1 provided
[ "$infile2" = "" ] && errMsg "--- NO INPUT FILE 2 SPECIFIED ---"


dir="$tmpdir/SHAPECOMPARE.$$"

mkdir "$dir" || errMsg "--- FAILED TO CREATE TEMPORARY FILE DIRECTORY ---"
trap "rm -rf $dir; exit 0" 0
trap "rm -rf $dir; exit 1" 1 2 3 15

# set up for invert
if [ "$invert" = "yes" ]; then
	inverting="-negate"
else
	inverting=""
fi

# get im_version
im_version=`convert -list configure | \
	sed '/^LIB_VERSION_NUMBER */!d; s//,/;  s/,/,0/g;  s/,0*\([0-9][0-9]\)/\1/g' | head -n 1`

# set up for IM 7 identify
if [ "$im_version" -ge "07000000" ]; then
	identifying="magick identify"
else
	identifying="identify"
fi

# set up for type
if [ "$type" = "binary" ]; then
	proc="-threshold $thresh%"
elif [ "$type" = "outline" ]; then
	proc="-threshold $thresh% -morphology $edgemode diamond:1"
else
	proc=""
fi

# read infile1 and process to type
# read the input image into the temporary cached image and test if valid
# note: need type palette so identify show binary or edge image as Gray stats, not RGB stats
convert -quiet "$infile1" +repage -alpha off $inverting -colorspace gray $proc -type palette $dir/A1.mpc ||
	errMsg "--- FILE $infile1 DOES NOT EXIST OR IS NOT AN ORDINARY FILE, NOT READABLE OR HAS ZERO size  ---"

# read infile2 and process to type
# read the input image into the temporary cached image and test if valid
# note: need type palette so identify show binary or edge image as Gray stats, not RGB stats
convert -quiet "$infile2" +repage -alpha off -colorspace gray $proc -type palette $dir/A2.mpc ||
	errMsg "--- FILE $infile2 DOES NOT EXIST OR IS NOT AN ORDINARY FILE, NOT READABLE OR HAS ZERO size  ---"

# get first 7 hu moments from I1.mpc
hu_Arr1=(`$identifying -verbose -moments $dir/A1.mpc | sed '/^[ ]*Gray:.*$/,/^[ ]*Channel perceptual hash:.*$/!d' | grep -e "I[0-7]" | awk '{print $2}'`)
#echo "${hu_Arr1[*]}"
num1="${#hu_Arr1[*]}"
#echo $num1

# get first 7 hu moments from I2.mpc
hu_Arr2=(`$identifying -verbose -moments $dir/A2.mpc | sed '/^[ ]*Gray:.*$/,/^[ ]*Channel perceptual hash:.*$/!d' | grep -e "I[0-7]" | awk '{print $2}'`)
#echo "${hu_Arr2[*]}"
num2="${#hu_Arr2[*]}"
#echo $num2


# test if same number of moments and both equal to 7 moments
[ $num1 -ne 7 ] && echo "--- INCONSISTENT NUMBER OF HU MOMENTS FOR INFILE 1 ---"
[ $num2 -ne 7 ] && echo "--- INCONSISTENT NUMBER OF HU MOMENTS FOR INFILE 2 ---"


# convert hu moments to log form as HU=-sign(hu)*log(abs(hu))
for ((i=0; i<7; i++)); do
	hu1="${hu_Arr1[$i]}"
	HU_Arr1[$i]=`convert xc: -format "%[fx:-(sign($hu1))*log(abs($hu1))]\n" info:`
	hu2="${hu_Arr2[$i]}"
	HU_Arr2[$i]=`convert xc: -format "%[fx:-(sign($hu2))*log(abs($hu2))]\n" info:`
done

if [ "$metric" = "sad" -o "$metric" = "all" ]; then
	metric1="sad"
	score=0
	for ((i=0; i<7; i++)); do
		HU1="${HU_Arr1[$i]}"
		HU2="${HU_Arr2[$i]}"
		score=`convert xc: -format "%[fx:$score + abs($HU1-($HU2))]\n" info:`
		#echo "$i; HU1=$HU1; HU2=$HU2; score=$score;"
	done
	score=`echo "$score" | awk '{printf("%0.3f",$0);}'`
	echo "Metric=$metric1 Score=$score"
fi

if [ "$metric" = "said" -o "$metric" = "all" ]; then
	metric1="said"
	score=0
	for ((i=0; i<7; i++)); do
		HU1="${HU_Arr1[$i]}"
		HU2="${HU_Arr2[$i]}"
		score=`convert xc: -format "%[fx:$score + abs((1/($HU1))-(1/($HU2)))]\n" info:`
		#echo "$i; HU1=$HU1; HU2=$HU2; score=$score"
	done
	score=`echo "$score" | awk '{printf("%0.3f",$0);}'`
	echo "Metric=$metric1 Score=$score"
fi

if [ "$metric" = "sand" -o "$metric" = "all" ]; then
	metric1="sand"
	score=0
	for ((i=0; i<7; i++)); do
		HU1="${HU_Arr1[$i]}"
		HU2="${HU_Arr2[$i]}"
		score=`convert xc: -format "%[fx:$score + abs($HU1-($HU2))/sqrt(abs($HU1)*abs($HU2))]\n" info:`
		#echo "$i; HU1=$HU1; HU2=$HU2; score=$score"
	done
	score=`echo "$score" | awk '{printf("%0.3f",$0);}'`
	echo "Metric=$metric1 Score=$score"
fi

if [ "$metric" = "rssd" -o "$metric" = "all" ]; then
	metric1="rssd"
	score=0
	for ((i=0; i<7; i++)); do
		HU1="${HU_Arr1[$i]}"
		HU2="${HU_Arr2[$i]}"
		score=`convert xc: -format "%[fx:$score + ($HU1-($HU2))^2]\n" info:`
		#echo "$i; HU1=$HU1; HU2=$HU2; score=$score"
	done
	score=`convert xc: -format "%[fx:sqrt($score)]\n" info:`
	score=`echo "$score" | awk '{printf("%0.3f",$0);}'`
	echo "Metric=$metric1 Score=$score"
fi

exit 0