#!/bin/bash
#
# Developed by Fred Weinhaus 10/29/2008 .......... revised 1/18/2020
#
# ------------------------------------------------------------------------------
# 
# 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: sahoothresh [-p power] [-g graph] infile outfile
# USAGE: sahoothresh [-help]
#
# OPTIONS:
#
# -p      power             power or exponent to use with method=4
#                           float; power>0; default=2
# -g	  graph             graph specifies whether to generate a 
#                           histogram graph image displaying the 
#                           location and value of the threshold;
#                           choices are: view or save; 
#                           default is no graph
#
###
#
# NAME: SAHOOTHRESH
# 
# PURPOSE: To automatically thresholds an image to binary (b/w) format 
# using Sahoo's technique.
# 
# DESCRIPTION: SAHOOTHRESH automatically thresholds an image to binary
# (b/w) format. It assume the histogram is bimodal, i.e. is the composite
# of two bell-shaped distributions representing the foreground and 
# background classes. The Sahoo appoach computes computes one measure of  
# Entropy for each of the foreground (above threshold data) and background 
# (at and below threshold value) classes. The optimal threshold is the one  
# that maximizes the Sum of the Foreground and Background Entropies.
# 
# OPTIONS: 
# 
# -p power ... POWER is the exponent used in method 4. The value for 
# power may be a float greater than zero. The default is 2.
# 
# -g graph ... GRAPH specifies whether to generate a graph (image) of 
# the histogram, displaying the location and value of the threshold. 
# The choices are: view, save and none. If graph=view is selected, the 
# graph will be created and displayed automatically, but not saved. 
# If graph=save is selected, then the graph will be created and saved 
# to a file using the infile name, with "_histog_sahoo.gif" appended,  
# but the graph will not be displayed automatically. If -g option is 
# not specified, then no graph will be created.
# 
# NOTE: It is highly recommended that the output not be specified 
# as a JPG image as that will cause compression and potentially a 
# non-binary (i.e. a graylevel) result. GIF is the recommended 
# output format.
# 
# REFERENCES: see the following:
# http://climate.gsfc.nasa.gov/publications/fulltext/RSEpaper.pdf
# http://www.istanbul.edu.tr/eng/ee/jeee/main/pages/issues/is62/62008.pdf
# 
# 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
pow=2			#pow>0 and cannot equal 1 exactly
graph=""		#none, save or view

# set directory for temporary files
dir="."    # suggestions are dir="." or dir="/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 6 ]
	then
	errMsg "--- TOO MANY ARGUMENTS WERE PROVIDED ---"
else
	while [ $# -gt 0 ]
		do
			# get parameter values
			case "$1" in
		  -h|-help)    # help information
					   echo ""
					   usage2
					   exit 0
					   ;;
				-p)    # get power
					   shift  # to get the next parameter
					   # test if parameter starts with minus sign 
					   errorMsg="--- INVALID POWER SPECIFICATION ---"
					   checkMinus "$1"
					   pow=`expr "$1" : '\([.0-9]*\)'`
					   [ "$pow" = "" ] && errMsg "--- POWER=$pow MUST BE A NON-NEGATIVE FLOAT ---"
					   powtest=`echo "$pow <= 0" | bc`
					   [ $powtest -eq 1 ] && errMsg "--- POWER=$pow MUST BE A POSITIVE FLOAT ---"
					   ;;
				-g)    # get  graph
					   shift  # to get the next parameter
					   # test if parameter starts with minus sign 
					   errorMsg="--- INVALID GRAPH SPECIFICATION ---"
					   checkMinus "$1"
					   graph="$1"
					   [ "$graph" != "view" -a "$graph" != "save" ] && errMsg "--- GRAPH=$graph MUST BE EITHER VIEW OR SAVE ---"
					   ;;
				 -)    # STDIN and end of arguments
					   break
					   ;;
				-*)    # any other - argument
					   errMsg "--- UNKNOWN OPTION ---"
					   ;;
		     	 *)    # end of arguments
					   break
					   ;;
			esac
			shift   # next option
	done
	#
	# get infile and outfile
	infile="$1"
	outfile="$2"
fi

# test that infile provided
[ "$infile" = "" ] && errMsg "NO INPUT FILE SPECIFIED"

# test that outfile provided
[ "$outfile" = "" ] && errMsg "NO OUTPUT FILE SPECIFIED"

# get outname from infile to use for graph
inname=`convert $infile -format "%t" info:`
histfile=${inname}_histog_sahoo.gif

tmpA1="$dir/sahoothresh_1_$$.mpc"
tmpA2="$dir/sahoothresh_1_$$.cache"
trap "rm -f $tmpA1 $tmpA2; exit 0" 0
trap "rm -f $tmpA1 $tmpA2 $histfile; exit 1" 1 2 3 15

# 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`

# colorspace RGB and sRGB swapped between 6.7.5.5 and 6.7.6.7 
# though probably not resolved until the latter
# then -colorspace gray changed to linear between 6.7.6.7 and 6.7.8.2 
# then -separate converted to linear gray channels between 6.7.6.7 and 6.7.8.2,
# though probably not resolved until the latter
# so -colorspace HSL/HSB -separate and -colorspace gray became linear
# but we need to use -set colorspace RGB before using them at appropriate times
# so that results stay as in original script
# The following was determined from various version tests using sahoo thresh.
# with IM 6.6.0.10, 6.7.4.10, 6.7.6.10, 6.7.5.5, 6.7.5.6, 6.7.5.7, 6.7.8.10
# Note: some images (esp. flower) do not work the same as the examples for versions greater than 6.7.5.6.
# There seems to be a bug 6.7.5.6, which I cannot seem to fix. But it appears very slightly different.
if [ "$im_version" -lt "06070607" -o "$im_version" -gt "06070707" ]; then
	setcspace="-set colorspace RGB"
else
	setcspace=""
fi
# no need for setcspace for grayscale or channels after 6.8.5.4
if [ "$im_version" -gt "06080504" ]; then
	setcspace=""
fi


if convert -quiet "$infile" $setcspace -colorspace gray +repage "$tmpA1"
	then
	: ' do nothing '
else
	errMsg "--- FILE $infile DOES NOT EXIST OR IS NOT AN ORDINARY FILE, NOT READABLE OR HAG ZERO SIZE ---"
fi	

# get totpix in image
width=`convert $tmpA1 -format "%w" info:`
height=`convert $tmpA1 -format "%h" info:`
totpix=`echo "scale=0; $width * $height / 1" | bc`

# function to convert IM histogram into two arrays, value and count
getHistog()
	{
	echo "Generate Histogram"
	img="$1"
	# get lists of values and counts from histogram
	# note that IM histograms are not well sorted (and have multiple bins with counts for the same values)
	value=`convert $img -depth 8 -format %c -define histogram:unique-colors=true histogram:info: | sed -n 's/[ ]*\([0-9]*\).*gray[(]\([0-9]*\).*$/\1 \2/p' | sort -k 2 -b -n | awk '{print $2}'`
	count=`convert $img -depth 8 -format %c -define histogram:unique-colors=true histogram:info: | sed -n 's/[ ]*\([0-9]*\).*gray[(]\([0-9]*\).*$/\1 \2/p' | sort -k 2 -b -n | awk '{print $1}'`
	
	# put value and count into arrays
	valueArr=($value)
	countArr=($count)
	
	# check if both arrays are the same size
	if [ ${#valueArr[*]} -ne ${#countArr[*]} ]
		then
			errMsg "--- ARRAY SIZES DO NOT MATCH ---"
			exit 1
		else
		numbins=${#valueArr[*]}
#echo "numbins=$numbins"
	fi
}

# function to normalize histog
getNormlizedHistog()
	{
	echo "Normalize Histogram"
	j=0
	while [ $j -lt $numbins ]; do
		countArr[$j]=`echo "scale=10; ${countArr[$j]}/$totpix" | bc`
		j=`expr $j + 1`
	done
	}


# process image using Kapur's approach

echo ""
getHistog "$tmpA1"
getNormlizedHistog
[ "$pow" = "1" ] && pow=0.999999

echo "Generate Cumulative Arrays"
# p=c(i)/N (normalized count or probability, p, at bin i)
# t=threshold bin
# n=p0=sum(c(i)/N)zeroth histogram moment => cumulative normalized count (from i=0 to t) = N(t)
# entropy=ln(sum((p/n)^pow))=ln(sum(p^pow)/n^pow)=ln(r/n^pow)=ln(r)-ln(n^pow)
# b^x=e^(x*ln(b)); law of base change in raising number to power

i=0
nlow=0
nhigh=0
rlow=0
rhigh=0
# test if integer; returns 1 if integer and 0 if not integer
test=`convert xc: -format "%[fx:($pow-floor($pow))==0?1:0]" info:`
while [ $i -lt $numbins ]; do
	if [ $test -eq 0 ]; then
		nlow=`echo "scale=10; $nlow + ${countArr[$i]}" | bc`
		nlowArr[$i]=`echo "scale=10; e($pow*l($nlow))" | bc -l`
		rlow=`echo "scale=10; $rlow + e($pow*l(${countArr[$i]}))" | bc -l`
		rlowArr[$i]=$rlow
		j=`expr $numbins - $i - 1`
		nhigh=`echo "scale=6; $nhigh + ${countArr[$j]}" | bc`
		nhighArr[$i]=`echo "scale=10; e($pow*l($nhigh))" | bc -l`
		rhigh=`echo "scale=10; $rhigh + e($pow*l(${countArr[$j]}))" | bc -l`
		rhighArr[$i]=$rhigh
	else
		nlow=`echo "scale=10; $nlow + ${countArr[$i]}" | bc`
		nlowArr[$i]=`echo "scale=10; $nlow^$pow" | bc`
		rlow=`echo "scale=10; $rlow + (${countArr[$i]})^$pow" | bc`
		rlowArr[$i]=$rlow
		j=`expr $numbins - $i - 1`
		nhigh=`echo "scale=6; $nhigh + ${countArr[$j]}" | bc`
		nhighArr[$i]=`echo "scale=10; $nhigh^$pow" | bc`
		rhigh=`echo "scale=10; $rhigh + (${countArr[$j]})^$pow" | bc`
		rhighArr[$i]=$rhigh
	fi
#echo "i=$i; j=$j; nlow=${nlowArr[$i]}; nhigh=${nhighArr[$i]}; rlow=${rlowArr[$i]}; rhigh=${rhighArr[$i]}"
	i=`expr $i + 1`
done


echo "Compute Threshold"
# loop through histogram
# compute threshold by maximizing total low and high class entropies
# te=El+Eh

i=0
teold=0
threshbin=0
lastbin=`expr $numbins - 1`
frac=`echo "scale=10; 1/(1 - $pow)" | bc`
#echo "frac=$frac"
while [ $i -lt $lastbin ]; do
	j=`expr $lastbin - $i - 1`
	nlow=${nlowArr[$i]}
	nhigh=${nhighArr[$j]}
	rlow=${rlowArr[$i]}
	rhigh=${rhighArr[$j]}
	te=`echo "scale=10; $frac*(l($rlow) -l($nlow) + l($rhigh) -l($nhigh)) / 1" | bc -l`
	test=`echo "$te > $teold" | bc`
	if [ $test -eq 1 ]; then
		teold=$te
		threshbin=$i
	fi
#echo "i=$i; rlow=$rlow; rhigh=$rhigh; te=$te; teold=$teold; test=$test; threshbin=$threshbin"
	i=`expr $i + 1`
done
thresh=${valueArr[$threshbin]}


# compute threshold graph x coord and threshold in percent
xx=$thresh
threshpct=`convert xc: -format "%[fx:100*$thresh/255]" info:`
#echo "xx=$xx; threshpct=$threshpct"


echo "Thresholding Image At $threshpct%"
convert $tmpA1 -threshold $threshpct% "$outfile"
echo ""


if [ "$graph" != "" ]; then
	convert $tmpA1 -define histogram:unique-colors=false histogram:- | \
		convert - -negate \
		-stroke red -strokewidth 1 -draw "line $xx,0 $xx,200" \
		-background gray -splice 0x30 \
		-fill white -stroke white -strokewidth 1 \
		-font ArialB -pointsize 24 \
		-draw "text 4,22 'threshold=$threshpct%'" -resize 50% \
		-bordercolor gray50 -border 5 \
		$histfile
fi

if [ "$graph" = "view" ]; then
	convert $histfile x:
	rm -f $histfile
fi

exit 0