diff options
Diffstat (limited to 'bin/kapurthresh')
| -rw-r--r-- | bin/kapurthresh | 329 |
1 files changed, 329 insertions, 0 deletions
diff --git a/bin/kapurthresh b/bin/kapurthresh new file mode 100644 index 0000000..c025ae9 --- /dev/null +++ b/bin/kapurthresh @@ -0,0 +1,329 @@ +#!/bin/bash +# +# Developed by Fred Weinhaus 10/29/2008 .......... revised 11/3/2015 +# +# ------------------------------------------------------------------------------ +# +# 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: kapurthresh [-g graph] infile outfile +# USAGE: kapurthresh [-help] +# +# OPTIONS: +# +# -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: KAPURTHRESH +# +# PURPOSE: To automatically thresholds an image to binary (b/w) format +# using Kapur's entropy technique. +# +# DESCRIPTION: KAPURTHRESH 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 Kapur 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: +# +# -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_kapur.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 +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 4 ] + 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 + ;; + -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_kapur.gif + +tmpA1="$dir/kapurthresh_1_$$.mpc" +tmpA2="$dir/kapurthresh_1_$$.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 kapurthresh. +# with IM 6.6.0.10, 6.7.2.10, 6.7.3.10, 6.7.4.10, 6.7.6.10, 6.7.7.6, 6.7.7.7, 6.7.8.10 +# Note: some images (esp. b/w) do not work for older versions. +# There seems to be a bug sometime between IM 6.7.2.10 and 6.7.3.10 through 6.7.7.7, which I cannot seem to fix +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` + + + # get value array from IM histogram + valueArr=(`convert $tmpA1 -depth 8 -format "%c" -define histogram:unique-colors=true histogram:info:- \ + | tr -cs '0-9\012' ' ' | sed -n 's/[ ]*\([0-9]*\)[ ]*\([0-9]*\).*$/\1 \2/p' |\ + awk ' + # AWK + { vbin[$2] += $2;} + END { for (i=0;i<256;i++) {print vbin[i]; } } '`) +# echo ${valueArr[*]} +# echo ${#valueArr[*]} + numvals=${#valueArr[*]} + + # get count array from IM histogram + countArr=(`convert $tmpA1 -depth 8 -format "%c" -define histogram:unique-colors=true histogram:info:- \ + | tr -cs '0-9\012' ' ' | sed -n 's/[ ]*\([0-9]*\)[ ]*\([0-9]*\).*$/\1 \2/p' |\ + awk ' + # AWK + { cbin[$2] += $1; } + END { for (i=0;i<256;i++) {print cbin[i]; } } '`) +# echo ${countArr[*]} +# echo ${#countArr[*]} + numcounts=${#countArr[*]} + + [ $numvals -ne $numcounts ] && errMsg "--- NUMBER OF COUNTS IS NOT THE SAME AS NUMBER OF VALUES ---" + + # compute normalized count array + ncountArr=( $(for ((i=0; i<$numcounts; i++)); do + echo "$i ${countArr[$i]}" + done |\ + awk -v totpix="$totpix" -v numcounts="$numcounts" ' + # AWK + { bin[$1] = $2; } + END { for (i=0;i<numcounts;i++) {print bin[i]/totpix; } } ') ) +# echo ${ncountArr[*]} +# echo ${#ncountArr[*]} + + # compute elowArr + elowArr=( $(for ((i=0; i<$numcounts; i++)); do + echo "$i ${ncountArr[$i]}" + done |\ + awk -v numcounts="$numcounts" ' + # AWK to generate a cumulative histogram 1D image... + { ncbin[$1] = $2; nlow += $2; nlowbin[$1] = nlow; qlow += $2*log($2); qlowbin[$1] = qlow;} + END { for (i=0;i<numcounts;i++) {if (ncbin[i]!=0) {elowbin[i]=log(nlowbin[i]) - qlowbin[i]/nlowbin[i]} else {elowbin[i]=0}; print elowbin[i] } } ') ) +# echo ${elowArr[*]} +# echo ${#elowArr[*]} + + # compute ehighArr + ehighArr=( $(for ((i=0; i<$numcounts; i++)); do + j=`expr $numcounts - 1 - $i` + echo "$j ${ncountArr[$j]}" + done |\ + awk -v numcounts="$numcounts" ' + # AWK to generate a cumulative histogram 1D image... + { ncbin[$1] = $2; nhigh += $2; nhighbin[$1] = nhigh; qhigh += $2*log($2); qhighbin[$1] = qhigh;} + END { for (i=0;i<numcounts;i++) {if (ncbin[i]!=0) {ehighbin[i]=log(nhighbin[i]) - qhighbin[i]/nhighbin[i]} else {ehighbin[i]=0}; print ehighbin[i] } } ') ) +# echo ${ehighArr[*]} +# echo ${#ehighArr[*]} + + # compute threshold + threshbin=$(for ((i=0; i<$numcounts; i++)); do + echo "$i ${elowArr[$i]} ${ehighArr[$i]}" + done |\ + awk -v numcounts="$numcounts" -v teold=0 -v threshbin=0 ' + # AWK to compute entropy threshold... + { tebin[$1] = ($2 + $3); } + END { for (i=0;i<numcounts;i++) { if (tebin[i]>teold) {teold=tebin[i]; threshbin=i}; } print threshbin } ') +# echo "threshbin=$threshbin" + thresh=${valueArr[$threshbin]} +# echo "thresh=$thresh" + threshpct=`convert xc: -format "%[fx:100*$thresh/255]" info:` + + + +# 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 + + + |