#!/bin/bash # # Developed by Fred Weinhaus 6/25/2014 .......... revised 2/14/2022 # # ------------------------------------------------------------------------------ # # 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: kmeans [-n numcolors] [-s seedcolors] [-m maxiters] [-c convergence] [-a area] # [-t type] [-C colorspace] [-b bgcolor] [-v view] [-A adjoin] [-k compression] # infile outfile # USAGE: kmeans [-h or -help] # # OPTIONS: # # -n numcolors number of colors to use as seeds; integer>1; default=5 # -s seedcolors list of seed colors rather than selecting a number of # colors; space separate list of opaque color; default # is to use the number of colors # -m maxiters maximum number of iterations before stopping; # integer>0; default=40 # -c convergence minimum rmse (times 100) between previous and current # set of colors to stop iterating; default=0.05 # -a area largest pixel area of a cluster to be merged into # its background; integer>=0; default=0 (no merging) # -t type type of output; choices are flattened (f) or # layered (l); default=flattened # -C colorspace colorspace in which to do processing; default=sRGB # -b bgcolor color to put under any transparency; any valid opaque # color is allowed; default is no change of color # -v view hexcolors (only), swatches (and hex colors), # progress (and hex colors), all (progress, hexcolors # swatches) and dominant (dominant color). # -A adjoin adjoin layered output images into a single multi-page # image; choices are: yes (y) or no (n); default=yes # -k compression compression type if saved to tif; choices are: none (n), # lzw (l), or zip (z); default=zip # ### # # NAME: KMEANS # # PURPOSE: To apply k-means color reduction to an image. # # DESCRIPTION: KMEANS applies k-means color reduction to an image. This is a # colorspace clustering or segmentation technique. The user must specify either # a number of desired final colors or a set of initial seed colors. If a list # of seed colors is not provided, then seed colors will be estimated using IM # -colors (color quantization). The algorithm uses the seed colors to group # (cluster) each pixel in the image according to the smallest rmse value to # each seed color. Then it computes the new mean colors from the clusters. # This process iterates until either the convergence value is reached or the # maximum number of iterations is reached. The script is limited to fully # opaque images for type=layered. If type=flattened, then the input may have # and alpha channel that will be remove for processing and added back at the # end. Optionally, connected components labeling may be use to remove small # isolated clusters for IM versions 6.8.9-10 or later. The final list of # colors will be sorted by histogram count so that the first color in the # list will be the dominant color in the image. # # OPTIONS: # # -n numcolors ... NUMCOLORS is the number of colors to use as seeds. Values # are integer>1. The default=5. # # -s seedcolors ... SEEDCOLORS is a space delimited list of opaque seed colors. # It is used rather than just selecting a given number of colors. Providing a # well selected list of colors can make the iteration process quicker. Any # valid set of opaque IM colors may be used. This includes rgb, hex or color # names. However, there must not be any spaces in the color, especially for rgb # color definitions. The default is to just use the desired number of colors. # # -m maxiters ... MAXITERS is the maximum number of iterations before stopping. # Values are integer>0. The default=40 # # -c convergence ... CONVERGENCE is the minimum rmse (times 100) between the # previous and current set of colors to stop iterating. Values are floats>=0. # Larger convergence values will run faster and converge to slightly different # colors. The default=0.05, but runs rather slow due to many iterations. # A value of 0.3 will run much faster with much fewer iterations, though the # colors will be slightly different and thus the clusters will be different. # # -a area ... AREA is the largest pixel area of a cluster to be merged into # its surrounding or largest neighboring cluster (color). Any cluster of this # area or smaller will be merged. Value are integers>=0. The default=0 is no # merging. # # -t type ... TYPE of output image. The choices are flattened (f) or # layered (l). The default=flattened. Note the format of the output must be # either GIF or TIF or TIFF to support the multi-page layered option, unless # -A adjoin is set to no. Suffixes may be all upper case or all lower case. # If other formats are used, then multiple output images will be created rather # than a layered image. # # -C colorspace ... COLORSPACE in which to do processing; default=sRGB; other # colorspaces that do well are YCbCr and LAB. # # -b bgcolor ... BGCOLOR is the backgrouond color to put under any transparency. # Any valid opaque color is allowed. The default is no change of color. # # -v view ... VIEW permits one to list to the terminal or display any of the # following options: hexcolors, swatches (and hex colors), progress (and hex # colors), all (progress, hexcolors swatches) and dominant (dominant color). # Hexcolors will list to the terminal for both the initial seed and # final cluster colors in hex notation. The final colors will be sorted by # histogram count with the first color the dominant color in the resulting # image. Swatches will display the initial and final cluster colors as images # to the display. It will also list the hex colors to the terminal. Progress # will list each iteration and rmse value to the terminal in addition to the # list of initial and final hex colors. All will do all of the above. Dominant # will list only the hexcolor value of the dominant color in the image. The # default is none of the above. Note that hexcolors and swatches will be # presented in the working colorspace and not converted to sRGB. # # -A adjoin ... ADJOIN layered output images into a single multi-page image. # The choices are: yes (y) or no (n). The default=yes. # # -k compression ... COMPRESSION type if saved to tif. The choices are: none (n), # lzw (l), or zip (z); default=zip # # REQUIREMENTS: IM version 6.8.9-10 or higher to use option -a with connected # components labeling to remove small isolated clusters. # # References: # http://en.wikipedia.org/wiki/Kmeans # # NOTE: the script may be slow due to its iterative nature. Also GIF files # cannot be made transparent in IM 6.9.1.7. # # 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 numcolors="5" # number of colors to use as seeds; corresponds to k in k-means seedcolors="" # use this list of colors for seeds rather than selecting a number of colors maxiters=40 # maximum number of iterations; stops if reaches this limit convergence=0.05 # minimum rmse between previous and current set of colors; if rmse at some iteration is smaller, then stop; usually stops at 0% before reaching this value or maxiters area=0 # maximum area to be merged into its surrounding/neighboring cluster type="flattened" # type of output; flattened or layered colorspace="sRGB" # working colorspace bgcolor="" # background color to put under transparency view="" # hexcolors (only), swatches (and hex colors), progress (and hex colors), all adjoin="yes" compression="zip" # set directory for temporary files 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 22 ] 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 ;; -n) # get numcolors shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID NUMCOLORS SPECIFICATION ---" checkMinus "$1" numcolors=`expr "$1" : '\([0-9]*\)'` [ "$numcolors" = "" ] && errMsg "--- NUMCOLORS=$numcolors MUST BE AN INTEGER ---" testA=`echo "$numcolors < 2" | bc` [ $testA -eq 1 ] && errMsg "--- NUMCOLORS=$numcolors MUST BE AN INTEGER GREATER THAN 1 ---" ;; -s) # get seedcolors shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID SEEDCOLORS SPECIFICATION ---" checkMinus "$1" seedcolors="$1" ;; -m) # get maxiters shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID MAXITERS SPECIFICATION ---" checkMinus "$1" maxiters=`expr "$1" : '\([0-9]*\)'` [ "$maxiters" = "" ] && errMsg "--- MAXITERS=$maxiters MUST BE AN INTEGER ---" testA=`echo "$maxiters < 1" | bc` [ $testA -eq 1 ] && errMsg "--- MAXITERS=$maxiters MUST BE AN INTEGER GREATER THAN 1 ---" ;; -c) # get convergence shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID CONVERGENCE SPECIFICATION ---" checkMinus "$1" convergence=`expr "$1" : '\([.0-9]*\)'` [ "$convergence" = "" ] && errMsg "--- CONVERGENCE=$convergence MUST BE A NON-NEGATIVE FLOAT ---" ;; -a) # get area shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID AREA SPECIFICATION ---" checkMinus "$1" area=`expr "$1" : '\([0-9]*\)'` [ "$area" = "" ] && errMsg "--- AREA=$area MUST BE AN INTEGER ---" ;; -t) # get type shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID TYPE SPECIFICATION ---" checkMinus "$1" type=`echo "$1" | tr "[:upper:]" "[:lower:]"` case "$type" in flattened|f) type="flattened";; layered|l) type="layered";; *) errMsg "--- TYPE=$type IS NOT A VALID VALUE ---" ;; esac ;; -C) # get colorspace shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID COLORSPACE SPECIFICATION ---" checkMinus "$1" colorspace="$1" ;; -b) # get bgcolor shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID BGCOLOR SPECIFICATION ---" checkMinus "$1" bgcolor="$1" ;; -v) # get view shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID VIEW SPECIFICATION ---" checkMinus "$1" view=`echo "$1" | tr "[:upper:]" "[:lower:]"` case "$view" in hexcolors|hex|h) view="hexcolors";; swatches|s) view="swatches";; progress|p) view="progress";; all|a) view="all";; dominant|d) view="dominant";; *) errMsg "--- VIEW=$view IS NOT A VALID VALUE ---" ;; esac ;; -A) # get adjoin shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID ADJOIN SPECIFICATION ---" checkMinus "$1" adjoin=`echo "$1" | tr "[:upper:]" "[:lower:]"` case "$adjoin" in yes|y) adjoin="yes";; no|n) adjoin="no";; *) errMsg "--- ADJOIN=$adjoin IS NOT A VALID VALUE ---" ;; esac ;; -k) # get compression shift # to get the next parameter # test if parameter starts with minus sign errorMsg="--- INVALID COMPRESSION SPECIFICATION ---" checkMinus "$1" compression=`echo "$1" | tr "[:upper:]" "[:lower:]"` case "$compression" in none|n) compression="none";; lzw|l) compression="lzw";; zip|z) compression="zip";; *) errMsg "--- COMPRESSION=$compression IS NOT A VALID 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, outfile infile="$1" outfile="$2" fi # test that infile provided [ "$infile" = "" ] && errMsg "--- NO INPUT FILE SPECIFIED ---" # test that outfile provided [ "$outfile" = "" ] && errMsg "--- NO OUTPUT FILE SPECIFIED ---" dir="$tmpdir/KMEANS.$$" mkdir "$dir" || errMsg "--- FAILED TO CREATE TEMPORARY FILE DIRECTORY ---" trap "rm -rf $dir; exit 0" 0 trap "rm -rf $dir; exit 1" 1 2 3 15 # test if alpha channel channels=`convert -quiet "$infile" -format "%[channels]" info:` last_char=`echo ${channels:${#channels} - 1}` #echo "channels=$channels; last_char=$last_char;" # test if infile exists, is readable and is not zero size if [ "$last_char" = "a" ]; then if [ "$bgcolor" != "" ]; then bgproc="-background $bgcolor -alpha background" else bgproc="" fi convert -quiet "$infile" +repage $bgproc \ \( -clone 0 -alpha extract +write $dir/tmpA.miff +delete \) \ -alpha off -colorspace $colorspace -set colorspace sRGB $dir/tmpI.miff || echo "--- FILE $infile DOES NOT EXIST OR IS NOT AN ORDINARY FILE, NOT READABLE OR HAS ZERO SIZE ---" else convert -quiet "$infile" +repage -colorspace $colorspace -set colorspace sRGB $dir/tmpI.miff || echo "--- FILE $infile DOES NOT EXIST OR IS NOT AN ORDINARY FILE, NOT READABLE OR HAS ZERO SIZE ---" 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` if [ "$im_version" -ge "07000000" ]; then identifying="magick identify" else identifying="identify" fi # get image dimensions ww=`$identifying -ping -format "%w" $dir/tmpI.miff` hh=`$identifying -ping -format "%h" $dir/tmpI.miff` #echo "ww=$ww; hh=$hh;" # get seed colors if [ "$seedcolors" != "" ]; then # get array of colors colorArr=($seedcolors) #echo "colors=${colorArr[*]};" numcolors=${#colorArr[*]} #echo "numcolors=$numcolors;" elif [ "$numcolors" != "" ]; then colorArr=(`convert $dir/tmpI.miff -alpha off \ +dither -colors $numcolors -unique-colors txt:- |\ tail -n +2 | grep -o "#[^ ]*"`) [ "$view" = "hexcolors" -o "$view" = "swatches" -o "$view" = "progress" -o "$view" = "all" ] && echo "seed colors = ${colorArr[*]}" numcolors=${#colorArr[*]} #echo "numcolors=$numcolors;" [ "$view" = "swatches" -o "$view" = "all" ] && convert $dir/tmpI.miff -colors $numcolors -unique-colors -scale 5000% show: fi # set up for flattening if [ "$type" = "flattened" ]; then flattening="-background none -flatten" else flattening="" fi # set up for adjoin if [ "$adjoin" = "no" ]; then adjoining="+adjoin" else adjoining="" fi # set up for tif compression # get suffix suffix="${outfile##*.}" # change to lower case suffix=`echo "$suffix" | tr '[:upper:]' '[:lower:]'` echo "$suffix" if [ "$suffix" = "tif" -o "$suffix" = "tiff" ]; then compressing="-compress $compression" else compressing="" fi echo "$compressing" # process kmeans code # create white image # note must add -colorspace gray for IM 7; # otherwise it will be doing -evaluate-sequence later between 3 channel white image and grayscale images, # which will produce a cyan result. convert -size ${ww}x${hh} xc:white -colorspace gray $dir/tmpW.miff # loop over iterations for ((k=0; k