Getting following error,help to rectify it

Question

Poonam 2015-3-9

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/182224-getting-following-error-help-to-rectify-it

回答： Jan 2015-3-9

        function [y, MS] = meanShiftPixCluster(x,hs,hr,th,plotOn)
        % FUNCTION: meanShiftPixCluster implements the classic mean shift pixel
        % clustering algorithm introduced in Cmaniciu etal.'s PAMI paper 
        % "Mean shift: a robust apporach toward feature space analysis", 2002.
        % -------------------------------------------------------------------------
        % Input: 
        %       x = an input image (either gray or rgb, please expect long time processing if image size is large)
        %      hs = the bandwidth of spatial kernel (see Eq.(35) in the cited paper)
        %      hr = the bandwidth of feature kernel (see Eq.(35) in the cited paper)
        %      th = the threshod of the convergence criterion (default = .25)
        %  plotOn = switch on/off the image display of intermediate results (default = 1)
        %
        % Output:
        %       y = the output pixel clustered image
        %      MS = the output of averaged mean shift
        % -------------------------------------------------------------------------% ------------------------------------------------------------------------- 
        %%Argument Check
        if nargin<3
            error('please type help for function syntax')
        elseif nargin == 3
            th = 1/100; plotOn = 1;
        elseif nargin == 4
            if th<0 || th >255
                error('threshold should be in [0,255]')
            else
                plotOn = 1;
            end
        elseif nargin == 5
            if sum(ismember(plotOn,[0,1])) == 0
                error('plotOn option has to be 0 or 1')
            end
        elseif nargin>5
            error('too many input arguments')
        end
        %%initialization
        x = double(x);
        [height,width,depth] = size(x);
        y = x;
        done = 0;
        iter = 0;
        if plotOn 
            figure(randi(1000)+1000); 
        end
        % padding image to deal with pixels on borders
        xPad = padarray(x,[height,width,0],'symmetric');
        % build up look up table to boost computation speed
        weight_map = exp( -(0:255^2)/hr^2 );
        MS = [];
        %%main loop
        while ~done
            weightAccum = 0;
            yAccum = 0;
            % only 99.75% area (3sigma) of the entire non-zero Gaussian kernel is considered
            for i = -hs:hs
                for j = -hs:hs
                    if ( i~=0 || j~=0 )
                        % spatial kernel weight 
                        %spatialKernel = 1;
                        % uncomment the following line to active Gausian kernel
                        spatialKernel = exp(-(i^2+j^2)/(hs/3)^2/2);
                        xThis =  xPad(height+i:2*height+i-1, width+j:2*width+j-1, 1:depth);
                        xDiffSq = (y-xThis).^2;
                        % feature kernel weight
                        intensityKernel = repmat( prod( reshape( weight_map( xDiffSq+1 ), height, width, depth) , 3 ), [1,1, depth]);
                        % mixed kernel weight
                        weightThis = spatialKernel.*intensityKernel;
      if true
        % code
      end
                        % update accumulated weights
                        weightAccum = weightAccum+ weightThis;
                        % update accumulated estimated ys from xs 
                        yAccum = yAccum+xThis.*weightThis;
                    end