calculation error in histogram features

Question

I am getting the value of kurtosis for only 251 blocks as i divided images into blocks i mnot getting what is wrong actually it should show it for 252 blocks please review the code thanks in advance

clear all;
close all;

x =  imread('image009.png');
rgb = imresize(x,0.5);
green  = rgb(:,:,2);
[m,n]=size(green);
imnum=input('enter image number');
g=1;
q=1;
scaler=36;
scalec=37.5;
bno=1;
g=1;

for i=1:scaler:(m-scaler)
    if((i==1)||(i==(m-scaler))
        continue;    
    end

    for j=1:scalec:(n-scalec)

        if((j==1)||(j==(n-scalec)))
            continue;
        end
        tbpcolr = imcrop(green,[j,i,scalec,scaler])
        ip=input('press some key');
        mgreen = mean2(tbpcolr);
        stats = hisfeatures(tbpcolr);
        Mean(1,g) = stats(1)
        Variance(1,g) =stats(2)
        Skewness(1,g) =stats(3)
        Kurtosis(1,g)=stats(4)
        Energy(1,g) =stats(5)
        Entropy(1,g) =stats(6)
        Kurtosis = Kurtosis(~isnan(Kurtosis))
        Entropy = Entropy(~isnan( Entropy))
        Skewness = Skewness(~isnan(  Skewness))
        g=g+1;
        bno=bno+1; 
    end
end

blockno = [];
for  i = 1:252
    blockno(i)=i;
end

for  i = 1:252
    result_his=vertcat(Energy,Mean,Variance,Kurtosis,Skewness,Entropy,blockno); 
end

result_his=result_his.'

Answer 1

Removing cells with NaN would destroy the matrix structure. Removing whole rows that contain NaN would discard real data. Instead, the Statistics Toolbox has a variety of functions that are similar to other MATLAB functions, but that treat NaN values as missing and therefore ignore them in the calculations.