Using post classification confusion matrix

Pls I need to perform confusion matrix, but I keep getting;

Error using confusion (line 43)
Targets and outputs have different dimensions.

The code I used is;

[c,cm,ind,per] = confusion(BW_1,new_image{1})

where;

BW_1=roipoly(my_image); %Trained class no. 1

BW_1 gives a (2592x4608 logical) variable value in the Workspace part

<2592x4608 logical>

new_image

new_image =

Columns 1 through 4

    [7776x4608 uint8]    [7776x4608 uint8]    [7776x4608 uint8]    [7776x4608 uint8]

Columns 5 through 6

    [7776x4608 uint8]    [7776x4608 uint8]

Kmeans Segmentation code used

he= imread('C:\Users\ISHOLA\Desktop\1.jpg'); %Reading image which is not gray
  cform = makecform('srgb2lab');
  lab_he = applycform(he,cform);
  ab = double(lab_he(:,:,2:3));
  nrows = size(ab,1);
  ncols = size(ab,2);
  disp(nrows);
  disp(ncols);
  ab = reshape(ab,nrows*ncols,2);
  nColors = 6;
  % repeat the clustering 3 times to avoid local minima
  [cluster_idx cluster_center] = kmeans(ab,nColors,'distance','sqEuclidean','replicates',6);
  pixel_labels = reshape(cluster_idx,nrows,ncols);
  %figure, imshow(pixel_labels,[]), title('image labeled by cluster index');
  segmented_images = cell(1,3);
  rgb_label = repmat(pixel_labels,[1 3]);
    for k = 1:nColors
        color = he;
        color(rgb_label ~= k) = 0;
        segmented_images{k} = color;
    end
    new_image = cellfun(@(x)reshape(x,2592*3,4608),segmented_images,'UniformOutput',false)

[Star Strider]

Post the code you are using to do the classification.

[bayoishola20]

okay!Thank you.

U r right, but below is the segmentation code I had used.

he= imread('C:\Users\ISHOLA\Desktop\1.jpg'); %Reading image which is not gray
  cform = makecform('srgb2lab');
  lab_he = applycform(he,cform);
  ab = double(lab_he(:,:,2:3));
  nrows = size(ab,1);
  ncols = size(ab,2);
  disp(nrows);
  disp(ncols);
  ab = reshape(ab,nrows*ncols,2);
  nColors = 6;
  % repeat the clustering 3 times to avoid local minima
  [cluster_idx cluster_center] = kmeans(ab,nColors,'distance','sqEuclidean','replicates',6);
  pixel_labels = reshape(cluster_idx,nrows,ncols);
  %figure, imshow(pixel_labels,[]), title('image labeled by cluster index');
  segmented_images = cell(1,3);
  rgb_label = repmat(pixel_labels,[1 3]);
    for k = 1:nColors
        color = he;
        color(rgb_label ~= k) = 0;
        segmented_images{k} = color;
    end
    new_image = cellfun(@(x)reshape(x,2592*3,4608),segmented_images,'UniformOutput',false)

[bayoishola20]

m-file for segmentation

Answer 1

[Mohammad Abouali]

Well, the answer is right in front of you. BW_1 has 2592x4608=11943936 elements while new_image{1} has 7776x4608=35831808 elements

confusion requires both of them have same number of elements.

since 7776/2592=3, it is possible that you made some mistake and all 3 color bands are getting next to each other on first dimension.If your image looks black and white, it is still possible that it has three color bands; but the colors are set in such a way that it looks gray.

[bayoishola20]

U r right, but below is the segmentation code I had used.

he= imread('C:\Users\ISHOLA\Desktop\1.jpg'); %Reading image which is not gray
  cform = makecform('srgb2lab');
  lab_he = applycform(he,cform);
  ab = double(lab_he(:,:,2:3));
  nrows = size(ab,1);
  ncols = size(ab,2);
  disp(nrows);
  disp(ncols);
  ab = reshape(ab,nrows*ncols,2);
  nColors = 6;
  % repeat the clustering 3 times to avoid local minima
  [cluster_idx cluster_center] = kmeans(ab,nColors,'distance','sqEuclidean','replicates',6);
  pixel_labels = reshape(cluster_idx,nrows,ncols);
  %figure, imshow(pixel_labels,[]), title('image labeled by cluster index');
  segmented_images = cell(1,3);
  rgb_label = repmat(pixel_labels,[1 3]);

    for k = 1:nColors
        color = he;
        color(rgb_label ~= k) = 0;
        segmented_images{k} = color;
    end

    new_image = cellfun(@(x)reshape(x,2592*3,4608),segmented_images,'UniformOutput',false)

Answer 2

[bayoishola20]

pls this is the m-file.