Determination of data points in each cluster of K-means algorithm

Hello,

How can I calculate the number of data points of each cluster of K-means ? I found the answer of counter in python, but donot know how to use such kind of commond in MATLAB. I am finding clusters using this code

clear workspace;
path = char('E:\final'); %pass to this variable your complet data set path  
net=alexnet();
imds = imageDatastore(fullfile(path),'IncludeSubfolders',true, 'LabelSource', 'foldernames');
augImds=augmentedImageDatastore(net.Layers(1, 1).InputSize(1:2),imds);
idx=randperm(numel(imds.Files),30);
imgEx=readByIndex(augImds,idx);
figure;montage(imgEx.input);title('example of the dataset');
figure;
Labels=imds.Labels;
% count the number of images
numClass=numel(countcats(Labels));
% feature extraction with the pre-trained network
feature=squeeze(activations(net,augImds,'fc8'));
% conduct a principal component analysis for the dimension reduction
A=pca(feature,"Centered",true);
subplot(1,2,1);
gscatter(A(:,1),A(:,2),Labels);
subplot(1,2,2);
% perform t-sne for the dimension reduction
T=tsne(feature');
gscatter(T(:,1),T(:,2),Labels);

% perform k-means algorithm 
% please note that as the result is dependent on the initial point in the algorithm, the
% result would not be same  

C=kmedoids(feature',numClass,"Start","plus");

% confirm the number of images in the largest group 
[~,Frequency] = mode(C);
sz=net.Layers(1, 1).InputSize(1:2);
% prepare a matrix to show the clustering result
I=zeros(sz(1)*numClass,sz(2)*Frequency,3,'uint8');
% loop over the class to display images assigned to the group
 
 for i=1:numClass
    % read the images assigned to the group 
    % use the function "find" to find out the index of the i-th group image
    ithGroup=readByIndex(augImds,find(C==i));
    
          % tile the images extracted above
I((i-1)*sz(1)+1:i*sz(1),1:sz(2)*numel(find(C==i)),:)=cat(2,ithGroup.input{ : });

 end
figure;
imshow(I);
title('result of the image clustering using k-means after feature extraction with alexnet')

[KALYAN ACHARJYA]

Can you show me the result clustered image?

[Learner]

Sure sir,

Input Image

PFA

[Learner]

Sir i want result in this format.The tabel in the below file is created manually by me.I want to do this by program itself.pls help

file attached below pls check

Answer 1

[Adam Danz]

C = kmedoids(___)
T = groupcounts(C)

[Learner]

Hello Sir,

With this T = groupcounts(C) I got the count of datapoints that are in the cluster.

But I want result in this format as explained below

Suppose in my cluster of ka images I have 10 images of ka and 1 image of ra and 2image of ha.So I want results in that format that this cluster has images of ka,this num of images of ra and this number of images ha

For better understanding I am aataching the output result

PFA

[Image Analyst]

If you're doing deep learning OCR/classification on those characters you have to put it into a loop where you pass each character into your network and then count up (make a histogram) of how many classes come back of each type. For sample pseudocode

myHistogram = zeros(1, numberOfClasses)
imds = imageDatastore(*.png');
numImages = length(imds.Files)
for k = 1 : numImages
    thisFullFileName = imds.Files{k};
    thisImage = imread(thisFullFileName);
    imshow(thisImage);
    caption = sprintf('Image #%d of %d', k, numImages);
    drawnow;
    thisClass = classify(thisImage);
    myHistogram(thisClass) = myHistogram(thisClass) + 1;
end

[Adam Danz]

> With this T = groupcounts(C) I got the count of datapoints that are in the cluster.

Doesn't that address your question, "How can I calculate the number of data points of each cluster of K-means" ?

It sounds like we've got an XY Problem. I'd have to look deeper into what you're doing and I don't have the time right now to do that. Hopefully ImageAnalyst's comment above can point you in the right direction.

[Learner]

T = groupcounts(C) worked for me..

Thanks a ton Adam Danz Sir and Imamge Analyst Sir for help and time

Answer 2

[Image Analyst]

classNumbers = kmedoids(X,k)

To find how many data points are in class 1 for example

numberInClass1 = sum(classNumbers == 1);