MATLAB: Help on Hierarchical Clustering

hierarchical clustering

I have 200 images, i extracted color, shape and texture features from it and used kmeans method to cluster it into 5 clusters. Is it possible to do Hierarchical Clustering method after K-means clustering for retrieving most matching image in each cluster?? How to do it?? Please do reply……

Best Answer

I am not sure....but this may help u. This is agglomerative clustering (Hierarchical clustering). http://www.mathworks.in/help/stats/linkage.html

Related Solutions

MATLAB: How i can solve this problem? Pleas!

Your ‘T’ matrix must become a cell array. See my sample of ‘T’ for an example.

Once you do that, I would do something like this:

Y = [12.004
    13.1573 
    11.1665  
    11.8082    
    12.2129   
    12.8075   
    12.4167  
    11.5708   
    12.5798    
    13.7489];
T={'cluster2'; 'cluster1'; 'cluster3'; 'cluster9'; 'cluster0'; 'cluster7'; 'cluster4'}; % Sample Of Cell Array
[UnqClust,~,idx] = unique(T);                                                           % Unique Values & Locations
Out = Y(idx);                                                                           % Mapped Output
for k1 = 1:length(idx)
    fprintf(1, '\t%s\t%.4f\n', T{k1}, Out(k1))              % Demonstration Output (Delete Loop)
end
  cluster2  11.1665
  cluster1  13.1573
  cluster3  11.8082
  cluster9  12.4167
  cluster0  12.0040
  cluster7  12.8075
  cluster4  12.2129

MATLAB: I want solution for this problem

This code might do what you are looking for

ix = sscanf( T(:,end), '%1d' );
Y  = cat( 1, Y, rand );     % add one element to get 10
R  = Y(ix+1);

inspect the result

>> R(1:6)'
ans =
   11.1665   11.1665   11.1665   11.5740   11.5740   11.5740

where

T=['cluster2'
'cluster2'
'cluster2'
'cluster7'
'cluster7'
'etc ....'];

Best Answer

Related Solutions

MATLAB: How i can solve this problem? Pleas!

MATLAB: I want solution for this problem

Related Question