1

I am doing Texture Segmentation in Images Using Gabor Filters. I have generated Feature images and now i want to cluster them using square clustering or K-means. Since i am working in MATLAB, I am using the matlab defined functions. The official documentation for K-means clustering states

 idx = kmeans(X,k)

where,X= n by p data matrix and k is the number of clusters. I want to know how to use this function for my dataset since i have n feature images which means i have n features for every pixel of the original image. So my question is how do I use my dataset in the above function. Also, if no function exists please explain how can I implement it on my own.

I am referring this research paper( page 6 ) Gabor filters for texture Segmentation

shivang gupta
  • 21
  • 1
  • 5
  • how many "feature" images do you have, what is the dimension of each such image? – Shai Apr 21 '15 at 10:51
  • The number of feature images generated depends on the image width of the original image. For the sake of simplicity, lets assume thatt i have 20 feature images each having dimensions 188 * 268. – shivang gupta Apr 21 '15 at 16:30

0 Answers0