Image Segmentation Using K means

When I execute the following command in Matlab 2012a

centroid=kmeans(imread('image.jpg'),4);

I get the following error

Error using +

Integers can only be combined with integers of the same class, or scalar doubles.

Error in kmeans>distfun (line 659)

            *D(:,i) = D(:,i) + (X(:,j) - C(i,j)).^2;*

*Error in kmeans (line 273)*

*D = distfun(X, C, distance, 0, rep, reps);*

I need to segment this image into 4 cluster. This image is a CT Brain tumour Image. Size of this image is 233 x 216. Please give me a solution to cluster this image file.

Answer 1

[Walter Roberson]

YourImage = imread('Image.jpg');
centroid = kmeans(double(YourImage), 4);

Note: if your .jpg is color rather than greyscale, you will probably need to convert it to greyscale before clustering.

[Octa]

I got it. Your reason is correct.

Instead of using kmeans for segmenting, I used the default kmeans in MATLAB. So this error occurred. Now my program is working by using the kmeans segmentation algorithm.

Thanks for commenting on my doubt.

[Image Analyst]

Do you want to cluster based on intensity of pixels (e.g. you want 4 gray level classes), or you want to find spatial clusters (e.g. 4 clumps of spatially separated pixels)?

[Octa]

I want kmeans to cluster based on the intensity of pixels, so I used the kmeans Segmentation algorithm and got the output.

Thank you for your comment

[syed salma banu s]

sir i need to cluster the image based on intensity of pixels e.g. i want 3 gray level classes

[Walter Roberson]

convert the image to grayscale and kmeans requesting 3 clusters .

Answer 2

[moahaimen talib]

hi i need to use kmean for segmenting and clustering a binary image please help

[Image Analyst]

OK. We'll try. It's your turn now to respond now.

Answer 3

[Gebra maryam Alehegn]

How to correctly culsture image using k menas?

[Walter Roberson]

https://www.mathworks.com/help/images/examples/color-based-segmentation-using-k-means-clustering.html

[Image Analyst]

See my attached demo.