what is a method for segmentation texture?

hi, i'm anggita. i have a question about segmentation texture. my project is classification plant disease based on texture. so all of method must using based on texture. for extraction feature, i'm using GLCM. and for classification, i'm using SVM. so, what is a method that i use for segmentation texture?

please give me any ideas, thank you so much.

Answer 1

[Constantino Carlos Reyes-Aldasoro]

Hello

The basic concept of texture is that you will transform your image, which has a certain texture, to a different space, where the texture will be recognised (i.e. the classification, which can be SVM, or any other, even thresholding if there is clear separation of the textures) depending on what texture method (GLCM, spatial filtering, Fourier filtering) you apply.

GLCM is just one of many methods, simple and effective, but not the most powerful. Have a look at this document for a guide to co-occurrence:

https://wrap.warwick.ac.uk/61393/

You could also explore filtering in the Fourier domain, and the matlab code is available here:

https://uk.mathworks.com/matlabcentral/fileexchange/67931-multiresolution-texture-segmentation

This recent paper compares different texture segmentations with different algorithms:

https://www.mdpi.com/2076-3417/9/18/3900/htm

Hope this gives you some ideas of how to proceed. Let me know if you need more information, or if solved, please accept the answer.

[Anggita Puspawardani]

Thank you so much for your information. Actually, my project has been finished. So the final, I used K-Means for segmentation method. If I use thresholding for segmentation, so can I still use GLCM for reach the extraction feature?

for this website https://wrap.warwick.ac.uk/61393/ I can't read the paper.

[Constantino Carlos Reyes-Aldasoro]

Yes indeed, GLCM will transform from the domain where you data is to a different domain, depending on the size of the matrix and all the parameters, and there you can apply thresholding, K-means, LVQ, SVM, anything to classify.

Look at page 22 of the document, perhaps the direct link will help:

http://wrap.warwick.ac.uk/61393/1/WRAP_Reyes_cs-rr-398.pdf

The images there have been processed with GLCM in different configurations, some highlight bones, some the boundaries.