Image Classification Using SVM Classifer

Hello everyone, I have extracted the features from my medical image sets and now I want to classify my images into two classes.

As I have studied features extracted there is no significant difference among the featuers depending on the already known manual classification results.

I would much appreciate if anyone could help me whether is it preferable to use SVM as the classifier? And also is there any specific code which may be useful for me to get this classification done using the SVM? I have tried classification APP but still I am not able to help with it.

If not what is the most suitable and preferable method for this classification?

Thank you in advance!

Answer 1

[Hiro Yoshino]

It is hard for you to tell if the features you extracted are good or bad. ML algorithms will tell you.

Generally speaking, Deep Learning (CNN) will be the best one for you if you have enough number of images, where you do not need to conduct feature extraction - just feed them into the neural network.

Just in the case you do not have millions of images, you should think about "transfer learning".

https://www.mathworks.com/help/deeplearning/gs/get-started-with-transfer-learning.html

If you want to stick to something traditional, you should keep using the algorithms available in Classification learner App.

But there is still room for you to work on: parameter tuning, PCA, feature selection... These can be done from the App! Do not worry, all you need is tick some boxes and wait.

[Nileema Abedeera]

Hiro Yoshino , Thank you for the valuable inputs.

Actually I have no that much of images for this study. I am working only on 200 images. In that case I can not use CNN methods for this.

I have got certain graphs which I wanted using classification APP but still helpless with training data set and then test the remaining data using the APP.

Thank you for the link provided! I will go through it.

[Hiro Yoshino]

My pleasure!!