I am trying to learn how to use Markov Random Fields for classifying pixels in an image. Could someone please direct me to a simple tutorial demonstrating how this is done. The tutorial needs to cover estimating the model parameters and handling the final classification.

Some of the things I don't understand:

  1. I have read of ICM and graph cuts being used to minimise the energy function that appears in the MRF. Is this referring only to the classification step, i.e. all model parameters are already known?
  2. In the Gaussian mixture models, there is the conditional probability of the pixel intensity given its class label (modelled by a Gaussian function) and the prior probability of getting the class label. Does the probability modelled by the MRF replace the prior probability for the class label or does it replace both probabilities?

Any help would be greatly appreciated. Thanks in advance.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.