Using machine learning to find an optimal set of parameters for a given segmentation algorithm.

In the "classical" case of machine learning, in the training phase, the data set is constant and the model fit -- produces a weight vector that maps the data set to the tag of each image label.

Now let's assume a given segmentation problem X, which is done using a given classic segmentation algorithm Y (classic, not Deep-Learning). The goal is to find an optimal parameter set for the Y algorithm under the set of ground truth segmentation. (Motivation: every segmentation algo. Have tuned, parameters, we want to learn them not to fine tune them)

I think about the two approaches of making the this:

  1. Offline - Extraction of General properties - let's say Haralick texture features and try to fit a model connecting between the parameters of the segmentation algorithm Y to the Haralick texture features.
  2. Online - Select random parameters for the Segmentation Y algorithm. Perform a segmentation for those parameters and a specific delta. Calculate the error and then updated the parameters accordingly.

Any thought or example of how the "online" approach could be performed would be welcome.

  • $\begingroup$ Can you please mention one example of segmentation algorithm optimisation you would be interested in applying this method to? $\endgroup$
    – A_A
    Apr 28, 2017 at 13:45
  • $\begingroup$ Just for example: Hough transforms or canny edge detection, but it could be any. However, If you have an answer with an example, it will be awesome. Thanks! $\endgroup$
    – Dov
    Apr 29, 2017 at 3:59
  • $\begingroup$ This is quite broad; I'm not sure there's a better answer than a generic ML answer: come up with a loss function and use cross validation or something else to set parameters. $\endgroup$
    – Batman
    Apr 30, 2017 at 14:44


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.