BIS as part of a feature extraction workflow.
The emphasis is automation and objective parameter selection.
Quantitatively compare each segmentation run to ground
How do I choose the parameters? Don't. Run all possible segmentation combinations and choose the one that looks the best. That is how BIS is designed: Let the computer do the number crunching and the scientist chooses which output is best.
With BIS API the "segmentation goodness" training and ranking functions can assist. It is best to do this computationally intensive step on a 1000x1000 or smaller representative clip of your image.