Use superpixels as input for conditional random fields in image segmentation

In the image segmentation tutorial for skimage, it was mentioned that These superpixels then serve as a basis for more sophisticated algorithms such as conditional random fields (CRF). Are there any examples/tutorials on using CRF with superpixels as input? Thanks.

Hi @wenyia!

We don’t have specific examples with CRFs, but we do show the basis of creating those in examples featuring region adjacency graphs, or RAGs. Search for “RAG” in the gallery.