Hierarchical Planar Correlation Clustering for Cell Segmentation

We introduce a novel algorithm for hierarchical clustering on planar graphs we call “Hierarchical Greedy Planar Correlation Cluster- ing” (HGPCC). We formulate hierarchical image segmentation as an ul- trametric rounding problem on a superpixel graph where there are edges between superpixels that are adjacent in the image. We apply coordi- nate descent optimization where updates are based on planar correlation clustering. Planar correlation clustering is NP hard but the efficient Pla- narCC solver allows for efficient and accurate approximate inference. We demonstrate HGPCC on problems in segmenting images of cells.