Image Segmentation by Edge Partitioning over a Nonsubmodular Markov Random Field

Figure 1

An image can be segmented by partitioning edges into two sets. Cut (dotted red) and connected (solid black) edge sets can be translated into a unique segmentation as in (c). However, it is also possible to have edge partitions that contradict the label assignments as in (d). By finding the image labeling that minimizes the edge partition energy, edge partitions like (d) are prevented, and a consistent image segmentation becomes possible as shown in (a) and (b).

(a)

(b)

(c)

(d)