Concave Region Partitioning with a Greedy Strategy on Imbalanced Points

Concave region partitioning is valuable for object modeling and recognition. A key issue to the design of an efficient partitioning method is on the selection of cut points. In this paper, we propose to use imbalanced points in a region to characterize cut points in the contour of the region, motivated by the good corner nature of imbalanced points. Specifically, we formulate a concave region as a minimum set of convex sub regions, in terms of the Minimal Description Length (MDL) principle. We propose algorithms to find the minimum set of convex sub regions based on a greedy strategy. We present results to demonstrate the promise of the proposed framework.