Globally Optimal Segmentation of Multi-Region Objects

Andrew Delong and Yuri Boykov

In International Conference on Computer Vision (ICCV), Kyoto, Japan, October 2009

Abstract

Many objects contain spatially distinct regions, each with a unique colour/texture model. Mixture models ignore the spatial distribution of colours within an object, and thus cannot distinguish between coherent parts versus randomly distributed colours. We show how to encode geometric interactions between distinct region+boundary models, such as regions being interior/exterior to each other along with preferred distances between their boundaries. With a single graph cut, our method extracts only those multi-region objects that satisfy such a combined model. We show applications in medical segmentation and scene layout estimation. Unlike Li et al. [17] we do not need “domain unwrapping” nor do we have topological limits on shapes.


WHOLE PAPER: pdf file (4MB)