Measuring convexity for figure/ground separation. The

In human perception, convex surfaces have a strong ten-dency to be perceived as the ”figure”. Convexity has a stronger influence on figural organization than other global shape properties, such as symmetry ([9]). And yet, there has been very little work on convexity properties in com-puter vision. We present a model for figure/ground segregatation which exhibits a preference for convex regions as the fig-ure (i.e., the foreground). The model also shows a prefer-ence for smaller regions to be selected as figures, which is also known to hold for human visual perception (e.g., Kof-fka [11]). The model is based on the machinery of Markov random fields/random walks/diffusion processes, so that the global shape properties are obtained via local and stochas-tic computations. Experimental results demonstrate that our model performs well on ambiguous figure/ground dis-plays which were not captured before. In particular, in am-biguous displays where neither region is strictly convex, the model shows preference to the “more convex ” region, thus offering a continuous measure of convexity in agreement with human perception. 1