Bone graphs: Medial shape parsing and abstraction

The recognition of 3-D objects from their silhouettes demands a shape representation which is stable with respect to minor changes in viewpoint and articulation. This can be achieved by parsing a silhouette into parts and relationships that do not change across similar object views. Medial descriptions, such as skeletons and shock graphs, provide part-based decompositions but suffer from instabilities. As a result, similar shapes may be represented by dissimilar part sets. We propose a novel shape parsing approach which is based on identifying and regularizing the ligature structure of a medial axis, leading to a bone graph, a medial abstraction which captures a more stable notion of an object’s parts. Our experiments show that it offers improved recognition and pose estimation performance in the presence of within-class deformation over the shock graph.

► A novel shape parsing approach based on the medial axis is presented.
► A shape is decomposed into a set of salient skeletal parts and their relations.
► The parts and relations are captured in a hierarchical abstraction - the bone graph.
► The bone graph avoids the ligature-based instability of a medial axis.
► The bone graph offers improved performance in view-based object recognition.