Supervised learning of large perceptual organization: Graph spectral partitioning and learning automata

Perceptual organization offers an elegant framework to group low-level feat ures that are likely to come from a single object. We offer a novel strateg y to adapt this grouping process to objects in a domain. Given a set of tra ining images of objects in context, the associated learning process decides on the relative importance of the basic salient relationships such as prox imity, parallelness, continuity, junctions, and common region toward segreg ating the objects from the background. The parameters of the grouping proce ss are cast as probabilistic specifications of Bayesian networks that need to be learned. This learning is accomplished using a team of stochastic aut omata in an N-player cooperative game framework. The grouping process, whic h is based on graph partitioning is, able to form large groups from relatio nships defined over a small set of primitives and is fast. We statistically demonstrate the robust performance of the grouping and the learning framew orks on a variety of real images. Among the interesting conclusions are the significant role of photometric attributes in grouping and the ability to form large salient groups from a set of local relations, each defined over a small number of primitives.