The structure of Bayes nets for vision recognition
This work addresses vision recognition for AI/robotics by introducing a principled approach, though it appears incremental as it builds on existing belief network techniques.
The paper tackles the problem of vision recognition by proposing a Bayes network model derived from first principles to avoid arbitrary parameters, and demonstrates a solution for a multiply connected network formulation.
This paper is part of a study whose goal is to show the effciency of using Bayes networks to carry out model based vision calculations. [Binford et al. 1987] Recognition proceeds by drawing up a network model from the object's geometric and functional description that predicts the appearance of an object. Then this network is used to find the object within a photographic image. Many existing and proposed techniques for vision recognition resemble the uncertainty calculations of a Bayes net. In contrast, though, they lack a derivation from first principles, and tend to rely on arbitrary parameters that we hope to avoid by a network model. The connectedness of the network depends on what independence considerations can be identified in the vision problem. Greater independence leads to easier calculations, at the expense of the net's expressiveness. Once this trade-off is made and the structure of the network is determined, it should be possible to tailor a solution technique for it. This paper explores the use of a network with multiply connected paths, drawing on both techniques of belief networks [Pearl 86] and influence diagrams. We then demonstrate how one formulation of a multiply connected network can be solved.