Computing with connections in visual recognition of origami objects

This paper summarizes our initial foray in tackling Artificial Intelligence problems using a connectionist approach. The particular task chosen was the visual recognition of objects in the Origami world as defined by. The two major questions answered were how to construct a connectionist network to represent and recognize projected line drawings of Origami objects and what advantages such an approach would have. The structure of the resulting connectionist network can be described as a hierarchy of parameter or feature spaces with each node in each of the feature spaces representing a hypothesis about the possible existence of a specific geometric feature of an Origami object. The dynamic behavior of the network is a form of iterative refinement or relaxation whose major characteristic is to prefer more globally interesting interpretations of the input over locally pleasing ones. Examples from the implementation illustrate the system's ability to deal with forms of noise, occlusion and missing information. Other benefits are an inherently parallel approach to vision, limitation of explicit ordering of the search involved in matching model to instance and the elimination of backtracking due to the sharing of partial results as the search progresses. Extensions and problems are also discussed.