A Parallel Computation That Assigns Canonical Object-Based Frames of Reference

Abstract

A viewpoint-independent description of the shape of an object can be generated by imposing a canonical frame of reference on the object and describing the spatial dispositions of the parts relative to this object-based frame. When a familiar object is in an unusual orientation, the deciding factor in the choice of the canonical object-based frame may be the fact that relative to this frame the object has a familiar shape description. This may suggest that we first hypothesise an object-based frame and then test the resultant shape description for familiarity. However, it is possible to organise the interactions between units in a parallel network so that the pattern of activity in the network simultaneously converges on a representation of the shape and a representation of the object-based frame of reference. The connections in the network are determined by the constraints inherent in the image formation process.