---
title: "A Parallel Computation that Assigns Canonical Object-Based Frames of Reference"
authors:
  - "Geoffrey E. Hinton"
doi: ""
url: "https://ijcai.org/proceedings/1981/129"
pdf: "https://ijcai.org/proceedings/1981/0129.pdf"
venue: "Proceedings of the Seventh International Joint Conference on Artificial Intelligence"
year: 1981
pages: "683-684"
track: "Vision: 3-d"
keywords:
---

# A Parallel Computation that Assigns Canonical Object-Based Frames of Reference

Geoffrey E. Hinton

*Proceedings of the Seventh International Joint Conference on Artificial Intelligence*, pages 683-684.

## Abstract

A. vievpoint-independent description of the shape of en object can be generated by imposing a canonical frame of reference on the object and describing the spatial dispositions of the parte 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 11ay 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 objectbased frame of reference. The connections in the network are determined by the constraints inherent in the image formation process.