White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Knowledge-based vision and simple visual machines

Cliff, D. and Noble, J. (1997) Knowledge-based vision and simple visual machines. Philosophical Transactions of the Royal Society B - Biological Sciences, 352 (1358). pp. 1165-1175. ISSN 1471-2970


Download (184Kb)


The vast majority of work in machine vision emphasizes the representation of perceived objects and events: it is these internal representations that incorporate the 'knowledge' in knowledge-based vision or form the 'models' in model-based vision. In this paper, we discuss simple machine vision systems developed by artificial evolution rather than traditional engineering design techniques, and note that the task of identifying internal representations within such systems is made difficult by the lack of an operational definition of representation at the causal mechanistic level. Consequently, we question the nature and indeed the existence of representations posited to be used within natural vision systems (i.e. animals). We conclude that representations argued for on a priori grounds by external observers of a particular vision system may well be illusory, and are at best place-holders for yet-to-be-identified causal mechanistic interactions. That is, applying the knowledge-based vision approach in the understanding of evolved systems (machines or animals) may well lead to theories and models that are internally consistent, computationally plausible, and entirely wrong.

Item Type: Article
Copyright, Publisher and Additional Information: © 1997 The Royal Society
Keywords: artificial evolution, visual machines, internal representations, knowledge
Institution: The University of Leeds
Academic Units: The University of Leeds > Faculty of Engineering (Leeds) > School of Computing (Leeds)
Depositing User: Repository Officer
Date Deposited: 12 Jun 2006
Last Modified: 05 Jun 2014 09:24
Published Version: http://dx.doi.org/10.1098/rstb.1997.0100
Status: Published
Publisher: The Royal Society
Refereed: Yes
Identification Number: 10.1098/rstb.1997.0100
URI: http://eprints.whiterose.ac.uk/id/eprint/1277

Actions (repository staff only: login required)