We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.

Durham Research Online
You are in:

Shape as an emergent property.

Jermyn, Ian H. (2013) 'Shape as an emergent property.', in Shape perception in human and computer vision : an interdisciplinary perspective. London, New York: Springer , pp. 187-199. Advances in computer vision and pattern recognition.


Shape is a ubiquitous property of our world. Inferences about it require ‘shape models’: probability distributions on shapes. The crucial property of any such shape model is the existence of long-range dependencies between boundary points. We look at how this property has typically been implemented in machine vision, and at the drawbacks of this ‘classical’ approach. We then discuss an alternative, inspired by classes of shapes arising in certain image processing problems. The resulting description of shape does not involve exogenous templates, but instead describes shape as an emergent property of interactions in a network of simple nodes.

Item Type:Book chapter
Full text:Publisher-imposed embargo
(AM) Accepted Manuscript
File format - PDF (Copyright agreement prohibits open access to the full-text)
Publisher Web site:
Date accepted:No date available
Date deposited:03 August 2015
Date of first online publication:2013
Date first made open access:No date available

Save or Share this output

Look up in GoogleScholar