Abstract
According to experience a fixed sequence of processing steps applied to all patterns in a task domain often leads to unsatisfactory results. Therefore, in this chapter we treat the problem of computing a good (or even optimal) processing strategy individually for every pattern; this is called control for short. Some general ideas are presented, but of course, the main emphasis is on control in a semantic network environment omitting techniques which are tailored, for example, to a purely rule-based environment.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Sagerer, G., Niemann, H. (1997). Control. In: Semantic Networks for Understanding Scenes. Advances in Computer Vision and Machine Intelligence. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-1913-7_6
Download citation
DOI: https://doi.org/10.1007/978-1-4899-1913-7_6
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-1915-1
Online ISBN: 978-1-4899-1913-7
eBook Packages: Springer Book Archive