Abstract
This chapter gives an account of techniques for initial segmentation of images into smaller units, called segmentation objects in the following, and their relevant properties. It is beyond the scope of this volume to give a detailed and in depth treatment of segmentation. Rather, the purpose of this chapter is to show which types of results can be achieved by an initial phase of mainly bottom-up (or data-driven) processing using no task specific knowledge, which problems occur, and how the results can be represented. So the intent is to show what will be the starting point of knowledge-based processing as discussed in subsequent sections. Therefore, it is with intention that this chapter does not contain pictures showing examples of particular segmentation results.
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). Segmentation. 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_2
Download citation
DOI: https://doi.org/10.1007/978-1-4899-1913-7_2
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-1915-1
Online ISBN: 978-1-4899-1913-7
eBook Packages: Springer Book Archive