Segmentation in Scale Space

Rolf D. Henkel

Prev: Introduction ^ Up: Table of Contents ^ Next: Global Analysis as Clustering

Local and Global Analysis

Basically, only two approaches toward segmentation can be differentiated. Since we are dealing with features f(x) given over some input space tex2html_wrap_inline325 , a single element of the dataset has two distinct properties: a value f and a spatial coordinate x. Depending on the feature quality used, we can distinguish two different ansätze for segmentation, called in the following global and local analysis. In a global analysis, one ignores metrical information, in a local analysis, one uses it. As we will see, both types of segmentation are closely connected with two complementary properties of objects: objects defined as prominent signal variations versus objects defined by being encircled with borders.

© 1994-2003 - all rights reserved.