Segmentation in Scale Space

Rolf D. Henkel

Abstract:

A segmentation scheme based on tracing objects and borders through scale space is proposed. Scale space allows to create a hierarchical representation of input data which can be used to tessellate input space into objects with closed and orientable borders. For analyzing the structure of scale space, a neural network approach using synchronizing neural oscillators is proposed.

• Introduction
• Local and Global Analysis
• Global Analysis as Clustering Process.
• Local Analysis as Grouping in Measurement Space.
• Scale Space
• Hierarchical Segmentation
• Possible Neural Implementation
• Segmentation Results
• Acknowlegdements.
• References

---

Comments are welcome! © 1997 by Rolf Henkel - all rights reserved.