Abstract
The proposed representation is similar to the primal sketch idea suggested by Marr (1976, 1982), in the sense that it is a two-dimensional representation of the significant grey-level structures in the image. It is also computed under extremely weak assumptions. In addition, it is a region-based, not an edge-based representation, and it is more qualitative,without strong assumptions about the shapes of the primitives. It consists of blobs (extremum regions) at multiple scales in scale-space, and allows for
-
automatic detection of salient (stable) scales, if they exist
-
ranking of blob-like structures in order of significance, and
-
generation of hypotheses for grouping and segmentation.
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
© 1994 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Lindeberg, T. (1994). Summary and discussion. In: Scale-Space Theory in Computer Vision. The Springer International Series in Engineering and Computer Science, vol 256. Springer, Boston, MA. https://doi.org/10.1007/978-1-4757-6465-9_12
Download citation
DOI: https://doi.org/10.1007/978-1-4757-6465-9_12
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4419-5139-7
Online ISBN: 978-1-4757-6465-9
eBook Packages: Springer Book Archive