Change search
ReferencesLink to record
Permanent link

Direct link
Automatic Scale Selection as a Pre-Processing Stage to Interpreting Real-World Data
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.ORCID iD: 0000-0002-9081-2170
1996 (English)In: Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence (Toulouse, France): Invited talk, 1996, 490-490 p.Conference paper (Other academic)
Abstract [en]

e perceive objects in the world as meaningful entities only over certain ranges of scale. A simple example is the concept of a branch of a tree, which makes sense only at a scale from, say, a few centimeters to at most a few meters, It is meaningless to discuss the tree concept at the nanometer or kilometer level. At those scales, it is more relevant to talk about the molecules that form the leaves of the tree, and the forest in which the tree grows, respectively.

This fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works, Witkin (1983) and Koenderink (1984) proposed to approach this problem by representing image structures at different scales in a so-called scale-space representation. Traditional scale-space theory building on this work, however, does not address the problem of how to select local appropriate scales for further analysis.

After a brief review of the main ideas behind a scale-space representation, I will in this talk describe a recently developed systematic methodology for generating hypotheses about interesting scale levels in image data---based on a general principle stating that local extrema over scales of different combinations of normalized derivatives are likely candidates to correspond to interesting image structures. Specifically, it will be shown how this idea can be used for formulating feature detectors which automatically adapt their local scales of processing to the local image structure.

Support for the proposed methodology will be presented in terms of general study of the scale selection method under rescalings of the input data, as well as more detailed analysis of how the scale selection method performs when integrated with various types of feature detection modules and then applied to characteristic image patterns. Moreover, it will be illustrated by a rich set of experiments how this scale selection approach applies to various types of feature detection problems in early vision.

In many computer vision applications, the poor performance of the low-level vision modules constitutes a major bottle-neck. It will be argued that the inclusion of mechanisms for automatic scale selection is essential if we are to construct vision systems to analyse complex unknown environments.

Place, publisher, year, edition, pages
1996. 490-490 p.
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-40220DOI: 10.1109/TAI.1996.560799OAI: diva2:456534
QC 20111115 NR 20140804Available from: 2011-11-15 Created: 2011-09-13 Last updated: 2012-01-05Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textAt author's home page

Search in DiVA

By author/editor
Lindeberg, Tony
By organisation
Computational Biology, CB
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 37 hits
ReferencesLink to record
Permanent link

Direct link