liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
An Associative Perception-Action Structure using a Localized Space Variant Information Representation
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
2000 (English)In: Algebraic Frames for the Perception-Action Cycle: second international workshop, AFPAC 2000, Kiel, Germany, September 10-11, 2000 : proceedings / [ed] Gerald Sommer and Yehoshua Y. Zeevi, Springer, 2000, 48-68 p.Chapter in book (Refereed)
Abstract [en]

Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separation between data and operations. This also goes well with conventional Cartesian representation of data. Currently, there is a trend towards context dependent processing in various forms. This implies that operations will no longer be spatially invariant, but vary over the image dependent upon the image content. There are many ways in which such a contextual control can be implemented. Mechanisms can be added for the modification of operator behavior within the conventional computing structure. This has been done e.g. for the implementation of adaptive filtering. In order to obtain sufficient flexibility and power in the computing structure, it is necessary to go further than that. To achieve sufficiently good adaptivity, it is necessary to ensure that sufficiently complex control strategies can be represented. It is becoming increasingly apparent that this can not be achieved through prescription or program specification of rules. The reason being that these rules will be dauntingly complex and can not be be dealt with in sufficient detail. At the same time that we require the implementation of a spatially variant processing, this implies the requirement for a spatially variant information representation. Otherwise a sufficiently effective and flexible contextual control can not be implemented. This paper outlines a new structure for effective space variant processing. It utilises a new type of localized information representation, which can be viewed as outputs from band pass filters such as wavelets. A unique and important feature is that convex regions can be built up from a single layer of associating nodes. The specification of operations is made through learning or action controlled association.

Place, publisher, year, edition, pages
Springer, 2000. 48-68 p.
, Lecture Notes in Computer Science, ISSN 0302-9743
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-21669DOI: 10.1007/10722492ISBN: 3-540-41013-9ISBN: 978-3-540-41013-3ISBN: 978-3-540-45260-7OAI: diva2:246014
Available from: 2009-10-08 Created: 2009-10-05 Last updated: 2013-12-20Bibliographically approved

Open Access in DiVA

fulltext(331 kB)392 downloads
File information
File name FULLTEXT01.pdfFile size 331 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textfind book at a swedish library/hitta boken i ett svenskt bibliotekfind book in another country/hitta boken i ett annat land

Search in DiVA

By author/editor
Granlund, Gösta H.
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 392 downloads
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: 272 hits
ReferencesLink to record
Permanent link

Direct link