Change search
ReferencesLink to record
Permanent link

Direct link
Scale detection and region extraction from a scale-space primal sketch
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.ORCID iD: 0000-0002-9081-2170
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
1990 (English)In: Computer Vision, 1990. Proceedings, Third International Conference on, IEEE Computer Society, 1990, 416-426 p.Conference paper (Refereed)
Abstract [en]

We present: (1) a multi-scale representation of gray-level shape, called a scale-space primal sketch, which makes explicit both features in scale-space and the relations between features at different levels of scales; (2) a theory for extraction of significant image structure from this representation; and (3) applications to edge detection, histogram analysis and junction classification demonstrating how the proposed method can be used for guiding later stage processing. The representation gives a qualitative description of the image structure that allows for detection of stable scales and regions of interest in a solely bottom-up data-driven way. In other words, it generates coarse segmentation cues and can be hence seen as preceding further processing, which can then be properly tuned. We argue that once such information is available many other processing tasks can become much simpler. Experiments on real imagery demonstrate that the proposed theory gives perceptually intuitive results.

Place, publisher, year, edition, pages
IEEE Computer Society, 1990. 416-426 p.
National Category
Computer Science Computer Vision and Robotics (Autonomous Systems)
URN: urn:nbn:se:kth:diva-58590DOI: 10.1109/ICCV.1990.139563ISBN: 0-8186-2057-9OAI: diva2:473392
International Conference on Computer Vision (ICCV'90), Osaka, Japan, Dec 4-7, 1990

QC 20140805

Available from: 2012-01-05 Created: 2012-01-05 Last updated: 2015-07-01Bibliographically approved

Open Access in DiVA

fulltext(7872 kB)44 downloads
File information
File name FULLTEXT03.pdfFile size 7872 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textAt authors' home pageIEEEXplore

Search in DiVA

By author/editor
Lindeberg, Tony
By organisation
Computational Biology, CBComputer Vision and Active Perception, CVAP
Computer ScienceComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 48 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: 227 hits
ReferencesLink to record
Permanent link

Direct link