Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
On the Representation and Matching of Qualitative Shape at Multiple Scales
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
Show others and affiliations
2002 (English)In: Computer Vision — ECCV 2002: 7th European Conference on Computer Vision Copenhagen, Denmark, May 28–31, 2002 Proceedings, Part III, Springer Berlin/Heidelberg, 2002, 759-775 p.Conference paper, Published paper (Refereed)
Abstract [en]

We present a framework for representing and matching multi-scale, qualitative feature hierarchies. The coarse shape of an object is captured by a set of blobs and ridges, representing compact and elongated parts of an object. These parts, in turn, map to nodes in a directed acyclic graph, in which parent/child edges represent feature overlap, sibling edges join nodes with shared parents, and all edges encode geometric relations between the features. Given two feature hierarchies, represented as directed acyclic graphs, we present an algorithm for computing both similarity and node correspondence in the presence of noise and occlusion. Similarity, in turn, is a function of structural similarity, contextual similarity (geometric relations among neighboring nodes), and node contents similarity. Moreover, the weights of these components can be varied on a node by node basis, allowing a graph-based model to effectively parameterize the saliency of its constraints. We demonstrate the approach on two domains: gesture recognition and face detection.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2002. 759-775 p.
Series
Lecture Notes in Computer Science, 2352
National Category
Computer Science Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-58581DOI: 10.1007/3-540-47977-5_50ISBN: 978-3-540-43746-8 (print)OAI: oai:DiVA.org:kth-58581DiVA: diva2:473383
Conference
European Conference on Computer Vision, Denmark, May 28–31, 2002
Note

QC 20130422

Available from: 2013-04-22 Created: 2012-01-05 Last updated: 2013-04-22Bibliographically approved

Open Access in DiVA

fulltext(600 kB)188 downloads
File information
File name FULLTEXT01.pdfFile size 600 kBChecksum SHA-512
a78260f1c8c818a6f6af92d276a5d81693b51cc9d0532c8f200a35b83519a2b68a12c8bd8c0f864d882018e073b3431974173e245f5f5d44eecbc4c91c38427f
Type fulltextMimetype application/pdf

Other links

Publisher's full textThe final publication is available at www.springerlink.com

Authority records BETA

Lindeberg, Tony

Search in DiVA

By author/editor
Jönsson, ClasBretzner, LarsLindeberg, Tony
By organisation
Computer Vision and Active Perception, CVAPNumerical Analysis and Computer Science, NADA
Computer ScienceComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 188 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

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 133 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf