Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A signal-symbol loop mechanism for enhanced edge extraction

Kalkan, Sinan ; Wörgötter, Florentin ; Yan, Shi ; Krüger, Volker LU orcid and Krüger, Norbert (2008) 3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008 2. p.217-221
Abstract

The transition to symbolic information from images involves in general the loss or misclassification of information. One way to deal with this missing or wrong information is to get feedback from concrete hypotheses derived at a symbolic level to the sub-symbolic (signal) stage to amplify weak information or correct misclas-sifications. This paper proposes such a feedback mechanism between the symbolic level and the signal level, which we call signal symbol loop. We apply this framework for the detection of low contrast edges making use of predictions based on Rigid Body Motion. Once the Rigid Body Motion is known, the location and the properties of edges at a later frame can be predicted. We use these predictions as feedback to the... (More)

The transition to symbolic information from images involves in general the loss or misclassification of information. One way to deal with this missing or wrong information is to get feedback from concrete hypotheses derived at a symbolic level to the sub-symbolic (signal) stage to amplify weak information or correct misclas-sifications. This paper proposes such a feedback mechanism between the symbolic level and the signal level, which we call signal symbol loop. We apply this framework for the detection of low contrast edges making use of predictions based on Rigid Body Motion. Once the Rigid Body Motion is known, the location and the properties of edges at a later frame can be predicted. We use these predictions as feedback to the signal level at a later frame to improve the detection of low contrast edges. We demonstrate our mechanism on a real example, and evaluate the results using an artificial scene, where the ground truth data is available.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
keywords
Edge extraction, Feedback mechanisms, Rigid body motion, Signal-symbol loop
host publication
VISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings
volume
2
pages
5 pages
conference name
3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008
conference location
Funchal, Madeira, Portugal
conference dates
2008-01-22 - 2008-01-25
external identifiers
  • scopus:57549090870
ISBN
9789898111210
language
English
LU publication?
no
id
89066d95-b1da-4c2a-9ae7-bff3a4776584
date added to LUP
2019-06-28 09:25:59
date last changed
2022-01-31 22:50:20
@inproceedings{89066d95-b1da-4c2a-9ae7-bff3a4776584,
  abstract     = {{<p>The transition to symbolic information from images involves in general the loss or misclassification of information. One way to deal with this missing or wrong information is to get feedback from concrete hypotheses derived at a symbolic level to the sub-symbolic (signal) stage to amplify weak information or correct misclas-sifications. This paper proposes such a feedback mechanism between the symbolic level and the signal level, which we call signal symbol loop. We apply this framework for the detection of low contrast edges making use of predictions based on Rigid Body Motion. Once the Rigid Body Motion is known, the location and the properties of edges at a later frame can be predicted. We use these predictions as feedback to the signal level at a later frame to improve the detection of low contrast edges. We demonstrate our mechanism on a real example, and evaluate the results using an artificial scene, where the ground truth data is available.</p>}},
  author       = {{Kalkan, Sinan and Wörgötter, Florentin and Yan, Shi and Krüger, Volker and Krüger, Norbert}},
  booktitle    = {{VISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings}},
  isbn         = {{9789898111210}},
  keywords     = {{Edge extraction; Feedback mechanisms; Rigid body motion; Signal-symbol loop}},
  language     = {{eng}},
  month        = {{12}},
  pages        = {{217--221}},
  title        = {{A signal-symbol loop mechanism for enhanced edge extraction}},
  volume       = {{2}},
  year         = {{2008}},
}