A curve tracing algorithm using level set based affine transforms

Existing curve tracing algorithms drive an evolving curve to the mean or median of the data. However, if the data set contains heavy noise, these algorithms may not produce correct results. In this paper, we introduce a level set based affine transform method to enhance the capability of a class of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2005 IEEE International Conference on Systems, Man and Cybernetics Jg. 3; S. 2667 - 2672 Vol. 3
Hauptverfasser: Lam, B.S.Y., Van, H.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 2005
Schlagworte:
Affine transform
Clustering algorithms
Data engineering
Data mining
Drives
Equations
Fuzzy curve-tracing (FCT) algorithm
Fuzzy sets
Image processing
Information technology
Level set
Level set method
Pattern thinning
Shape
Skeletonization
ISBN:9780780392984, 0780392981
ISSN:1062-922X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Existing curve tracing algorithms drive an evolving curve to the mean or median of the data. However, if the data set contains heavy noise, these algorithms may not produce correct results. In this paper, we introduce a level set based affine transform method to enhance the capability of a class of fuzzy curve tracing algorithms. The essential idea of our approach is to drive the initial curve towards the object data using level sets as well as affine transforms. Experimental results show that the proposed method can enhance fuzzy curve tracing algorithms for dealing with the data corrupted by noise.
ISBN:9780780392984
0780392981
ISSN:1062-922X
DOI:10.1109/ICSMC.2005.1571552