Fuzzy direction field method for fringe and tree-like patterns analysis
The problem of geometrical structure detection and measurements for fringe patterns and tree-like objects images is considered. We introduce the notion of a local-structure function that generalizes the concepts of direction and spatial frequency fields and describes local geometrical properties of...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Tagungsbericht |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The problem of geometrical structure detection and measurements for fringe patterns and tree-like objects images is considered. We introduce the notion of a local-structure function that generalizes the concepts of direction and spatial frequency fields and describes local geometrical properties of the images under study. It can be considered as a fuzzy set of directions and spatial frequencies in every point of image. On basis of fuzzy sets operations we develop a number of general-purpose image analyzing algorithms that have parametrical tuning on image type. We have shown experimentally that this approach allows us to analyze efficiently various technical and medical diagnostic images of specified classes, such as interference patterns, objects registered in structural light, blood vessels images, and so on. |
---|---|
ISSN: | 1051-4651 2831-7475 |
DOI: | 10.1109/ICPR.2004.1334374 |