Color space selection for unsupervised color image segmentation by histogram multi-thresholding

We propose a new color image segmentation algorithm by unsupervised classification of pixels. This procedure iteratively constructs the classes by histogram multi-thresholding. For this purpose, the procedure selects different color spaces in which the modes of the 1D-histograms are separated as wel...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Busin, L., Vandehbroucke, N., Macaire, L., Postaire, J.G.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Classification algorithms Computer hacking Computer Science Computer Vision and Pattern Recognition Histograms Image analysis Image color analysis Image segmentation Iterative algorithms Pixel Space technology
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	We propose a new color image segmentation algorithm by unsupervised classification of pixels. This procedure iteratively constructs the classes by histogram multi-thresholding. For this purpose, the procedure selects different color spaces in which the modes of the 1D-histograms are separated as well as possible, so that each mode corresponds effectively to a region in the image.
ISSN:	1522-4880 2381-8549
DOI:	10.1109/ICIP.2004.1418725