DocumentCode :
2222536
Title :
Are multifractal multipermuted multinomial measures good enough for unsupervised image segmentation?
Author :
Kam, Lui ; Blanc-Talon, Jacques
Author_Institution :
Centre Tech. d´´Arcueil, France
Volume :
1
fYear :
2000
fDate :
2000
Firstpage :
58
Abstract :
By extending multinomial measures, a new class of self-similar multifractal measures is developed for texture representation. Two multifractal features have been shown to be suitable for texture discrimination and classification. Their use within a supervised segmentation framework provides us with satisfactory results. In this paper we complete the survey on these features by showing their rotation invariant property and their scaling behaviour. Both properties are particularly important for analyzing aerial images because the geographical elements can appear in different orientations and scales. Then, an automatic clustering algorithm based on a watershed technique is used for the segmentation of real world images. The experimental results are encouraging
Keywords :
image segmentation; image texture; aerial images; image segmentation; multifractal measures; multinomial measures; texture representation; Clustering algorithms; Filtering; Fractals; Geometry; Image analysis; Image segmentation; Image texture analysis; Information analysis; Satellites; US Department of Transportation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on
Conference_Location :
Hilton Head Island, SC
ISSN :
1063-6919
Print_ISBN :
0-7695-0662-3
Type :
conf
DOI :
10.1109/CVPR.2000.855799
Filename :
855799
Link To Document :
بازگشت