DocumentCode :
3629040
Title :
Segmentation of hyperspectral images using fuzzy approaches
Author :
Gokhan Bilgin;Sarp Erturk;Tulay Yildirim
Author_Institution :
Elektronik ve Haberle?me M?hendisli01E7i B?l?m?, Yildiz Teknik ?niversitesi, Turkey
fYear :
2008
fDate :
4/1/2008 12:00:00 AM
Firstpage :
1
Lastpage :
4
Abstract :
In this paper fuzzy clustering algorithms are utilized for the segmentation of hyperspectral images. For this purpose fuzzy c-means and an extended version of this algorithm, namely the fuzzy Gustafson-Kessel algorithms are used. Because of the high dimensionality in hyperspectral images, the data dimension is reduced using the Discrete Wavelet Transform. The advantage of using fuzzy approaches for the segmentation is that for every pixel fuzzy membership degrees can be obtained. Hereby, a novel method which includes the utilization of spatial information is developed for segmentation with increased accuracy. The method is called dasiawithin kernel phase correlationpsila. Furthermore, it is shown that by two- and three-dimensional Gaussian filtering of the fuzzy membership cube the accuracy can be increased.
Keywords :
"Kernel","Hyperspectral imaging","Hyperspectral sensors","Remote sensing","Image segmentation","Clustering algorithms","Feature extraction"
Publisher :
ieee
Conference_Titel :
Signal Processing, Communication and Applications Conference, 2008. SIU 2008. IEEE 16th
ISSN :
2165-0608
Print_ISBN :
978-1-4244-1998-2
Type :
conf
DOI :
10.1109/SIU.2008.4632552
Filename :
4632552
Link To Document :
بازگشت