DocumentCode :
295947
Title :
Unsupervised classification of Antarctic satellite imagery using Kohonen´s self-organising feature map
Author :
Kilpatrick, D. ; Williams, R.
Author_Institution :
Dept. of Appl. Comput. & Math., Tasmania Univ., Launceston, Tas., Australia
Volume :
1
fYear :
1995
fDate :
Nov/Dec 1995
Firstpage :
32
Abstract :
This paper describes an investigation into the use of Kohonen´s self-organising feature map (SOM) for the classification of remotely sensed imagery of Antarctica. The SOM is an unsupervised neural network which is trained using unlabelled input data. The network consists of a grid of nodes and, after training, each node corresponds to a prototype vector in the input data space. In order to use the trained SOM as an image classifier it is necessary to calibrate the grid of prototype vectors whereby the prototype vectors are clustered and these clusters mapped to physical class labels. The K-means iterative clustering technique is demonstrated as a means of performing this clustering. However this method requires the user to specify the number of clusters to be formed. The U-matrix method is investigated as a way of identifying the number of clusters represented by the grid of prototype vectors
Keywords :
geophysical signal processing; geophysics computing; image classification; oceanographic regions; oceanographic techniques; remote sensing; sea ice; self-organising feature maps; unsupervised learning; Antarctic satellite imagery; K-means iterative clustering; K-means iterative clustering technique; Kohonen; Kohonen´s self-organising feature map; Southern Ocean; U-matrix method; coast; image classification; image classifier; measurement technique; ocean; optical imaging; remote sensing; remotely sensed imagery; sea ice; unlabelled input data; unsupervised classification; unsupervised neural network; Antarctica; Earth; Humans; Mathematics; Neural networks; Pixel; Prototypes; Satellites; Sea ice; Sea surface;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
Type :
conf
DOI :
10.1109/ICNN.1995.487872
Filename :
487872
Link To Document :
بازگشت