Share Email Print

Proceedings Paper

Experiences from operational cloud classifier based on self-organizing map
Author(s): Ari J. E. Visa; K. Valkealahti; Jukka Iivarinen; O. Simula
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A new operational system to interpret satellite images is represented. The described method is adaptive. It is trained by examples. In the reported application a combination of textural and spectral measures is used as a feature vector. The adaptation or learning of the extracted feature vectors occurs by a self-organizing process. As a result a topological feature map is generated. The map is identified by known samples, examples of clouds. The map is used later on as a code book for cloud classification. The obtained verification results are good. The represented method is general in the sense that by reselecting features it can be applied to new problems.

Paper Details

Date Published: 2 March 1994
PDF: 12 pages
Proc. SPIE 2243, Applications of Artificial Neural Networks V, (2 March 1994); doi: 10.1117/12.169997
Show Author Affiliations
Ari J. E. Visa, Helsinki Univ. of Technology (Finland)
K. Valkealahti, Helsinki Univ. of Technology (Finland)
Jukka Iivarinen, Helsinki Univ. of Technology (Finland)
O. Simula, Helsinki Univ. of Technology (Finland)

Published in SPIE Proceedings Vol. 2243:
Applications of Artificial Neural Networks V
Steven K. Rogers; Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top