Share Email Print

Proceedings Paper

Noise reduction in multispectral images using the self-organizing map
Author(s): Pekka J. Toivanen; Mikko Laukkanen; Arto Kaarna; Jarno S. Mielikainen
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, a new group of noise reduction methods for multispectral images is presented. First, a 1-dimensional Self-Organizing Map (SOM) is taught using the pixel vectors of the noisy multispectral image. Then, a gray-level index image is formed containing the indexes of the SOM vectors. Several gray-level noise reduction methods are applied to the index image for three noise types: impulse, Gaussian, and coherent noise. Tests are made for three kinds of noise distrubutions: for all channels, for channels 30-50, and for 9 selected channels. Error measures imply that the obtained results are very good for coherent noise images, but rather poor for other noise categories, compared to the bandwise coherent filter.

Paper Details

Date Published: 2 August 2002
PDF: 7 pages
Proc. SPIE 4725, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII, (2 August 2002); doi: 10.1117/12.478751
Show Author Affiliations
Pekka J. Toivanen, Lappeenranta Univ. of Technology (Finland)
Mikko Laukkanen, Lappeenranta Univ. of Technology (Finland)
Arto Kaarna, Lappeenranta Univ. of Technology (Finland)
Jarno S. Mielikainen, Lappeenranta Univ. of Technology (Finland)

Published in SPIE Proceedings Vol. 4725:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery VIII
Sylvia S. Shen; Paul E. Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top