Use of self-organized maps for feature extraction of hyperspectral data.

摘要

In this paper, the problem of analyzing hyperspectral data is presented. The complexity of multi-dimensional data leads to the need for computer assisted data compression and labeling of important features. A brief overview of Self-Organizing Maps and their variants is given and then two possible methods of data analysis are examined. These methods are incorporated into a program derived from som_toolbox2. In this program, ASD data (data collected by an Analytical Spectral Device sensor) is read into a variable, relevant bands for discrimination between classes are extracted, and several different methods of analyzing the results are employed. A GUI was developed for easy implementation of these three stages.