A Study on the Rule-Based Selection of Training Set for the Classification of Satellite Imagery


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 3, No. 7, pp. 1763-1772, Dec. 1996
10.3745/KIPSTE.1996.3.7.1763,   PDF Download:

Abstract

The conventional training set selection methods for the satellite image classification usually depend on the manual selection using data from the direct measurements of the ground or the ground map. However this task takes much time and cost, and some feature values vary in wide ranges even if they are in the same class. Such feature values can increase the robustness of the neural net but learning time becomes linger. In this paper, we propose a new training set selection algorithm using a rule-based method. By the technique proposed, the SPOT multispectral Imagery is classified in 3 bands, and the pixels which satisfy the rule are employed as the training sets for the neural net classifier. The experimental results show faster initial covergence and almost the same or better classification accuracy. We also showed an improvement of the classification accuracy by using texture features and NDVI.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
U. G. Mun and L. K. Hi, "A Study on the Rule-Based Selection of Training Set for the Classification of Satellite Imagery," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 3, no. 7, pp. 1763-1772, 1996. DOI: 10.3745/KIPSTE.1996.3.7.1763.

[ACM Style]
Um Gi Mun and Lee Kwae Hi. 1996. A Study on the Rule-Based Selection of Training Set for the Classification of Satellite Imagery. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 3, 7, (1996), 1763-1772. DOI: 10.3745/KIPSTE.1996.3.7.1763.