Training Strategies for Neural Network Soft Classification of Remotely Sensed Imagery.
Evidence from the recent literature demonstrates little progress in discrete (hard) classification of land cover from remotely sensed imagery. An empirical study is presented to test training procedures with neural networks for soft (mixture) classification. The results show that land cover mixtures are best recognized following training with two-component mixed pixels, and that linearly re-scaled or binneed target vector representations are equally satisfactory.
BERNARD Alice;
KANELLOPOULOS Ioannis;
1996-08-06
JRC13602
https://publications.jrc.ec.europa.eu/repository/handle/JRC13602,
Additional supporting files
| File name | Description | File type | |
|---|
