Applying Self-Organizing Map to Select Landsat TM Difference Features for Forest Change Analysis
Efficient use of multitemporal Landsat thematic mapper (TM) information in forest change detection requires that the best features from the huge amount of data can be selected for the task. This paper shows how the Self-Organizing Map (SOM) can be used as a tool for evaluating the class discriminatory potentials of different features and for selecting suitable features for the change detection task.
Bibliographic Reference: Paper presented: International Conference on Engineering Applications of Neural Networks, London (GB) June 17-19, 1996
Availability: Available from (1) as Paper EN 39777 ORA
Record Number: 199610683 / Last updated on: 1996-06-21
Original language: en
Available languages: en