Satellite image classification using Modified Counter-Propagation
Abstract
A supervised classifier for satellite images by the Modified Counter-Propagation (MCP) is proposed. The MCP is a neural network for competitive learning. It is the modified version of the Counter-Propagation, whose competitive layer has been replaced by the Self-Organizing map (SOM). The Landsat image data are adopted as the input data of the MCP, and the output layer consists of the pixel values, which represent categories to be classified. Our results shows that the MCP can classify the data more accurately and stably than can the SOM only, especially in the case of classification of vegetation, farm and wood.
Fields of Study & Subjects
Remote-Sensing Image Classification
Neural Networks and Applications
Remote Sensing and Land Use
Publication details
- Journal / source
- CRC Press eBooks
- Pages
- 89–97
- Publication date
- 11 February 2026
- Language
- EN
- Document type
- Book chapter