Abstract:
This paper presents a preliminary study on usage of Artificial Neural Network (ANN) for land cover classification using multispectral remotely sensed data. The ANN model used is a simple multi-layer perceptron trained through generalized delta learning rule. Performance of the ANN classifier has been assessed with reference to the conventional maximum likelihood (MXL) classifier. In the current study, it is found that the ANN classifier has a better classification accuracy than the MXL classifier.
