Skip to Main Content
A classification of remote sensing data by using several classifiers and neural networks is presented in this paper. The application was conducted using a scene about agricultural areas, and it contains several agricultural classes. Several classification methods were compared and tested over a multispectral scene containing agricultural classes using a data base, and the Hybrid Learning Vector Quantization neural network approaches are used to classify multispectral TM images. The main result obtained in this paper is that the neural network considered here provides a satisfying effect for the classification of agricultural multispectral images, and it means that this neural network architecture may be considered as a good alternative to the classical Bayesian method, especially when processing hyper-spectral data where several hundreds of spectral bands have to be considered together.