Remotely Sensed LANDSAT Image Classification Using Neural Network Approaches

In paper, LANDSAT multispectral image is classified using several unsupervised and supervised techniques. Pixel-by-pixel classification approaches proved to be infeasible as well as time consuming in case of multispectral images. To overcome this, instead of classifying each pixel, feature based classification approach is used. Three supervised techniques namely, k-NN, BPNN and PCNN are investigated for classification using textural, spatial and spectral images. Experiments shows supervised approaches perform better than unsupervised ones. Comparison between k-NN, BPNN, and PCNN is done using these features and classification accuracies for BPNN is found out to be more than k-NN and PCNN.