Classification of satellite cloud imagery based on multi-feature texture analysis and neural networks

The aim of this work was to develop a system based on modular neural networks and multi-feature texture analysis that facilitates the automated interpretation of cloud images. This speeds up the interpretation process and provides continuity in the application of satellite imagery for weather forecasting. A series of infrared satellite images from the geostationary satellite METEOSAT7 were employed. Nine different texture feature sets (a total of 55 features) were extracted from the segmented cloud images using the following algorithms: first order statistics, spatial gray level dependence matrices, gray level difference statistics, neighborhood gray tone difference matrix, statistical feature matrix, Laws texture energy measures, fractals and Fourier power spectrum. The neural network SOFM (self organising feature map) classifier and the statistical KNN (Kohonen neural network) classifier were used for the classification of the cloud images. Furthermore, the classification results of the different feature sets were combined improving the classification yield to 91%.