A method to classify precipitation events based on their intensity, spatial extend, and texture has been developed. The method allows to distinguish large-scale precipitation features typically associated with frontal systems from more small-scale features which are usually found in isolated convective cells. The classification is performed in three steps. Firstly, contiguous precipitation areas are identified in the radar data. In a second step, each of these areas is subjected to an analysis where different texture parameters are calculated. In a third step, these texture parameters are evaluated by means of a neural network and a type of precipitation is assigned to each class. The neural network has been trained using a large set of visually classified radar scenes. A validation of the results has been performed by (1) evaluating the classification results by eye (2) comparing regions where forecasts identify large contiguous frontal areas and (3) by using surface observation where the surface observer reported intermittet rainfall. While all of these methods (including the here presented classification) inhere some degree of subjectivity, the results of the comparison are in good agreement.