| Abstract: | In this paper an experiment in the application of LANDSAT MSS digital image proces. sing technique to classify the aquatic plants in the Honghu Lake, China, as well as the necessary ground feature spectrum measurement and plant chlorophyll content determination techniques are introduced. In order to obtain the expected computer aided classification result different methods of digital image feature extraction have been tried, namely the ratio transformation, the biomass index transformation and the linear stretching of image intensity. The data from spectrum measurement and chlorophyll content determination were used to distinguish the attributions of different classes of aquatic plant associations from one another by comparing with their spectrum response intensity values on different LANDSAT band images. The original LANDSAT MSS images were digitally rectified by control points to a certain map projection system using a general polynomial approach scheme before the classifying activities, so that the classification result may be transfered to an existing map. In this paper the resulting colourassigued image and the thematic map of Honghu Lakes aquatic plant (association) distribution are included, the areas of different classes of aquatic plants are listed and the reliability of the resulting classification and pattern recognition are analysed. These results will provide useful informations for the investigation of the present situation as well as the historical succession of the Honghu Lake and its aquatic plant distribution, and also for the research works of the lake management. |
