Application Research On Remote Sensing Image Classification Based On Classification Method Of CPN

RS technology has good advantages on dynamic cycle, data, abundant information and easily acquisition as a tool in age of information, so it is the most effective technology and means of obtaining space-time information. RS image is mostly used to map relief maps, make orthograph and thematic maps by professional interpretation, which can be saved in the databases of geographical information system (GIS) or updated the GIS databasesRS image classification is that use the difference of the ground objects'spectrum energy characteristic and the structure characteristic to distinguish the ground objects information in the certain time. The remote sensing image classification is the important method to carry on information extraction.With the remote sensing technology development, the traditional classification methods have demonstrated the obvious insufficiency.In order to obtain more effective information, and enhance classification precision, people have conducted a lot of research, in summary it induces mainly two aspects: one thing, seeking new and more effective classification methods; for another, adding new data source and using the multisource data to participate in classification research. Remote sensing image classification is the concrete application of the pattern recognition technology in the remote sensing domain. In recent years,with the pattern recognition and the artificial intelligence theory rapid development, especially the artificial neural network technology started and the application, the remotesensing image automatic classification method gradually is making great strides forward to the practical direction. This article is based on the research of the tradition classification method,and has also conducted the research of the neural network classification.In summary, following the mainly researches are carried out in this dissertation:1)The feature extraction, pattern classification method, and specially the statistics pattern classification method are thoroughly disscussed in detail.2) The process of the remote sensing image classification is disscussed in detail, and the concrete process is achieved by using erdas software.3)The basic thought and the algorithm flow of CPN are studied,the algorithm of CPN is analyzed, in foundation of which one kind of improved classification method of CPN is proposed, and the general model of the remote sensing image supervised classification is stablished in foudation of improved CPN classification method.4)The classification result is evaluated, the different classification results which are obtained by different classification methods iscompared and analyzed.