Based on self-organizing network and fuzzy logic reasoning, this paper discusses an adaptive fuzzy rule classifier for landcover classification. The fuzzy rules can be extracted from the nodes and weight vector of network which can adjust the node numbers (rule number accordingly) and weight vector. This classifier finished TMlandcover by fuzzy logic reasoning, and the unclassified pixels increase K adaptively to be classified; It improved 2.7% and 2.9% in overall accuracy and Kapp coefficient compared with MLC, deceased 1% in Kapp coefficient and no change in overall accuracy compared with self-organizing network. How to extract and express the non-spectral knowledge dissolved class confusion, is the key step to improve the classification.
孙丹峰, 林培. 自适应模糊规则分类方法及在TM土地覆盖分类中的应用研究[J]. 国土资源遥感, 2000, 12(1): 44-50，56.
Sun Danfeng, Lin Pei . AN ADAPTIVE FUZZY RULE CLASSIFIER APPLIED TO LANDCOVER CLASSIFICATION OF TM. REMOTE SENSING FOR LAND & RESOURCES, 2000, 12(1): 44-50，56.
[1] Ncgia. The research plan of the national center for geographical information and analysis. Int J.Geographical Information Systems, 1989,3(2):117～136[2] Mooneyhan. The potential of expert systems for remote sensing application. InProc. IEEE Geosci Remote Sensing Symp. 1983,41～45[3] Wharton. A spectral knowledge－based approach for urban land－cover discrimination. IEEE Trans. Geosci Remote Sensing, 1987,25:272～282[4] Mckeown. The role of artifical intelligence in the tntergration of remotely sensed data with geographic information systems. IEEE Trans. Geosci Remote Sensing, 1987,25:330～348[5] Matsuyama. Knowledge－based aerial image understanding systems and expert systems for image processing. IEEE Trans. Geosci Remote Sensing, 1987,25:305～316[6] Wang. Improving remote sensing image analysis through fuzzy information representation. Photogrammetric Engineering & Remote Sensing, 1990,56:1163～1169[7] Benediktsson, Swain, Ersoy. Neural network approaches versus statistical methods in classification of multisources remote sensing data. IEEE Trans. Geosci. Remote Sensing, 1990,4:540～552[8] Foody. Using prior knowledge in artificial neural network classification with a minimal training set. Int J. Remote Sensing, 1995,12(6):301～312 [9] 孙丹峰,汲长远,林培.自组织网络在遥感土地覆盖分类中应用研究.遥感学报,1998,3(2): 139～143 [10] 孙丹峰,林培,汲长远.自组织网络与模糊规则结合在遥感土地覆盖分类中的应用研究.中国土地科学,1998,12(5): 42～44
2000, Vol. 12 
