模糊神经网络在台风云系图象识别中的应用  

The Application of Fuzzily Neural Network to Picture Recognition of Typhoon Clouds

作　　者：于波[1] 冯民学[1] 陈必云[1] 

机构地区：[1]江苏省气象台

出　　处：《气象》1996年第1期22-25,共4页Meteorological Monthly

基　　金：中国气象局科教司青年基金

摘　　要：利用数学形态学方法对台风云系进行区域分割，计算并统计出了台风云系纹理特征的概率密度，然后结合模糊判别技术，利用多层神经网络对ＧＭＳ云图的台风云系进行图象识别，结果表明，该方案是成功的。Using the method of maths morphology,the area-spliting of typhoon clouds is conducted,and the possibility density of grain features of typhoon clouds is statistically analysed.Combined with the method of fuzzily discriminant and multi-level neural network, the typhoon clouds' picture recognition of GMS satellite image is studied. The result suggests thatthe method in successful.

关 键 词：台风 云系 模糊判别 模糊神经网络 

分 类 号：P444[天文地球—大气科学及气象学]