Feature-based fuzzy-neural network approach for target classification and recognition in remote sensing images
基于特征的模糊神经网络遥感图像目标分类识别

Feature is themostessentialattribute for recognizing target in image processing. This paperproposes to recognize ship targetby utilizing a fuzzy neuralnetwork processing on its geometry, momentand texture features. Firs,t we simply depictgeometry feature andmoment feature especiallyHumomen.t After tha,t we respectively extractand analyze geometry, Humomentand texture feature of ship target in simulated and satellite observed data, as well as ship target acquired by automatic target detection. By analyzing the ship target s features, the feature set( or subset), comprising geometry, Humomentand texture feature, can be used to recognize ship targe.t Fuzzy-neuralnetworkmethod can combine fuzzy set s advantageswith neuralnetwork s, bywhich feature- based classification and recognition for targets in images can be implemented validly. The paper depicts a fuzzy-neural network methodwith principal-subordinate neuro for classification and recognition at firs,t and then, utilize the method to classify and recognize, basing on single category feature and multi-source (multi-temporal) data fusion. Experiments results indicates that classification and recognition for large ship can be implemented validly by utilizing fuzzy-neural network methods based on large ships geometry features, moment features and texture features. Furthermore, usingmulti-source data fusion, the classification and recognition effectcan be improved.