本文针对遥感图像分类的特点 ,提出了一种基于模糊B样条基函数神经网络的遥感图像分类器。该分类器采用B样条函数作为模糊隶属函数 ,将模糊技术与神经网络相结合 ,利用神经网络实现模糊推理 ,从而使系统具备了自适应的特性。实验结果表明 ,这种基于模糊B样条基函数神经网络的分类器经过训练后 ,可应用于遥感图像的分类 ,其分类精度明显高于传统的最大似然分类法 Aiming at the characteristics of remote sensing image classification, this paper proposes a remote sensing image classifier based on fuzzy B-spline basis function neural network. The classifier adopts B-spline function as fuzzy membership function, combines fuzzy technology with neural network, and uses neural network to realize fuzzy reasoning, so that the system possesses adaptive characteristics. Experimental results show that this classifier based on fuzzy B-spline basis function neural network can be applied to the classification of remote sensing images after training, and its classification accuracy is obviously higher than the traditional maximum likelihood classification