概率神经网络在超谱图像分类中的应用

Research on Application of Probability Neural Network in Hyperspetral Image Classification

针对超谱图像高维光谱信息给传统分类带来的困难,结合径向基神经网络的原理,提出了一种概率神经网络分类方法。并将其成功应用到具体超谱图像数据中,验证了概率神经网络分类器的有效性。通过实验仿真,研究了特征向量维数对分类结果的影响,证明概率神经网络可应用于大于100个波段的超谱图像数据。

Aiming at based on the theory of method is illustrated, tion. research on the the difficulty of traditional classification brought by hyperspectral image＇s high dimension, radical basis function network, a kind of PNN （Probability Neural Network） classification and its affectivity is verified by its application in hyperspectral image. Through the emula-effect of feature image＇s dimensions to classification result, proves the PNN＇s applicability high dimension hyperspectral image.