基于主成分分析的自组织竞争神经网络在多光谱遥感影像分类中的应用

Self-Organizing Competition Neural Network Based on Principle Component Analysis in Multi-Spectrum Remote-Sensing Images Classification

多光谱遥感影像具有波段多、信息量大的特点,传统的分类方法难以达到提高精度的要求。利用主成分分析对多波段遥感图像进行降维,再采用竞争型自组织神经网络对图像进行非监督分类。这种方法的分类精度为87.5%,Kappa系数为0.86,明显高于最大似然法,最小距离法和基于像元的自组织竞争神经网络法。实验结果表明该方法在多光谱遥感影像分类中具有较好的适用性。

Due to the characteristics of many wavebands and large information quantity, multi-spectrum remote-sensing images are difficult to be classified with high accuracy by traditional methods. In this paper, we reduce the dimensions of multi-spectrum remote-sensing images with principle component analysis at first, and then perform unsupervised classification with self-organizing competition neural network. The classification accuracy of this method is 87. 5% and the Kappa coefficient is 0. 86. They are obviously higher than that of conventional maximum likelihood method, minimum distance method and selforganizing competition neural network method based on pixels. The results indicate this method can be well applied in multi-spectrum remote-sensing images classification.