基于人工神经网络的遥感图像分类研究

Studies on Classification of Remote Sensing Image Processing Based on Artificial Neural Network

随着人工神经网络系统理论的发展,神经网络技术日益成为遥感图像分类处理的有效手段,并有逐步取代最大似然法的趋势。本文重点讨论了遥感图像分类处理研究中应用效果显著的BP神经网络方法,并在MATLAB平台下对基于BP神经网络的分类算法进行了研究,最后将它的分类结果与最大似然法的分类结果进行了精度比较分析。结果表明基于BP神经网络的遥感图像分类效果是较好的,是一种有效的图像分类方法。

With the development of the theory about Artificial Neural Network（ANN）system, the neural network technology is becoming increasingly an effective means of classification processing of remote sensing digital images and beginning to replace the Maximum Likelihood Classifier （MLC）. This paper mainly discusses the method of BP Neural Network that have been very effectively applied to remote sensing digital hnage processing and presents the classification algorithm of BP Neural Network developed using Madab. At last, its classification accuracy is compared to maximum likelihood classifier（Bayes）. The results show that the classification method based on BP neural network is an effective approach.