Application of neural networks to terrain classification
Application of neural networks to terrain classification
复制标题
神经网络在地形分类中的应用
DOI：
10.1109/ijcnn.1989.118592
复制
发表时间：
1989
期刊：
影响因子：
--
通讯作者：
Scott E. Decatur
中科院分区：
文献类型：
--
作者：
Scott E. Decatur
本文报道了神经网络在雷达地形图像分类中的应用研究结果。介绍了神经网络方法，并与传统的贝叶斯最大似然估计分类方法进行了比较。以前被认为是最优的性能被证明是通过使用神经网络来改进的。所示结果推广到目前使用贝叶斯分类的所有应用。
Results of an investigation into the applicability of neural networks to the classification of radar terrain images are reported. The neural network approach is described and compared with the conventional technique of Bayesian classification with maximum-likelihood estimation. Performance that was previously thought to be optimal is shown to be improved upon by the use of neural networks. The results shown generalize to all applications currently employing Bayesian classification.<<ETX>>