基于Fuzzy ARTMAP神经网络的景像匹配实时图选取方法

提出一种新的基于Fuzzy ARTMAP神经网络并利用图像直方图特征的快速景像匹配实时图选取方法。与已有的方法相比，该方法充分考虑了图像的边缘、亮度、对比度、信噪比等特征对影像实时图质量的影响，具有自适应聚类、收敛导速，实时性好，分类准确率高和通用性强等优点。将该方法应用于SMGS（景像匹配制导系统）进行实时图像的自动选取，可大大提高SMGS的智能性，可靠性和实时性。

Fuzzy ARTMAP Neural Network Based on Realtime Image Selection in Scene Matching

This paper presents a novel fast realtime image selection method using image histogram features which is based on the fuzzy ARTMAP neural network.Compared with the previous method,the edge,brightness,contrast and SNR feature of its images are taken into account in this method,and it has many advantages such as selfadaptive clustering,fast convergence,good realtime ability,high classification accuracy and high universality, etc.It can be adopted in SMGS (scene matching guidance system)to autoselect realtime images,so it improves the level of intelligence,reliability and realtime ability of SMGS.