一种基于知识的自然景物解释

利用我们研制成的基于知识的区域分析系统,我们对自然景物图象做了分析、解释。本文介绍:(1)图象初始分割;(2)图象特征提取;(3)规则集构造。这里,图象初始分割采用的是模糊域方法,它基于Fuzzy C-means 算法,并在此基础上修改了收敛准则,增加了迭代分割功能。图象特征分为主持征及从特征,它们建立在层次化的区域数据结构上。适合于区域分析的规则集已包括三类规则,它们不仅具有较强的知识表示能力,而且易于控制及利用。本文介绍针对包括天空、道路、树木、建筑物等物体的简单景物图象所做的解释实验,并给出了实验结果.

This paper consists or three parts:(1)initial image segmentation;(2)image fea-ture extraction;(3)rule set organization.Based on a Knowledge-Based Region Ana-lysis System,some experiments on interpretation of natural scenes have been made.Three tyPes of rules which are preforable to region analysis have been proposed.Theyare easy to control and utilize.The experiments on interpretation of natural scenes which contain sky,road,tree,buildings,etc.are introduced and the results are enclosed in the paper.