基于神经网络的点状地图符号识别  

The Identification of Point Map Symbols Based on Neural Networks

作　　者：昝秀红[1] 付和[2] 黄静新[1] 

机构地区：[1]河北省地勘局测绘院,河北廊坊065000 [2]河北中色测绘中心,河北三河065201

出　　处：《测绘与空间地理信息》2008年第6期183-186,共4页Geomatics & Spatial Information Technology

摘　　要：地图符号识别是地图成图自动化的一个重要研究方向,但是传统的地图符号识别方法已经不能满足数字地图发展的需要,迫切需要一种用自动化技术代替人工数字化的作业方式[1]。因此地图符号的识别是整个技术的关键,而点状地图符号的识别更是地图符号识别的基础。本文探讨和研究了基于神经网络的点状地图符号识别。Map symbols identification is an important research direction for map production automation, but the traditional map symbols identification methods can not meet the requirements of development of digital map. Thus,it is necessary to develop a kind of automation technique to replace the method of manual digitization work. It is the whole technical key to identify the map symbol, but the identification of point map symbols is the basic and key for map symbol identification. This paper discussed and studied the identification of point map symbols based on neural network.

关 键 词：点状符号 神经网络 识别模型 HOPFIELD网络 

分 类 号：P283.1[天文地球—地图制图学与地理信息工程]