基于距离变换的提取和识别点状符号的方法  

Extracting and Identifying Point Symbols Based on Distance Transform

作　　者：陈飞[1] 胡鹏[1] 王秀芳[2] 王坤[1] 

机构地区：[1]武汉大学资源与环境科学学院 [2]武汉大学遥感信息工程学院,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2007年第12期1172-1175,共4页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(40471107;40464006;40571124)

摘　　要：提出了一种基于距离变换提取和识别点状符号的新方法。首先对分版图的提取结果进行优化处理,然后根据弯曲密度和线划密度等特征,进一步过滤掉不满足点状符号特征的线划。为了更准确地度量图像间的相似性,提出了加权距离函数,并用该函数值为度量标准进行模板匹配以识别符号。该算法较好地解决了字线粘连、背景复杂等情况下的点状符号提取和识别问题,识别准确率较高。A new method for extracting and identifying point-shaped symbols of scanned top-ographic maps based on map algebra is presened. The extracting results of element maps are optimized and the lines which do not meet the features of point symbols are filtered according to curve density and line density. Weighed distance function, and identify symbols using the method of template matching are put forward according to the function results. The algo-rithm can work out the problems of extracting and identifying point symbols in the condition of character ＆ line conglutination or complex background, and it achieves a high level of recognition accuracy.

关 键 词：模式识别 点状符号 距离变换 模板匹配 符号识别 

分 类 号：P283.1[天文地球—地图制图学与地理信息工程]