专题图注记信息去除方法探讨

Study on Removing Annotations from Thematic Map

注记信息的存在使得从专题图自动获取矢量数据具有一定难度。该文提出一种去除专题图注记信息的有效方法:在区分出注记信息的基础上,利用空间最近邻原则对注记进行背景填充,然后利用ArcObjects构建该功能模块,并与ArcGIS集成。研究表明,该模块能有效去除专题图注记信息,使ArcScan从专题图自动提取高精度矢量数据成为现实。

It is difficult to automatically and accurately extract vector data from thematic map because of annotations. Therefore, a modal of removing annotations from thematic map named Background Painting is discussed in this paper. Firstly, the color difference equation LCH is applied to the thematic map to identify annotations. When the maximum thresholds of △L（lightness difference） and △C（chroma difference） and △H（hue difference） are defined, the pixels of thematic map fall into two groups： background pixels and annotation pixels. As a result, the thematic map can be considered as a binary image. Then, a method similar to the algorithm of dilation is used to remove annotations. Because mainly used for binary image, the algorithm of dilation is developed in this paper. The annotation pixel value is replaced by its nearest background value but not a single value. Finally, the model for removing annotations from thematic map is developed based on ArcObjects and integrated with ArcGIS. The study shows that the model can be applied to remove annotations from thematic map effectively, so that the vector data can be obtained automatically and accurately from thematic maps by using ArcScan of ArcGIS.