Voronoi Diagram Based Automated Skeleton Extraction from Colour Scanned Maps

This paper presents a methodology to automate some parts of the manual digitization process. This includes replacing the manual digitization process by computer assisted skeletonization using scanned paper maps. In colour scanned paper maps various features on the map can be distinguished based on their colour. This research work utilizes the Delaunay triangulation and the Voronoi diagram in order to extract the skeletons that are guaranteed to be topologically correct. The features thus extracted as object centrelines can be stored as vector maps in a Geographic Information System after labelling and editing. Map updates are important in any Geographic Information System. Therefore, this research work can also be used for updates from sources that are either paper copy maps or digital raster images. A prototype application that is developed as part of the research has been presented.