Automated vectorization of cartographic maps by a knowledge-based system

Developing an automated vectorizing system as an input method for a geograp hic information system (GIS) is of extreme importance due to the fact that an input process takes a lot of time and cost in constructing a GIS. Most v ectorizing systems require users to set the parameters as appropriately as possible for a particular map image, but it is quite difficult for a novice to adjust the parameters appropriately. This paper proposes a knowledge-ba sed system for automated vectorization, allowing an appropriate choice of t he parameters. Since thinning of the input image to produce a skeleton of u nit width is a prerequisite for the automated vectorization among several s teps, the performance of representative thinning algorithms is systematical ly evaluated in various map images, and appropriate rules for the maps are devised. Each rule in the knowledge base is characterized by the type of ma p, and by the resolution, line width, slope and protrusions. Experimental r esults with various map images show that the proposed system is superior in terms of performance and convenience of use. (C) 2000 Elsevier Science Ltd . All rights reserved.