摘要：Map would be the most critical information in daily real-world activities. Due to the advance of the Web and digital map processing techniques, we can now easily find various maps of different presentations appropriate to diverse user purposes such as trivial searching for a restaurant or consulting a path during a trip. However, maps served by today’s representative map search engines such as Google Maps cannot satisfy all users whose map-reading ability and search purposes are quite different. Thus, map search engine need to provide maps well represented for specific needs. Nowadays, there are numerous numbers of map contents available on the web, which are appropriately well drawn and shared on various web sites. However, it is not an easy task for users to find out appropriate maps on the Web. In order to support user's map search on the Web, we developed a map search system, which can search for map contents drawn in various viewpoints by interacting with users based on a relevance feedback. In particular, we analyze each map content according to two distinguishing features, geographical features and image features. Significantly, the proposed system can deal with visual map contents by considering how the map contents are represented. In this paper, we analyze effective features based on user intention for map search.
