Intelligent Recognition Of Electronic Maps Of Geographic Objects To Study

Obtaining and recognizing geographic information is the foundation of Geographic Information System (GIS). Existing vectorization methods usually take a two-phase workflow: convert a raster image to raw vectors and recognize graphic objects from the raw vectors. The first phase separates a graphic object into several parts, thus, the second phase faces the difficulty of searching for and merging raw vectors belonging to the same object. These operations slow down vectorization and degrade the recognition quality. Imitating the way of which humans read maps this paper introduces the complete concept of direct object-oriented vectorization. An automatic vectorization system using this method is also established on the Visual C++ 6.0 environment.The idea of object-oriented is introduced in this paper, the geographic elements in the map are classified into line, symbol and text, and line furthermore into bar, arc (circle) and curve. This method recognizes each class of graphic objects from their natural characteristics. Each graphic object is recognized directly in its entirety at the pixel level. To vectorize the bar and arc objects accurately, the character segment is introduced as the guidance of geometrical parameters. The raster image is progressively simplified by erasing recognized graphic objects to eliminate their interference with subsequent recognition. Moreover using operations of mathematic morphology, this paper revectorizes the recognized map, the system using the method shows the significant improvement in speed and recognition quality.At present the research about vectorization is mainly among the CAD/CAM, the method designed in this paper realizes the interface with Mapinfo, a GIS software. This paper satisfies the demand of GIS.