Intelligent Recognition Research On Geographic Elements In Scanned Map

The extraction of recognition of the geography information is the basic of geographic information system (GIS) and global position system (GPS). Automation vectorization has transcendent advantages in efficiency, precision and reliability and has become the main method of getting digital information. After having studied the recent methods, combined the characters of scanned maps images, the author designs a method to recognize and capture the digital geography information, which is based on thinning algorithm. A map vectorization system is also realized by this method in the Visual C++ programming environment.The current prevalent vectorization method based on thinning algorithm is adopted in the paper. Words labels in the scanned gray map are separated from the map using MAS wavelet transform theory which is much better than classic theory like Canny, Sobel etc. It can not only extract the geographic information availably, but also have a good work in noise elimination. In the process of thinning the image, a new thinning method keeping node area based on labeling is put forward. Compared with the traditional thinning algorithm, the method avoids the node distortion and changing the map topology.In the process of vectorization, the node area and connected segment are abstracted according to the whole topology of map. The connected segment is transformed into its vector form by improved variable-step-length vectorization method. The longest expended principle is used to combine the vector segment, and then the nodes are ensured and the last vector list is got. The erasing process after thinning and segment code avoids re-recognition and reducing the complexity. So the speed is improved.At present the research on vectorization is mainly among the engineering image. The method proposed in the paper satisfies the demand of GIS and realizes the interface with MapInfo which is a kind of GIS software. The experimental results show that the improved method can reestablish the map's topology faster and better, and improve precision and speed obviously. It has certain significance and application value in the field of GIS.