Knowledge-Based System for Color Maps Recognition
In this paper, we describe the Fine-to-Coarse Scale Method in which the knowledge of cartographic patterns into small-scale map aids to recognize the corresponding patterns into large-scale map of the same territory. This approach exploits the user’s experience providing the knowledge domain in the form of the prescribed feature-attribute set. The cartographic patterns are presented in raster maps. A map is composed by thematic layers that contain cartographic patterns. The knowledge to recognize cartographic objects in raster fine scale maps is based on the information about the objects of the coarse scale map. These recognized objects are removed from the map, reaching a simplified representation of the map. Then, the rest of objects are recognized as new cartographic material in this simplified map. The goal of these representations is to obtain a GIS database.
Unable to display preview. Download preview PDF.
- 1.Levachkine, S.P., Polchkov, E.A.: Integrated Technique for Automated Digitization of Raster Maps. Revista Digital Universitaria 1(1) (2000), Available on-line at http://www.revista.unam.mx/vol.1/art4/index.html
- 3.Meyers, G.K., Chen, C.-H.: Verification-based Approach for Automated Text and Feature Extraction from Raster-scanned Maps. LNCS, vol. 1072, pp. 190–203. Springer, Heidelberg (1996)Google Scholar
- 4.Gonzalez-Gómez, E., Levachkine, S.: Color cartographic pattern recognition using the coarse to fine scale method. LNCS, vol. 3287, pp. 540–547. Springer, Heidelberg (2004)Google Scholar
- 8.Torres-Ruiz, M., Levachkine, S.: Semantics Definition to Represent Spatial Data. In: Levachkine, S., Ruas, A., Bodansky, E. (eds.) Proc. International Workshop on Semantic Processing of Spatial Data (GEOPRO 2002), Mexico City, Mexico, December 3-4 (2002)Google Scholar