Automatic interpretation of cadasters by image analysis techniques

Vectorization plays an important role for map interpretation in geographic information systems. A new method to convert a raster map into a vector is proposed. A scanner was used to convert the paper source map into a raster representation. Text and graphics in the raster image are first segmented. By connecting the neighboring character blocks, text in different orientations can be recognized. To achieve a high degree of accuracy, thinning is adopted to find the center line. By utilizing double run-length codes, thinning and tracing can be executed very quickly. Line approximation is then conducted to extract all the straight line segments. A3 size cadaster maps copied from the land agency are tested. The experimental results show that the proposed method is very effective