No abstract

Abstract.A method to separate and recognize the touching/overlapping alphanumeric characters is proposed. The characters are processed in raster-scanned color cartographic maps. The map is segmented first to extract all text strings including those that are touching other symbols, strokes and characters. Second, OCR-based recognition with Artificial Neural Networks (ANN) is applied to define the coordinates, size and orientation of alphanumeric character strings in each case presented in the map. Third, four straight lines or a number of "curves" computed as a function of primarily recognized by ANN characters are extrapolated to separate those symbols that are attached. Finally, the separated characters input into ANN again to be finally identified. Results showed high method's rendering in the context of raster-to-vector conversion of color cartographic images.

No abstract

One main problem in image analysis is the segmentation of a cartographic image into its different layers. The text layer is one of the most important and richest ones. It comprises the names of cities, towns, rivers, monuments, streets, and so on. Dozens of segmentation methods have been developed to segment images. Most of them are useful in the binary and the gray level cases. Not to many efforts have been however done for the color case. In this paper we describe a novel segmentation technique specially applicable to raster-scanned color cartographic color images. It has been tested with several dozen of images showing very promising results.