Intelligent segmentation of color geo-images

We present an approach to a segmentation of color cartographic images. This is a simultaneous segmentation-recognition-interpretation system when successfully segmented objects of interest (alphanumeric, punctual, linear, and area) are labeled by the system in the same gray-level values, but are different for each type of object. We call it the composite image technique. We exchange the source image for a number of composite image representations. Every composite image representation is associated with certain features. Some of the composite images that contain the objects of interest serve to be used in the following object detection-recognition-interpretation. The specification of features associated with perspective composite representations is regarded as a type of knowledge domain. The results of gray-level color image segmentation are presented.