Perceptual grouping for symbol chain tracking in digitized topographic maps

In this paper a new algorithm that applies perceptual grouping to detect an d track discontinuous chains of symbols in digitized maps is proposed. The procedure is based on an artificial intelligence kernel that supervises thr ee different auxiliary processes: the Search Strategy Generation module tha t is responsible for the strategy to scan pixels; the Symbol Detection (SD) module that extracts the recognized symbols; the Cost Function Evaluation (CFE) module that assigns a global quality index to each symbol by consider ing the whole course of the line. Selected Gestalt rules are used to optimi ze the grouping procedures. After the algorithm discussion, the problem of the extraction of dotted and dashed lines from digitized topographic maps i s discussed. Experimental results on many maps of the Istituto Geografico M ilitare Italiano (IGMI) show a very good behavior: 92% of the discontinuous lines have been correctly chained, and the percentage of incorrectly class ified symbols is also very small. (C) 1999 Elsevier Science B.V. All rights reserved.