AN ENTROPY-BASED METHOD FOR EXTRACTING ROBUST BINARY TEMPLATES

In applications based on template matching, the design of the template is a critical point and has a considerable effect on the overall perf ormance that can be obtained. In this paper we present a method, appli cable to binary images, for extracting robust templates. Starting from a provisional prototype (defined as the image that minimizes its over all distance from the samples of a training set), the template is obta ined by eliminating unreliable pixels determined by means of an entrop y-based criterion. The method is compared experimentally with the matc hed filtering technique in the recognition of symbols on topographic m aps and shows promising results regarding the recognition rate and the computational cost of the matching process.