A cognitive heuristic algorithm for reseau mark detection by hill climbing

A hill-climbing approach for the automatic detection of Reseau marks (RM) on the vidicon type of imagery is presented. This procedure is based on the minimization of a figure of merit which is a measure of the clustering nature of the gray values of the Reseau pixels around a nominal value. The often-encountered problem of false detection is circumvented by incorporating the concept of ``learning'' the mean gray value of the RM pixels. Results of applying the algorithm to both synthetic and actual imagery demonstrate the efficacy of the proposed method.