Fuzzy modeling based palm print recognition system

This paper is concerned with the palm print recognition. The features consist of primary lines and secondary lines and their intersections. The primary lines are fitted with polynomial equations whose coefficients are utilized in the new entropy function of Anirban and Hanmandlu. A fuzzy rule is constructed in which the entropy function make their way into the criterion function for the purpose of learning parameters which modify the coefficients of all the primary lines. Next a test function is devised to match the unknown palm print with the reference palm print having the learned parameters as its knowledge base. While learning the parameters, the reinforcement learning law of Hanmandlu and Murthy leads to the fast convergence of the parameters.