Improving Handwritten Isolated Arabic characters Recognition with Particle Swarm Optimization Algorithm

Abstract

This manuscript considers a new approach to Simplifying pattern recognition based on simulation of behavior of schools of fish and flocks of birds and called particles swarm optimization algorithm (PSOA). We present an overview of the proposed approaches to be optimized and tested on a number of handwritten characters in the experiments as well. Experimental results of the optimization algorithm are found to be very efficient and give higher recognition accuracy. It is noted that the PSOA in general generates an optimized comparison between the input samples and database samples which improves the final recognition rate. Experimental results show that the PSOA algorithm is convergence and more accurate in solution with low error recognition rate .The recognition rate of our proposed system is 87.856% and rate error recognition is 12.142%.