Characters and Digits Recognition Using Neural Network Learned by Particle Swarm Optimization

Abstract

The meaning of the Particle Swarm Optimization (PSO) refers to a relatively new family of algorithms that may be used to find optimal (or near optimal) solutions to numerical and qualitative problems. Neural Network is an information processing system that has been developed as generalization models of human cognition of neural biology. In this paper the neural network learned by PSO method to solve one of pattern recognition problems which is considered as one of the important applications in the classification field, instead of using Back Propagation (BP) or Genetic Algorithm (GA) methods. The suggested method is found to learn the NN, to solve characters and digits or decimal numbers (0..9) recognition problem, by modifying the NN weights, this is done by calculating the fitness value which is considered as a threshold value. A comparison studies are made between PSO and Back Propagation (BP) methods in NN learning to specify which is better in solving letter recognition problem.