Character recognition using firefly based back propagation neural network

Abstract

The use of artificial neural network technique has significantly improved the quality of pattern recognition day-by-day with better performance. After the evolution of optimization algorithms, it has given new directions for achieving efficient result. In this paper a firefly based back-propagation network has proposed for character recognition. The firefly algorithm is a nature inspired optimization algorithm and it is simulated into back-propagation algorithm to achieve faster and better convergence rate within few iteration. The characters are collected from system through mouse that are used for training and characters are collected from MS-Paint that are used for testing purpose. The performance is analyzed and it is observed that proposed method performs better and leads to converge in less number of iteration than back-propagation algorithm.