Application of Natured-Inspired Technique to Odia Handwritten Numeral Recognition

Abstract

In this chapter an effort has been made to develop a hybrid system using functional link artificial neural network (FLANN) and differential evolution (DE) for effective recognition of Odia handwritten numerals. The S-transform (ST) is chosen for feature extraction from handwritten numerals and these are further reduced by using principal component analysis (PCA). After reduction of feature the reduced features are applied to FLANN model for recognition of each numeral. Further differential evolution algorithm (DE) is used for the optimization of weights of FLANN classifier. For performance comparison, genetic algorithm (GA) and particle swarm optimization (PSO) based FLANN models (FLANN_GA and FLANN_PSO) are also designed and simulated under similar condition. The efficiency of proposed DE based FLANN (FLANN_DE) method is assessed through simulation with standard dataset consisting of 4000 handwritten Odia numerals. The results of three models are compared and it is observed that the FLANN_DE model provides the best result as compared to other models.