Hindi character recognition using RBF neural network and directional group feature extraction technique

In this paper, Radial Basis Function (RBF) neural Network has been implemented on eight directional values of gradient features for handwritten Hindi character recognition. The character recognition system was trained by using different samples in different handwritings collected of various people of different age groups. The Radial Basis Function network with one input and one output layer has been used for the training of RBF Network. Experiment has been performed to study the recognition accuracy, training time and classification time of RBF neural network. The recognition accuracy, training time and classification time achieved by implementing the RBF network have been compared with the result achieved in previous related work i.e. Back propagation Neural Network. Comparative result shows that the RBF with directional feature provides slightly less recognition accuracy, reduced training and classification time.