HAND WRITTEN CHARACTER RECOGNITION USING BACK PROPAGATION NETWORK
Srinivasa Kumar Devireddy, Settipalli Appa Rao · 2009
A Neural network is a machine that is designed to model the way in which the brain performs a particular task or function of interest: The network is usually implemented by using electronic components or is simulated in software on a digital computer. “ A neural network is a massively parallel distributed processor made up of simple processing units which has a natural propensity for storing experiential knowledge and making it available for use. It resembles the brain in two respects: 1)Knowledge is required by the network from its environment through a learning process. 2)Interneuron connection strengths, known as synaptic weights, are used to store the acquired knowledge”. In this paper, we proposed a system capable of recognizing handwritten characters or symbols, inputted by the means of a mouse. The system provides means for training the input characters first, then there is a classification option where the patterns or symbols that have already been trained should be fed, in order to recognize it. There are full options for the users, like (1) To load a default set of patterns which can either be trained or the default training file can be loaded. After which the recognition takes place. (2) To classify a line of text and (3) Options to either load a pattern file, trained or untrained & finally the option to create new patterns by the user to train & classify.