Character recognition in neural networks using back propagation method

One of the most classical applications of the Artificial Neural Network is the Character Recognition System. This system is the base for many different types of applications in various fields, many of which we use in our daily lives. This paper attempts to recognize the characters using a back propagation algorithm and studies the effect of variations of error percentage with number of hidden layers in a neural network. First, the aim is to recognize the twenty-six characters i.e. from A to Z &a to z and then to create a network that could recognize the numerals correctly.