An efficient Optical Character Recognition algorithm using artificial neural network by curvature properties of characters

Optical Character Recognition (OCR) has gained so much importance among the researchers now a day as it is an eminent sector for a Human Computer Interaction (HCI) System. For an efficient recognition system the primary need is a reliable feature extraction process. So far the feature extraction systems used are mainly based on the character pattern, enclosure or symmetry. Still another property which is based on the angular properties of the several predetermined positions can be used for the purpose of feature extraction process that is the main motivation of this work. The effectiveness of the algorithm has been discussed in the experimental result section where the performance has been compared for different number of feature used.