Hand printed Character Recognition using Neural Networks

In this paper an attempt is made to recognize hand-printed characters by using features extracted using the proposed sector approach. In this approach, the normalized and thinned character image is divided into sectors with each sector covering a fixed angle. The features totaling 32 include vector distances, angles, occupancy and end-points. For recognition, both neural networks and fuzzy logic techniques are adopted. The proposed approach is implemented and tested on hand-printed isolated character database consisting of English characters, digits and some of the keyboard special characters. The problem of recognition of hand-printed characters is still an active area of research. With ever increasing requirement for office automation, it is imperative to provide practical and effective solutions. It has been observed that all sorts of structural, topological and statistical information about the characters does not lend a helping hand in the recognition process due to different writing style