Hand-written character recognition using artificial neural network

Abstract

In todays’ world advancement in sophisticated scientific techniques is pushing further the limits of human outreach in various fields of technology. One such field is the field of character recognition commonly known as OCR (Optical Character Recognition). In this fast paced world there is an immense urge for the digitalisation of printed documents and documentation of information directly in digital form. And there is still some gap in this area even today. OCR techniques and their continuous improvisation from time to time is trying to fill this gap. This project is about devising an algorithm for recognition of hand written characters leaving aside types of OCR that deals with recognition of computer or typewriter printed characters. A novel technique is proposed using Artificial Neural Network including the schemes of feature extraction of the characters and implemented. The persistency in recognition of characters by the AN network was found to be more than 90% of times.