An efficient handwritten Devnagari character recognition system using neural network

Abstract

Character recognition systems for various languages and script has gain importance in recent decades and is the area of deep interest for many researchers. Their development is strongly integerated with Neural Networks. But, recognizing Devanagari Script is relatively greater challenge due to script's complexity. Various techniques have been implemented for this problem with many improvements so far. This paper describes the development and implementation of one such system comprising combination of several stages. Mainly Artificial Neural Network technique is used to designed to preprocess, segment and recognize devanagari characters. The system was designed, implemented, trained and found to exhibit an accuracy of 75.6% on noisy characters.