Handwritten Devanagari script recognition system using neural network is presented in this paper. A new method, called, diagonal based feature extraction is used for extracting features of the handwritten Devanagari script. Fifty data sets, each containing 44 characters written by various people, are used for training neural network and 570 different handwritten Devanagari characters are used for testing. The proposed recognition system performs quite well yielding higher levels of recognition accuracy compared to systems employing the conventional horizontal and vertical methods of feature extraction.

Download PDF

Back