Abstract: The OCR system provides an efficient way to translate human readable characters to machine readable characters. It is to identify and analyze a document image by dividing the page into line, words, and then characters. Handwriting character recognition is a challenging and interesting task in the field of pattern recognition. In this paper we are segmenting the Kannada handwritten characters. For the feature extraction we are using twelve directional feature extraction techniques and for the recognition back propagation neural network is used. Experimental results show the good recognition rate towards segmented handwritten Kannada characters.
Keywords: Handwritten Kannada Character Recognition Feed forward neural network, Recognition accuracy rate.
Title: Segmentation of Kannada Handwritten Characters and Recognition Using Twelve Directional Feature Extraction Techniques
Author: Lohitha B.J, Y.C Kiran
International Journal of Computer Science and Information Technology Research
ISSN 2348-1196 (print), ISSN 2348-120X (online)
Research Publish Journals
