Devanagari Hand-printed Character Recognition using Multiple Features and Multi-stage Classifier

Abstract

Devanagari is an important script mostly used in South Asia and it is also the script of Hindi the mothertongue of majority of Indians. Though work done for the recognition of Devanagari hand-printed characters have been reported by some authors, but the availability of good ICR for this script is still a dream. In this paper, a three tier strategy is suggested to recognize the handprinted characters of this script. In primary and secondary stage classification, the structural properties of the script are exploited to avoid classification error. The results of all the three stages are reported on two classifiers i.e. MLP and SVM and the results achieved with the later are very good. The performance of the proposed scheme is reported in respect of recognition accuracy and time. The recognition rate achieved with the proposed scheme is 94.2% on our database consisting of more than 25000 characters belonging to 43 alphabets. The recognition rate has further improved to 95.3% when a conflict resolution strategy between some pair of characters is used