Performance Comparison of Devanagari Handwritten Numerals Recognition

Abstract

In this paper an automatic recognition system for isolated Handwritten Devanagari Numerals is proposed and compared the recognition rate with different classifier. We presented a feature extraction technique based on recursive subdivision of the character image so that the resulting sub images at each iteration have balanced numbers of foreground pixels as possible. Database, provided by Indian Statistical Institute, Kolkata, have 22547 grey scale images written by 1049 persons and obtained 98.98% highest accuracy with SVM classifier. Results are compared with KNN and Quadratic classifier.