Title :
A framework for recognizing the hand written digits with multi-zone approach
Author :
Rajiv, K. ; Saritha, T. ; Srikanth, Punugoti ; Sukesh, M.
Author_Institution :
Dept. of CSE, Nalla Narasimha Reddy Educ. Soc.´s Group of Instn., Hyderabad, India
Abstract :
In this paper, we proposed a handwritten digit recognition system which uses multiple feature extraction methods. Here we extract the size features, and we proposed multi-zoning method. It is shown that multi zoning method is sufficient to achieve high recognition rates. Several combination schemes were tested, showing good results. By using this multi-zoning method we achieved a recognition rate of 97%, the highest one on the MNIST database.
Keywords :
feature extraction; handwritten character recognition; image classification; MNIST database; handwritten digit recognition system; multiple feature extraction methods; multizoning method; Character recognition; Databases; Feature extraction; Handwriting recognition; Neural networks; Training; Vectors; Digit recognition; Handwritten; MNIST; database; multi-zone;
Conference_Titel :
Computational Intelligence and Computing Research (ICCIC), 2013 IEEE International Conference on
Conference_Location :
Enathi
Print_ISBN :
978-1-4799-1594-1
DOI :
10.1109/ICCIC.2013.6724268
