CFP last date
22 April 2024
Reseach Article

Recognition of Multi-font English Numerals using SOM Neural Network

by Hamid Hassanpour, Najmeh Samadiani
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 98 - Number 4
Year of Publication: 2014
Authors: Hamid Hassanpour, Najmeh Samadiani
10.5120/17174-7259

Hamid Hassanpour, Najmeh Samadiani . Recognition of Multi-font English Numerals using SOM Neural Network. International Journal of Computer Applications. 98, 4 ( July 2014), 37-41. DOI=10.5120/17174-7259

@article{ 10.5120/17174-7259,
author = { Hamid Hassanpour, Najmeh Samadiani },
title = { Recognition of Multi-font English Numerals using SOM Neural Network },
journal = { International Journal of Computer Applications },
issue_date = { July 2014 },
volume = { 98 },
number = { 4 },
month = { July },
year = { 2014 },
issn = { 0975-8887 },
pages = { 37-41 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume98/number4/17174-7259/ },
doi = { 10.5120/17174-7259 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:25:21.404846+05:30
%A Hamid Hassanpour
%A Najmeh Samadiani
%T Recognition of Multi-font English Numerals using SOM Neural Network
%J International Journal of Computer Applications
%@ 0975-8887
%V 98
%N 4
%P 37-41
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

In this paper a new scheme is proposed for off-line recognition of multi-font numeral, using neural networks. Recognition of numerals has been a research area for many years because of its various applications. But there wasn't much research done for recognition of multi-font numerals. The approaches proposed so far, suffer from larger computation time and training because they must have a set of training samples per each font. They can be extended to recognize many more fonts but the accuracy decreases rapidly. So as to eliminate these drawbacks, in this paper, a method is presented which recognizes 30 different fonts of different sizes varying from size 10 to 28, with an accuracy of 99. 55% on a database of 2000 numeral images. The purpose of this study is to provide a new method to recognize digits based on neural network that can identify the same symbols after training without limitation on the type of the font. In the proposed method, a high accuracy rate is achieved in recognizing digits by extracting the appropriate features without the need for complex neural network architecture. This method uses a self-organizing map (SOM) neural network to measure similarity between the features of digits and the features of the indicators associated with the digits from 0 to 9 obtained in the training stage. In this method, one sample is used for each digit to train the network. So, the proposed method can be used to recognize typed letters without limitation on fonts.

References
  1. Dhandra, B. V. , Malemath, V. S. , Mallikarjun, H. and Hegadi, R. 2007 Multi-font Numeral Recognition without Thinning based on Directional Density of Pixels, 1st International Conference on Digital Information Management.
  2. Mallikarjun, H. , Shashikala, P. and Dhandra, B. V. 2010. Multi-font/size Kannada Vowels and Numerals Recognition Based on Modified Invariant Moments, International Journal of Computer Applications, (Special Issue on RTIPPR (2)) 126–130.
  3. Ebrahimnezhad, H. , Montazer, GH. A. and Jafari, N. 2007 Recognition of Persian Numeral Fonts by Combining the Entropy minimized fuzzifier and fuzzy Grammar, in WSEAS Transactions on Artificial intelligence, knowledge Engineering and data bases.
  4. Montazer, G. A. , Saremi, H. Q. and Khatibi, V. 2010 A neuro-fuzzy inference engine for Farsi numeral characters recognition, Expert Systems with Applications, 37(9), 6327-6337.
  5. Lingaraju G. M. , Sujata, C. , Prabhakar, D. L. and Shantarajappa, A. N. 2003 Cognition and Recognition of Numerals using Hermite Curves, in 2nd National Conference on Document Analysis and Recognition (NCDAR), Mandya, India, 139-144.
  6. Hanmandlu, M. , Hafizuddin, M. , Yusif, M. and Madasu, V. K. 2003 fuzzy based approach to recognition of multi-font numerals, in 2th National Conference on Document Analysis and Recognition (NCDAR), Mandya, India.
  7. Santosh Arjun, N. , Navaneetha, G. , Preethi, G. V. and Babu, T. K. 2007 An approach to multi-font numeral recognition, in TENCON- IEEE Region 10 Conference.
  8. Rani, R. , Dhir, R. and Lehal, G. S. 2013 Script Identification of Pre-segmented Multi-font Characters and Digits, 12th International Conference on Document Analysis and Recognition (ICDAR).
  9. Tokunaga, K. and Furukawa, T. 2009 Modular network SOM, Neural Networks, 22(1) 82-90.
  10. Maitre, G. 1995 Experiments with robust similarity measures for OCR, IDIAP TR, 95-103.
  11. Kahya, E. 2005 A new unidimensional search method for optimization: Linear interpolation method, Applied Mathematics and Computation, 171(2) 912-926.
  12. Sablonnière, P. 1982 Interpolation by quadratic splines on triangles and squares, Computers in Industry, 3(1-2) 45-52.
  13. Duan, Q. , Djidjeli, K. , Price, W. G. and Twizell, E. H. 2000 Weighted rational cubic spline interpolation and its application, Journal of Computational and Applied Mathematics, 117(2) 121-135.
  14. Dunlop, G. R. 1980 A rapid computational method for improvements to nearest neighbor interpolation, Computers& Mathematics with Applications 6(3) 349-353.
  15. Hassanpour, H. , Darvishi, A. and Khalili, A. 2011 A regression-based approach for measuring similarity in discrete signals, International Journal of Electronics, 98.
Index Terms

Computer Science
Information Sciences

Keywords

OCR numeral recognition self-organizing map (SOM) similarity measure