CFP last date
20 May 2024
Reseach Article

An Approach for Devanagari Handwritten Character Recognition using HMM and Fuzzy ARTMAP

Published on February 2013 by Sudhir Chitnis, Renuka Zope
International Conference on Recent Trends in Information Technology and Computer Science 2012
Foundation of Computer Science USA
ICRTITCS2012 - Number 12
February 2013
Authors: Sudhir Chitnis, Renuka Zope
0884b61e-5875-4f40-9f00-1e724a5418d7

Sudhir Chitnis, Renuka Zope . An Approach for Devanagari Handwritten Character Recognition using HMM and Fuzzy ARTMAP. International Conference on Recent Trends in Information Technology and Computer Science 2012. ICRTITCS2012, 12 (February 2013), 20-24.

@article{
author = { Sudhir Chitnis, Renuka Zope },
title = { An Approach for Devanagari Handwritten Character Recognition using HMM and Fuzzy ARTMAP },
journal = { International Conference on Recent Trends in Information Technology and Computer Science 2012 },
issue_date = { February 2013 },
volume = { ICRTITCS2012 },
number = { 12 },
month = { February },
year = { 2013 },
issn = 0975-8887,
pages = { 20-24 },
numpages = 5,
url = { /proceedings/icrtitcs2012/number12/10420-1454/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference on Recent Trends in Information Technology and Computer Science 2012
%A Sudhir Chitnis
%A Renuka Zope
%T An Approach for Devanagari Handwritten Character Recognition using HMM and Fuzzy ARTMAP
%J International Conference on Recent Trends in Information Technology and Computer Science 2012
%@ 0975-8887
%V ICRTITCS2012
%N 12
%P 20-24
%D 2013
%I International Journal of Computer Applications
Abstract

In this paper focus is on recognition of handwritten characters of Devanagari script. Recognition of Devanagari handwritten alphabets is important because of its applicability to a number of problems like many commercial forms, mythological records recognition in archeology department and offline document recognition generated by the expanding technological society. Though various new trends and technologies emerged in these days, still handwriting is playing an important role. To recognize handwritten data there are different strategies like Hidden Markov Models (HMM) and Simplified Fuzzy ARTMAP (SFAM). Our focus is on Fuzzy ARTMAP, which is an updated version of Predictive Adaptive Resonance Theory, works on feedback mechanism. It also has an ability to adjust clusters as per the requirements, which is beneficial to reduce noise.

References
  1. Carpenter,G. A. at. al(1991) ,"ARTMAP :Supervised Real Time Learning and Classification of Non Stationary Data by Self organizing Neural Network". Neural Network,Vol $ , pp-565-588.
  2. S. Rajasekaran, G. A. & Pai, Vijayalakshmi, "Neural Networks, Fuzzy Logic and Genetic Algorithms Synthesis and Application"
  3. Ross, Timothy J, "Fuzzy Logic with Engineering Application"
  4. Neural Network Classroom Approach by Satish Kumar by Tata McGraw-Hill (2004)
  5. Carpenter, G. A. at. al. (1987), ART2:Self Organization of stable category Recognition Codes for Analog input patterns.
  6. Khanale, S. B. , Mr. Sudhir Chitnis, "Journal of Artificial Intelligence @2011 Recognition of handwritten Devanagari character using Artificial Neural Networks" ISSN 1994-5450 / DOI:10. 3923/jai. 2011,55to 62
  7. Lawrence R. Rabiner. "A tutorial on HMMs and selected applications in speech Recognition". Proceedings of IEEE, Vol77, No2, Feb1989.
  8. G. A. Carpenter and S. Grossberg and D. B. Rosen, "Fuzzy ART: Fast Stable learning and Categorization of analog patterns by an adaptive resonance system "Neural Network, Vol 4, pp 779-771, 1991.
  9. Thammano, A. ICTAI 05, Thai character recognition by using Fuzzy ARTMAP
  10. Prime Kumar, K. P. ICECT, and 2011 Malayalam character recognition by using Fuzzy ARTMAP.
  11. G. A. Carpenter and Ross: A Neural Network Architecture for Object Recognition by Evidence Accumulation. IEEE transaction for Neural Networks Vol 6 No 4 1995.
Index Terms

Computer Science
Information Sciences

Keywords

Pattern Recognition Hmm Simplified Fuzzy Artmap