Open Access Open Access  Restricted Access Subscription or Fee Access

Result Evolution of Online Handwritten Digit Recognition using SVM over HMM

Manish Vyas, Amit Singhal, Neetesh Gupta

Abstract


Handwritten Numeral recognition plays a vital role in
postal automation services especially in countries like India where multiple languages and scripts are used Discrete Hidden Markov Model (HMM) and hybrid of Neural Network (NN) and HMM are popular methods in handwritten word recognition system. The hybrid system gives better recognition result due to better discrimination
capability of the NN. A major problem in handwriting recognition is the huge variability and distortions of patterns. Elastic models based on local observations and dynamic programming such HMM are not efficient to absorb this variability. But their vision is local. But they cannot face to length variability and they are very sensitive to
distortions. Then the SVM is used to estimate global correlations and classify the pattern. Support Vector Machine (SVM) is an alternative to NN. In Handwritten recognition, SVM gives a better recognition result. The aim of this paper is to develop an approach which improve the efficiency of handwritten recognition using artificial neural network


Keywords


Handwriting Recognition, Support Vector Machine, Neural Network.

Full Text:

PDF

References


Sandip Kaur, “ Recognition of Handwritten Devanagri Script using Feature Based on Zernike Moments and Zoning and Neural Network Classifier”, A M. Tech. Thesis Report, Panjabi University, Patiala, 2004, pp.

Gaurav Jain, Jason Ko, “Handwritten Digits Recognition”, Multimedia Systems, Project Report, University of Toronto, November 21, 2008, pp. 1-3.

Scott D. Connell, R.M.K. Sinha, Ani1 K. Jain “Recognition of

Unconstrained On-Line Devanagari Characters”, 2000, IEEE.

A.K. Jain, Robert P.W.Duin, Jianchang Mao, “ Statistical Pattern Recognition: A Review”, IEEE Trans. PAMI, Vol.22, No. 1, 2000.

Anuj Sharma, “Online Handwritten Gurmukhi Character Recognition”, A Ph. D. Thesis report, School of [6] Shubhangi D.C., P.S.Hiremath, “Multi-Class SVM Classifier for English Handwritten Digit Recognition using Manual Class Segmentation”, Proc. Int’l Conf. on Advances in Computing. Communication and Control (ICAC3’09) 2009, pp. 353-356.

Sabri A. Mahmoud and Sameh M. Awaida, “Recognition Of Off-Line Handwritten Arabic (Indian) Numerals Using Multi-Scale Features And Support Vector Machines Vs. Hidden Markov Models” The Arabian Journal For Science And Engineering, Volume 34, Number 2b, October, 2009,Pp. 430-444.

A.Borji, and M. Hamidi, “Support Vector Machine for Persian Font Recognition”, International Journal of Intelligent Systems and Technologies, Summer 2007, pp. 184-187

C. Vasantha Lakshmi, Ritu Jain, C. Patvardhan, “Handwritten Devanagari Numerals Recognition With Higher Accuracy”, Proc. of IEEE Int. Conf. on Computational Intelligence and Multimedia Application, 2007, pp 255-259.

U.Bhattacharya, B.B.Chaudhari, “Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals”, IEEE Trans. on PAMI, Vol.31, No.3, 2009, pp.444-457.

U. Pal, T. Wakabayashi, N. Sharma and F. Kimura, “Handwritten Numeral Recognition of Six Popular Indian Scripts”, Proc. 9th ICDAR, Curitiba, Brazil, Vol.2 (2007),749-753.

Christopher M. Bishop, “Pattern Recognition and Machine Learning”, Springer Publication, Singapore, 2006, Pp. 1-3, 308-320.


Refbacks

  • There are currently no refbacks.