Handwritten Devnagri Character Recognition
Prof. Shraddha V. Shelke, K. K. Wagh Institute of engineering Education and Research Nashik, Maharashtra; Dr. Prof. Dinesh M. Chandwadkar ,K. K. Wagh Institute of engineering Education and Research Nashik, Maharashtra
Devnagri Characters, Multilayer perceptron, K-Nearest Neighbour, Naive Bayes
Recognition of handwritten characters has been a popular research area for many years. Devnagari script is a major script of India and is widely used for various languages. In this paper we propose a system to recognize devnagri handwritten characters. Total 60 devnagri characters (50 letters and 10 digits) are taken in to consideration. 60 samples of each character i.e. total 3600 samples are used for features extraction. Classification is done by four different classifiers which are Multilayer perceptron, K-Nearest Neighbour, Naive Bayes classifier and Classification tree. Performance of different classifiers is compared.98.9 % accuracy is obtained by Multilayer perceptron.
-
[1] Jayadevan, R., Satish R. Kolhe, Pradeep M. Patil and Umapada Pal, 2011. "Offline Recognition of Devanagari Script: A Survey", IEEE Transactions on Systems, Man and Cybernetics, Part C, 41(6): 782-796
[2] Pal, U. and B.B. Chaudhuri, 2004. “Indian script character recognition: A survey,” Pattern Recognit., 37: 1887-1899
[3] I.K. Sethi and B. Chatterjee, “Machine Recognition of constrained Hand printed Devnagari”, Pattern Recognition, Vol. 9, pp. 69-75, 1977
[4] Umapada Pal, Sukalpa Chanda,Tetsushi Wakabayashi, Fumitaka Kimura, ”Accuracy Improvement of Devnagari Character Recognition Combining SVM and MQDF”
[5] VelappaGanapathy, and Kok Leong Liew,” Handwritten Character Recognition Using Multiscale Neural Network Training Technique”, World Academy of Science, Engineering and Technology 39 2008
[6] R. Bouckaert, Frank, M.Hall, R.kirkby, P. Reutemann,A. Seewald ,D. Scuse ,”WEKA Manual for Version 3-6-2”, Ch no 4.3 P.no.41,January 11, 2010
Paper ID: GRDJEV01I050029
Published in: Volume : 1, Issue : 5
Publication Date: 2016-05-01
Page(s): 67 - 70
Published in: Volume : 1, Issue : 5
Publication Date: 2016-05-01
Page(s): 67 - 70