Open Access Open Access  Restricted Access Subscription or Fee Access

An Artificial Neural Network based Multistage Offline Handwritten Character Recognition

V. Pawar, A. Gaikwad

Abstract


Devanagari is one of the basic Script widely used for many Indian Languages Like Hindi, Marathi, Rajasthani etc. Devanagari Scripts Hindi language is the third common language used all over the word. In this work we propose an artificial neural network based classifier and statistical and structural method based feature extraction. Optical isolated Hindi Characters are taken as an input image through the scanner. An input image is preprocessed and is segmented in terms of various structural and stastical features like End points, middle bar, loop, end bar, aspect ratio. Features are extracted and the feature vector is applied to Self organizing map (SOM) which is one of the classifier of an artificial neural Network.SOM is trained for such 500 different characters collected from 500 persons. The characters are classified into three different classes. The proposed classifier attains 91% accuracy.

Keywords


Artificial Neural Network, Feature Extraction, Preprocessing, Training, Testing

Full Text:

PDF

References


A.M.Namboodiri, A.K.Jain, “Online script recognition,” IEEE Trans. Patten Analysis and Intelligence, Vol.26, No.1, pp.124-130, January 2004.

U.Bhattacharya,B.B.Choudhari, “Handwritten Numeral database of Indian Scripts and Multistage Recognition of Mixed Numbers” IEEE Trans. Patten Analysis and Machine Intelligence, Vol.31No.3 pp. 444-457, March.2009.

A.W. Senior, J.Robinson, “An Offline Cursive Handwriting Recognition System,”IEEE Trans. Patten Analysis and Intelligence, Vol.20 No.3 pp. 309-321, March 1998.

In-Jung Kim and Jin Hyung Kim, “Statistical character structure modeling and its application to handwritten Chinese recognition,” Pattern Analysis and Machine Intelligence, Vol.25, No.11, pp.1422-1436, 2003.

J Park, “An Adaptive Approach to Offline Handwritten Word Recognition,”IEEE Trans. Patten Analysis and Intelligence, Vol.24 No.7 pp. 919-931, July.2002.

T.Kohonen, “The Self Organizing Map,” IEEE Trans. Patten Analysis and Intelligence, Vol.78, No.9 pp. 1464-1480, Sept.1990.

Macro Bressan and Jordi Vitria , “On the selection and Classification of Independent Features,” IEEE Trans. Patten Analysis and Intelligence, Vol.25 No.10pp. 1312-1322, October 2003.

Luiz S. Oliveria,F. Bortolozzi,R.Sabourn “Automatic Recognition of Handwritten Numeral Strings: A Recognition and Verification Strategy ,” IEEE Trans. Patten Analysis and Intelligence, Vol.24 No.11 pp. 1438-1453, NOV.2002.

R.O.Duda, P.E.Hart and D.G.Strork,”Pattern Classification and scene analysis,” second ed. Wiley-sons, Oct2001.

R. Gonzalez,”Digital Image Processing Using Matlab”second ed. Tata McGraw-Hill , 2010.

Kohonen Springer Verlag, “Self Organizing Map,”Berlin, NewYark, Oct2001.

V.Pawar, A.Gaikwad, “Multistage recognition approach for handwritten Devanagari script recognition”,Pg. No.651-656 Proceeding of the WICT-2012


Refbacks

  • There are currently no refbacks.