Multistage Recognition Approach for Handwritten Devanagari Script Recognition

Author

Rahul, P.V. ; Gaikwad, Arun N.

Author_Institution

Dept. of Electron. Eng., Bharati Vidyapeeth, Pune, India

fYear

2012

fDate

Oct. 30 2012-Nov. 2 2012

Firstpage

651

Lastpage

656

Abstract

This paper is focused on Devanagari Handwritten Script Recognition. The scanned word image is taken as an input image. An Input image is preprocessed and segmented. The features are extracted. Feature vector is applied to an artificial Neural Network. The Network is trained for the different set of numerals and alphabets. Output of Self Organizing Map applied to Learning Vector Quantization and the accuracy is calculated.

Keywords

feature extraction; handwritten character recognition; image segmentation; learning (artificial intelligence); natural language processing; self-organising feature maps; vector quantisation; alphabet set; artificial neural network; feature extraction; feature vector; handwritten Devanagari script recognition; image preprocessing; image segmentation; learning vector quantization; multistage recognition approach; network training; numeral set; self-organizing map; word image scanning; Educational institutions; Feature extraction; Handwriting recognition; Image segmentation; Organizing; Training; Vectors; Feature Extraction; Image Preprocessing; Network Neighborhood; Segmentation; Self Organizing Map;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Communication Technologies (WICT), 2012 World Congress on

Conference_Location

Trivandrum

Print_ISBN

978-1-4673-4806-5

Type

conf

DOI

10.1109/WICT.2012.6409156

Filename

6409156