MU Digital Repository
Logo

Character Recognition based on Neural Network and Lexical support for Machine Printed Malayalam Documents

Gopakumar, Rajesh and Acharya, Dinesh U and Subbareddy , NV (2005) Character Recognition based on Neural Network and Lexical support for Machine Printed Malayalam Documents. In: National Conference on Devices, Intelligent Systems and Communications, Electronics and Communication Engineering Department, MIT, Manipal.

[img] PDF
MITDISC-1(2005).pdf - Published Version
Restricted to Registered users only

Download (446kB) | Request a copy

Abstract

Exclusive and intensive research has been done on optical character recognition and a large number of research papers have been published in the last few decades. Most of the efforts were made to develop OCR systems for foreign languages like English, Japanese, Roman and Arabic characters. Many commercial OCR systems for these foreign languages are available in the market. Even though in this direction efforts are made on some Indian languages, much work has not been done on any South Indian languages, especially on Malayalam Script. This paper describes a Recognition algorithm for machine printed Malayalam character based on Artificial Neural Network and Lexical support. Malayalam Unicode character database has been used as test input dataset. The proposed Optical Character Recognition system uses a backpropagation neural network with simple dynamic lexical component.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Character Segmentation, Lexicon, Malayalam Script, Neural Network Classifier.
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Engineering > MIT Manipal > Electronics and Communication
Depositing User: MIT Library
Date Deposited: 04 Jul 2011 08:59
Last Modified: 04 Jul 2011 08:59
URI: http://eprints.manipal.edu/id/eprint/467

Actions (login required)

View Item View Item