Cover Image

Hand-written Malayalam character recognition an approach based on pen movement

In this paper we introduce a novel approach for character recognition based on the pen movement i.e., recognition based on sequence of pen strokes.A Backpropagation Neural Network is used for identifying individual strokes.The recognizer has a two-pass architecture i.e., the inputs are propagated tw...

Full description

Saved in:
Bibliographic Details
Main Authors: G, Jayababu, Idicula, Sumam Mary
Format: Conference or Workshop Item
Language:English
Published: 2004
Subjects:
QA76 Computer software
Online Access:http://repo.uum.edu.my/13915/1/KM200.pdf
http://repo.uum.edu.my/13915/
http://www.kmice.cms.net.my
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uum.repo.13915
record_format eprints
spelling my.uum.repo.139152015-05-12T03:25:15Z http://repo.uum.edu.my/13915/ Hand-written Malayalam character recognition an approach based on pen movement G, Jayababu Idicula, Sumam Mary QA76 Computer software In this paper we introduce a novel approach for character recognition based on the pen movement i.e., recognition based on sequence of pen strokes.A Backpropagation Neural Network is used for identifying individual strokes.The recognizer has a two-pass architecture i.e., the inputs are propagated twice through the network.The first pass does the initial classification and the second for exact recognition. The two-pass structure of the recognizer helped in achieving accuracy of about 95 percent in recognizing Malayalam letters.The training set contains samples of all independent strokes that are commonly used while writing Malayalam.Input values to the network are the directions of pen movement.A “minimum error” technique is used for finding the firing neuron in the output layer. Based on the output of FirstPass the network is dynamically loaded with a fresh set of weights for exact stroke recognition.Analyzing the stroke sequences identifies individual characters.This work also demonstrates how a statistical pre-analysis of training set reduces training time. 2004-02-14 Conference or Workshop Item PeerReviewed application/pdf en http://repo.uum.edu.my/13915/1/KM200.pdf G, Jayababu and Idicula, Sumam Mary (2004) Hand-written Malayalam character recognition an approach based on pen movement. In: Knowledge Management International Conference and Exhibition 2004 (KMICE 2004), 14-15 February 2004, Evergreen Laurel Hotel, Penang. http://www.kmice.cms.net.my
institution Universiti Utara Malaysia
building UUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Utara Malaysia
content_source UUM Institutionali Repository
url_provider http://repo.uum.edu.my/
language English
topic QA76 Computer software
spellingShingle QA76 Computer software
G, Jayababu
Idicula, Sumam Mary
Hand-written Malayalam character recognition an approach based on pen movement
description In this paper we introduce a novel approach for character recognition based on the pen movement i.e., recognition based on sequence of pen strokes.A Backpropagation Neural Network is used for identifying individual strokes.The recognizer has a two-pass architecture i.e., the inputs are propagated twice through the network.The first pass does the initial classification and the second for exact recognition. The two-pass structure of the recognizer helped in achieving accuracy of about 95 percent in recognizing Malayalam letters.The training set contains samples of all independent strokes that are commonly used while writing Malayalam.Input values to the network are the directions of pen movement.A “minimum error” technique is used for finding the firing neuron in the output layer. Based on the output of FirstPass the network is dynamically loaded with a fresh set of weights for exact stroke recognition.Analyzing the stroke sequences identifies individual characters.This work also demonstrates how a statistical pre-analysis of training set reduces training time.
format Conference or Workshop Item
author G, Jayababu
Idicula, Sumam Mary
author_facet G, Jayababu
Idicula, Sumam Mary
author_sort G, Jayababu
title Hand-written Malayalam character recognition an approach based on pen movement
title_short Hand-written Malayalam character recognition an approach based on pen movement
title_full Hand-written Malayalam character recognition an approach based on pen movement
title_fullStr Hand-written Malayalam character recognition an approach based on pen movement
title_full_unstemmed Hand-written Malayalam character recognition an approach based on pen movement
title_sort hand-written malayalam character recognition an approach based on pen movement
publishDate 2004
url http://repo.uum.edu.my/13915/1/KM200.pdf
http://repo.uum.edu.my/13915/
http://www.kmice.cms.net.my
_version_ 1644281317609701376
score 13.211869

Similar Items