Feature enhancement for extracting on-line isolated handwritten characters

The study of online handwriting recognition has gained an immense interest among the researchers especially with the increase in use of the personal digital assistant (PDA). The large number of writing styles and the variability between them make the handwriting recognition a challenging area to dat...

Full description

Saved in:

Bibliographic Details
Main Author:	Zafar, Muhammad Faisal
Format:	Thesis
Language:	English
Published:	2006
Subjects:	TA Engineering (General) Civil engineering (General)
Online Access:	http://eprints.utm.my/id/eprint/18645/1/MuhammadFaisalZafarPFSKSM2006.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.18645
record_format	uketd_dc
spelling	my-utm-ep.186452018-09-17T03:47:05Z Feature enhancement for extracting on-line isolated handwritten characters 2006-08 Zafar, Muhammad Faisal TA Engineering (General). Civil engineering (General) The study of online handwriting recognition has gained an immense interest among the researchers especially with the increase in use of the personal digital assistant (PDA). The large number of writing styles and the variability between them make the handwriting recognition a challenging area to date. The present tools for modelling are not sufficient to cater for the various styles of human handwriting. Furthermore, the techniques used to get appropriate features, architecture and network parameters for online handwriting recognition are still ineffective. The success of any recognition system depends critically upon how far a set of appropriate numerical attributes or features can be extracted from the object of interest for the purpose of recognition. Thus the aim of this research work is to propose novel feature extraction methods to facilitate a system or device to achieve satisfactory online handwriting recognition. Two new simple and robust methods based on annotated image and sub-character primitive feature extractions have been proposed. The selection of features is based mainly on their effectiveness. Using the proposed techniques and a neural network based classifier, several experiments were carried out using the UNIPEN benchmark database. The techniques are independent of character size and can extract features from raw data without resizing. The maximum recognition rates achieved are 94% and 92% for annotated image and subcharacter primitive methods respectively. 2006-08 Thesis http://eprints.utm.my/id/eprint/18645/ http://eprints.utm.my/id/eprint/18645/1/MuhammadFaisalZafarPFSKSM2006.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:62489 phd doctoral Universiti Teknologi Malaysia, Fakulti Sains Komputer dan Sistem Maklumat Fakulti Sains Komputer dan Sistem Maklumat
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	TA Engineering (General) Civil engineering (General)
spellingShingle	TA Engineering (General) Civil engineering (General) Zafar, Muhammad Faisal Feature enhancement for extracting on-line isolated handwritten characters
description	The study of online handwriting recognition has gained an immense interest among the researchers especially with the increase in use of the personal digital assistant (PDA). The large number of writing styles and the variability between them make the handwriting recognition a challenging area to date. The present tools for modelling are not sufficient to cater for the various styles of human handwriting. Furthermore, the techniques used to get appropriate features, architecture and network parameters for online handwriting recognition are still ineffective. The success of any recognition system depends critically upon how far a set of appropriate numerical attributes or features can be extracted from the object of interest for the purpose of recognition. Thus the aim of this research work is to propose novel feature extraction methods to facilitate a system or device to achieve satisfactory online handwriting recognition. Two new simple and robust methods based on annotated image and sub-character primitive feature extractions have been proposed. The selection of features is based mainly on their effectiveness. Using the proposed techniques and a neural network based classifier, several experiments were carried out using the UNIPEN benchmark database. The techniques are independent of character size and can extract features from raw data without resizing. The maximum recognition rates achieved are 94% and 92% for annotated image and subcharacter primitive methods respectively.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Zafar, Muhammad Faisal
author_facet	Zafar, Muhammad Faisal
author_sort	Zafar, Muhammad Faisal
title	Feature enhancement for extracting on-line isolated handwritten characters
title_short	Feature enhancement for extracting on-line isolated handwritten characters
title_full	Feature enhancement for extracting on-line isolated handwritten characters
title_fullStr	Feature enhancement for extracting on-line isolated handwritten characters
title_full_unstemmed	Feature enhancement for extracting on-line isolated handwritten characters
title_sort	feature enhancement for extracting on-line isolated handwritten characters
granting_institution	Universiti Teknologi Malaysia, Fakulti Sains Komputer dan Sistem Maklumat
granting_department	Fakulti Sains Komputer dan Sistem Maklumat
publishDate	2006
url	http://eprints.utm.my/id/eprint/18645/1/MuhammadFaisalZafarPFSKSM2006.pdf
_version_	1747815324032434176

Feature enhancement for extracting on-line isolated handwritten characters

Similar Items