A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network

This paper presents a new, simple and fast approach for character segmentation of unconstrained handwritten words. The developed segmentation algorithm over-segments in some cases due to the inherent nature of the cursive words. However the over segmentation is minimum. To increase the efficiency of...

Full description

Bibliographic Details
Main Authors: Khan, Amjad Rehman, Mohamad, Dzulkifli
Format: Article
Language:English
Published: CSC Journals, Kuala Lumpur, Malaysia 2008
Subjects:
Online Access:http://eprints.utm.my/9951/
http://eprints.utm.my/9951/1/AmjadRehmanKhan2008_AsimpleSegmentationApproachforUnconstrainedCursiveS.pdf
_version_ 1848891982534934528
author Khan, Amjad Rehman
Mohamad, Dzulkifli
author_facet Khan, Amjad Rehman
Mohamad, Dzulkifli
author_sort Khan, Amjad Rehman
building UTeM Institutional Repository
collection Online Access
description This paper presents a new, simple and fast approach for character segmentation of unconstrained handwritten words. The developed segmentation algorithm over-segments in some cases due to the inherent nature of the cursive words. However the over segmentation is minimum. To increase the efficiency of the algorithm an Artificial Neural Network is trained with significant amount of valid segmentation points for cursive words manually. Trained neural network extracts incorrect segmented points efficiently with high speed. For fair comparison benchmark database IAM is used. The experimental results are encouraging
first_indexed 2025-11-15T21:06:37Z
format Article
id utm-9951
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T21:06:37Z
publishDate 2008
publisher CSC Journals, Kuala Lumpur, Malaysia
recordtype eprints
repository_type Digital Repository
spelling utm-99512011-05-18T07:37:07Z http://eprints.utm.my/9951/ A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network Khan, Amjad Rehman Mohamad, Dzulkifli QA76 Computer software This paper presents a new, simple and fast approach for character segmentation of unconstrained handwritten words. The developed segmentation algorithm over-segments in some cases due to the inherent nature of the cursive words. However the over segmentation is minimum. To increase the efficiency of the algorithm an Artificial Neural Network is trained with significant amount of valid segmentation points for cursive words manually. Trained neural network extracts incorrect segmented points efficiently with high speed. For fair comparison benchmark database IAM is used. The experimental results are encouraging CSC Journals, Kuala Lumpur, Malaysia 2008 Article PeerReviewed application/pdf en http://eprints.utm.my/9951/1/AmjadRehmanKhan2008_AsimpleSegmentationApproachforUnconstrainedCursiveS.pdf Khan, Amjad Rehman and Mohamad, Dzulkifli (2008) A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network. International Journal of Computer Science and Security, 2 (3). pp. 29-35. ISSN 1985-1553 (online) http://www.cscjournals.org/csc/manuscript/Journals/IJIP/Volume2/Issue3/IJIP-13.pdf
spellingShingle QA76 Computer software
Khan, Amjad Rehman
Mohamad, Dzulkifli
A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network
title A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network
title_full A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network
title_fullStr A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network
title_full_unstemmed A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network
title_short A simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network
title_sort simple segmentation approach for unconstrained cursive handwritten words in conjunction with neural network
topic QA76 Computer software
url http://eprints.utm.my/9951/
http://eprints.utm.my/9951/
http://eprints.utm.my/9951/1/AmjadRehmanKhan2008_AsimpleSegmentationApproachforUnconstrainedCursiveS.pdf