Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad

The presence of features such as cursive, diversity of writing styles and sizes of characters in a Jawi text, ligature, and vertical overlapping make the recognition of Jawi handwritten text to be difficult. For the recognition system based on model development using windows, the presence of such fe...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohamad, Roslim
Format:	Thesis
Language:	English
Published:	2017
Subjects:	PL Languages and literatures of Eastern Asia Africa Oceania PL Languages and literatures of Eastern Asia, Africa, Oceania Algorithms
Online Access:	https://ir.uitm.edu.my/id/eprint/67546/1/67546.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uitm-ir.67546
record_format	uketd_dc
spelling	my-uitm-ir.675462023-05-08T03:29:29Z Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad 2017 Mohamad, Roslim PL Languages and literatures of Eastern Asia, Africa, Oceania Development. UML (Computer science) Algorithms The presence of features such as cursive, diversity of writing styles and sizes of characters in a Jawi text, ligature, and vertical overlapping make the recognition of Jawi handwritten text to be difficult. For the recognition system based on model development using windows, the presence of such features cause the resulting model to be less consistent, where it produces a different sequence of primitive structures of words/sub-words from the same lexicon. To overcome the inconsistency model problem, a handwritten Jawi text recognition system based on a sub-word model has been developed. The proposed modeling technique which is known as Selection Segmentation-Free (SSF) separates core and connection structure of a sub-word into a different window. The resulting window will go through a selection process to determine the windows that will be used to represent the sub-word model. In order to increase accuracy and efficiency of the representation feature, two categories of features which are known as primary and secondary features were extracted from each of the selected windows. Primary feature were extracted using Window Code Representation (WCR) technique from main structure. Secondary feature for supporting the primary feature were extracted from dot and main structure. For the experiment purposes, a total of 1200 sub-words of 80 lexicons were used. Each lexicon is randomly selected and divided into three sets. Three experiments to evaluate the performance of SSF, WCR and combination of primary and secondary feature techniques were conducted. The three techniques are combined to represent the proposed system and compared with the comparison system introduced by Remon (2009). Comparison result shows that the recognition rate of proposed system (84.8%) is better than comparison system (79.1 %). 2017 Thesis https://ir.uitm.edu.my/id/eprint/67546/ https://ir.uitm.edu.my/id/eprint/67546/1/67546.pdf text en public phd doctoral Universiti Teknologi MARA (UiTM) Faculty of Computer and Mathematical Sciences Manaf, Mazani
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
advisor	Manaf, Mazani
topic	PL Languages and literatures of Eastern Asia Africa Oceania PL Languages and literatures of Eastern Asia, Africa, Oceania Algorithms
spellingShingle	PL Languages and literatures of Eastern Asia Africa Oceania PL Languages and literatures of Eastern Asia, Africa, Oceania Algorithms Mohamad, Roslim Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad
description	The presence of features such as cursive, diversity of writing styles and sizes of characters in a Jawi text, ligature, and vertical overlapping make the recognition of Jawi handwritten text to be difficult. For the recognition system based on model development using windows, the presence of such features cause the resulting model to be less consistent, where it produces a different sequence of primitive structures of words/sub-words from the same lexicon. To overcome the inconsistency model problem, a handwritten Jawi text recognition system based on a sub-word model has been developed. The proposed modeling technique which is known as Selection Segmentation-Free (SSF) separates core and connection structure of a sub-word into a different window. The resulting window will go through a selection process to determine the windows that will be used to represent the sub-word model. In order to increase accuracy and efficiency of the representation feature, two categories of features which are known as primary and secondary features were extracted from each of the selected windows. Primary feature were extracted using Window Code Representation (WCR) technique from main structure. Secondary feature for supporting the primary feature were extracted from dot and main structure. For the experiment purposes, a total of 1200 sub-words of 80 lexicons were used. Each lexicon is randomly selected and divided into three sets. Three experiments to evaluate the performance of SSF, WCR and combination of primary and secondary feature techniques were conducted. The three techniques are combined to represent the proposed system and compared with the comparison system introduced by Remon (2009). Comparison result shows that the recognition rate of proposed system (84.8%) is better than comparison system (79.1 %).
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Mohamad, Roslim
author_facet	Mohamad, Roslim
author_sort	Mohamad, Roslim
title	Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad
title_short	Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad
title_full	Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad
title_fullStr	Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad
title_full_unstemmed	Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad
title_sort	jawi sub-word recognition system using window-based segmentation-free approach / roslim mohamad
granting_institution	Universiti Teknologi MARA (UiTM)
granting_department	Faculty of Computer and Mathematical Sciences
publishDate	2017
url	https://ir.uitm.edu.my/id/eprint/67546/1/67546.pdf
_version_	1783735696822894592

Jawi sub-word recognition system using window-based segmentation-free approach / Roslim Mohamad

Similar Items