Improved Classification of Handwritten Jawi Script
Based on Main Part of Script Body
Dublin Core
Title
Improved Classification of Handwritten Jawi Script
Based on Main Part of Script Body
Based on Main Part of Script Body
Subject
jawi script; FCC; SVM; the shape of the main part of the character; decision-making rules
Description
Since the entry of Islam, many ancient relics in the archipelago were written using Jawi script. Due to human or natural factors,
these ancient relics will be damaged or destroyed. To avoid the loss of this ancient heritage data, the data must be stored in
digital documents. In order to convert digital documents into machine-readable text format, the use of Optical Character
Recognition (OCR) technology is inevitable. In this research, OCR technology is implemented on isolated Jawi scripts.
Freeman Chain Code (FCC) is used to extract the isolated Jawi script features. Subsequently, the FCC feature is fed into
Support Vector Machine (SVM) in order to classify the character. The decision rule classification is applied to the class of
SVM classification in the Jawi script form. The results of the SVM classification into 19 classes reached 81.58%, while the
results for merging into 15 classes produced better results with the accuracy 84.21%. Feature extraction of dot location is
divided into the top, middle, and bottom. Feature extraction of the number of dotss is done by counting the number of dots,
while feature extraction of the presence of holes is carried out by detecting the presence of holes in the characters. These
features are applied to the class of results from SVM classification with decision-making rules. The percentage of success in
applying the decision rules to the results of the classification of incorporation into 15 classes by SVM reached 92.86%. Further
research will be conducted to determine the effect of the feature of the location of the dot and the number of dots on the shape
of the main part of the character
these ancient relics will be damaged or destroyed. To avoid the loss of this ancient heritage data, the data must be stored in
digital documents. In order to convert digital documents into machine-readable text format, the use of Optical Character
Recognition (OCR) technology is inevitable. In this research, OCR technology is implemented on isolated Jawi scripts.
Freeman Chain Code (FCC) is used to extract the isolated Jawi script features. Subsequently, the FCC feature is fed into
Support Vector Machine (SVM) in order to classify the character. The decision rule classification is applied to the class of
SVM classification in the Jawi script form. The results of the SVM classification into 19 classes reached 81.58%, while the
results for merging into 15 classes produced better results with the accuracy 84.21%. Feature extraction of dot location is
divided into the top, middle, and bottom. Feature extraction of the number of dotss is done by counting the number of dots,
while feature extraction of the presence of holes is carried out by detecting the presence of holes in the characters. These
features are applied to the class of results from SVM classification with decision-making rules. The percentage of success in
applying the decision rules to the results of the classification of incorporation into 15 classes by SVM reached 92.86%. Further
research will be conducted to determine the effect of the feature of the location of the dot and the number of dots on the shape
of the main part of the character
Creator
Safrizal Razali1
, Fitri Arnia2
, Rusdha Muharrar3
, Kahlil Muchtar4
, Akhyar Bintang5
, Fitri Arnia2
, Rusdha Muharrar3
, Kahlil Muchtar4
, Akhyar Bintang5
Publisher
Syiah Kuala University
Date
03-02-2023
Contributor
Fajar bagus W
Format
PDF
Language
Indonesia
Type
Text
Files
Collection
Citation
Safrizal Razali1
, Fitri Arnia2
, Rusdha Muharrar3
, Kahlil Muchtar4
, Akhyar Bintang5, “Improved Classification of Handwritten Jawi Script
Based on Main Part of Script Body,” Repository Horizon University Indonesia, accessed June 7, 2025, https://repository.horizon.ac.id/items/show/9343.
Based on Main Part of Script Body,” Repository Horizon University Indonesia, accessed June 7, 2025, https://repository.horizon.ac.id/items/show/9343.