Melola Discovery

← Melola Discovery

Journal SINTA 3

The object detection system of balinese script on traditional Balinese manuscript with findcontours method

Matrix: Jurnal Manajemen Teknologi dan Informatika · Vol. 11 No. 3 (2021) · pp. 177–184

DOI
10.31940/matrix.v11i3.177-184
ISSN
2580-5630, 2088-284X
Published
2021-11-28
Publisher
Unit Publikasi Ilmiah, P3M, Politeknik Negeri Bali
Language
eng

Abstract

Lontar is a traditional Balinese manuscript with a Balinese script in it. Balinese traditional manuscripts can be more than 100 years old. The age factor of the Balinese manuscript has an impact on the Balinese script in it. Balinese script that has been written more than 10 years tends to be darker. This makes Balinese script not visible well, and this affects the image quality of the manuscript. This thing becomes the main issue in this research, Balinese script detection on Balinese manuscript images. the first of all is image processing using edge detection, canny and Sobel becomes the main algorithm of this process. After image processing, the Balinese manuscript will be processed with the findcontour method to detect an object that contains in it. The final process of this detection system is to separate detected objects into three main groups namely noise object, Balinese script object, and hole object. Application (Balinese script object detection system) is more accurate in detecting Balinese script objects in Balinese script under 1 year (new script), it tends to be more likely to find noise/dirt. This is because the writing of the lontar using a pencil first before using the knife media. This adds to the noise or dirt detected by the application The findcontour method can detect Balinese script objects with a detection result of 30% - 70% Balinese script objects.

Keywords

Collaboration network of the authors

8 authors · 11 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Politeknik Negeri Bali
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Ida Bagus Putra ManuabaPoliteknik Negeri Bali1
Irma Nuraeni SalsabilaAffiliation unknown1
Muhammad FahmiAffiliation unknown1
I Komang SudiartaPoliteknik Negeri Bali1
I Gusti Ayu Astri PramitariPoliteknik Negeri Bali1
Putu Gede SukarataAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://ojs2.pnb.ac.id/index.php/MATRIX/oai, first harvested 19 Nov 2026, last seen 19 Nov 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">The object detection system of balinese script on traditional Balinese manuscript with findcontours method</dc:title>
	<dc:creator>Manuaba, Putra</dc:creator>
	<dc:creator>Indah  , Komang Ayu Triana </dc:creator>
	<dc:subject xml:lang="en-US">object detection</dc:subject>
	<dc:subject xml:lang="en-US">Balinese manuscript</dc:subject>
	<dc:subject xml:lang="en-US">edge detection</dc:subject>
	<dc:subject xml:lang="en-US">findcontour</dc:subject>
	<dc:description xml:lang="en-US">Lontar is a traditional Balinese manuscript with a Balinese script in it. Balinese traditional manuscripts can be more than 100 years old. The age factor of the Balinese manuscript has an impact on the Balinese script in it. Balinese script that has been written more than 10 years tends to be darker. This makes Balinese script not visible well, and this affects the image quality of the manuscript. This thing becomes the main issue in this research, Balinese script detection on Balinese manuscript images. the first of all is image processing using edge detection, canny and Sobel becomes the main algorithm of this process. After image processing, the Balinese manuscript will be processed with the findcontour method to detect an object that contains in it. The final process of this detection system is to separate detected objects into three main groups namely noise object, Balinese script object, and hole object. Application (Balinese script object detection system) is more accurate in detecting Balinese script objects in Balinese script under 1 year (new script), it tends to be more likely to find noise/dirt. This is because the writing of the lontar using a pencil first before using the knife media. This adds to the noise or dirt detected by the application The findcontour method can detect Balinese script objects with a detection result of 30% - 70% Balinese script objects.</dc:description>
	<dc:publisher xml:lang="en-US">Unit Publikasi Ilmiah, P3M, Politeknik Negeri Bali</dc:publisher>
	<dc:date>2021-11-28</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ojs2.pnb.ac.id/index.php/MATRIX/article/view/37</dc:identifier>
	<dc:identifier>10.31940/matrix.v11i3.177-184</dc:identifier>
	<dc:source xml:lang="en-US">Matrix : Jurnal Manajemen Teknologi dan Informatika; Vol. 11 No. 3 (2021): Matrix: Jurnal Manajemen Teknologi dan Informatika; 177-184</dc:source>
	<dc:source>2580-5630</dc:source>
	<dc:source>2088-284X</dc:source>
	<dc:source>10.31940/matrix.v11i3</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ojs2.pnb.ac.id/index.php/MATRIX/article/view/37/35</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2021 Matrix : Jurnal Manajemen Teknologi dan Informatika</dc:rights>
	<dc:rights xml:lang="en-US">https://scholar.google.co.id/citations?user=NDE5gXYAAAAJ&amp;hl=id</dc:rights>
</oai_dc:dc>