Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

BonoNet: a deep convolutional neural network for recognizing bangla compound characters

IAES International Journal of Artificial Intelligence · Vol. 14 No. 5 (2025) · pp. 4171–4180

DOI
10.11591/ijai.v14.i5.pp4171-4180
ISSN
2252-8938, 2089-4872
Published
2025-10-01
Publisher
Institute of Advanced Engineering and Science
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

The bangla alphabet includes vowels, consonants, and compound symbols. The compound nature of bangla is a product of combining two or more root bangla characters into one graph. They are difficult to differentiate because they have a sophisticated geometric shape and an immense variety of scripts used by different places and individuals. This is one of the greatest challenges in creating effective optical character recognition (OCR) systems for bangla. In this paper, a deep convolutional neural network (DCNN)-based system is presented to identify bangla compound characters with high precision. The model was trained using the AIBangla dataset. It has about 171 classes of bangla compound characters. A DCNN system, BonoNet, was designed to classify compound characters. BonoNet outperformed all other state-of-the-art architecture on the test set and improved over current state-of-the-art architecture methods. BonoNet will greatly improve the automation and analysis of the bangla language by accurately identifying these compound complex characters.

Keywords

Collaboration network of the authors

24 authors · 65 co-authorship links · 12 across different organisations

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

  • Daffodil International University
  • Bangladesh University of Professionals
  • Universiti Sains Malaysia
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Md. Shohel ArmanDaffodil International University2
Rozina AkterDaffodil International University1
Thurasamy RamayahUniversiti Sains Malaysia1
Md. Tazmim HossainDaffodil International University1
Md. Arafat Rahman TalukderDaffodil International University1
Md. Tanvir AhmedAffiliation unknown1
Imran AhmedDaffodil International University1
Rubayed Ahmmad RakinDaffodil International University1
Mst. Tuhin AkterDaffodil International University1
Rashidul Hasan HridoyDaffodil International University1
Arindra Dey ArniDaffodil International University1
Shomitro Kumar GhoshDaffodil International University1
Narayan Ranjan ChakrabortyDaffodil International University1
Md. Sabbir AhmedDaffodil International University1
Md. Hafizul ImranDaffodil International University1
Musabbir SmmakDaffodil International University1
Touhid BhuiyanAffiliation 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) http://ijai.iaescore.com/index.php/IJAI/oai, first harvested 8 Nov 2026, last seen 16 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">BonoNet: a deep convolutional neural network for recognizing bangla compound characters</dc:title>
	<dc:creator>Ahmed, Kazi Rifat</dc:creator>
	<dc:creator>Jahan, Nusrat</dc:creator>
	<dc:creator>Masud, Adiba</dc:creator>
	<dc:creator>Tasnim, Nusrat</dc:creator>
	<dc:creator>Sharmin, Sazia</dc:creator>
	<dc:creator>Mim, Nusrat Jahan</dc:creator>
	<dc:creator>Mahmud, Imran</dc:creator>
	<dc:subject xml:lang="en-US"></dc:subject>
	<dc:subject xml:lang="en-US">Bangla; BonoNet; Compound characters; Deep convolutional neural  network; Handwritten; Optical character recognition</dc:subject>
	<dc:description xml:lang="en-US">The bangla alphabet includes vowels, consonants, and compound symbols. The compound nature of bangla is a product of combining two or more root bangla characters into one graph. They are difficult to differentiate because they have a sophisticated geometric shape and an immense variety of scripts used by different places and individuals. This is one of the greatest challenges in creating effective optical character recognition (OCR) systems for bangla. In this paper, a deep convolutional neural network (DCNN)-based system is presented to identify bangla compound characters with high precision. The model was trained using the AIBangla dataset. It has about 171 classes of bangla compound characters. A DCNN system, BonoNet, was designed to classify compound characters. BonoNet outperformed all other state-of-the-art architecture on the test set and improved over current state-of-the-art architecture methods. BonoNet will greatly improve the automation and analysis of the bangla language by accurately identifying these compound complex characters.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US"></dc:contributor>
	<dc:date>2025-10-01</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"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijai.iaescore.com/index.php/IJAI/article/view/26734</dc:identifier>
	<dc:identifier>10.11591/ijai.v14.i5.pp4171-4180</dc:identifier>
	<dc:source xml:lang="en-US">IAES International Journal of Artificial Intelligence (IJ-AI); Vol 14, No 5: October 2025; 4171-4180</dc:source>
	<dc:source>2252-8938</dc:source>
	<dc:source>2089-4872</dc:source>
	<dc:source>10.11591/ijai.v14.i5</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijai.iaescore.com/index.php/IJAI/article/view/26734/14753</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Kazi Rifat Ahmed, Nusrat Jahan, Adiba Masud, Nusrat Tasnim, Sazia Sharmin, Nusrat Jahan Mim, Imran Mahmud</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>