BonoNet: a deep convolutional neural network for recognizing bangla compound characters
Open Access
- 1 October 2025
- journal article
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (5) , 4171-4180
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
This publication has 25 references indexed in Scilit:
- Bangla Sign Language Recognition With Multimodal Deep Learning FusionEngineering Reports, 2025
- Proposed method of acquiring train data for early-modern Japanese printed character recognizersThe Journal of Supercomputing, 2025
- Tamil NLP Technologies: Challenges, State of the Art, Trends and Future Scope2023
- Bangla Handwritten Digit Recognition using RNN-CNN Hybrid Approach2022
- KDANet: Handwritten Character Recognition for Bangla Language using Deep Learning2022
- A squeeze and excitation ResNeXt-based deep learning model for Bangla handwritten compound character recognitionJournal of King Saud University Computer and Information Sciences, 2022
- Bangla Handwritten Character Recognition Using Deep Convolutional Autoencoder Neural Network2020
- AIBangla: A Benchmark Dataset for Isolated Bangla Handwritten Basic and Compound Character Recognition2019
- Bengali Handwritten Alphabet Recognition using Deep Convolutional Neural Network2019
- Shape decomposition-based handwritten compound character recognition for Bangla OCRJournal of Visual Communication and Image Representation, 2018