# Bengali Handwritten Grapheme Classification: Deep Learning Approach

arXiv: https://arxiv.org/abs/2111.08249 · HTML: https://mlsanity.com/paper/2111.08249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 6 of 6)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Brain Tumor Segmentation with Deep Neural Networks](https://mlsanity.com/paper/1505.03540/) (2015)
- [Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification](https://mlsanity.com/paper/1309.0261/) (2013)
- [A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes](https://mlsanity.com/paper/2010.00170/) (2020)
- [Handwritten Isolated Bangla Compound Character Recognition: a new benchmark using a novel deep learning approach](https://mlsanity.com/paper/1802.00671/) (2018)

## Abstract (arXiv)

Despite being one of the most spoken languages in the world (6th based on population), research regarding Bengali handwritten grapheme (smallest functional unit of a writing system) classification has not been explored widely compared to other prominent languages. Moreover, the large number of combinations of graphemes in the Bengali language makes this classification task very challenging. With an effort to contribute to this research problem, we participate in a Kaggle competition citekagglelink where the challenge is to separately classify three constituent elements of a Bengali grapheme in the image: grapheme root, vowel diacritics, and consonant diacritics. We explore the performances of some existing neural network models such as Multi-Layer Perceptron (MLP) and state of the art ResNet50. To further improve the performance we propose our own convolution neural network (CNN) model for Bengali grapheme classification with validation root accuracy 95.32%, vowel accuracy 98.61%, and consonant accuracy 98.76%. We also explore Region Proposal Network (RPN) using VGGNet with a limited setting that can be a potential future direction to improve the performance.