# End-to-End Optical Character Recognition for Bengali Handwritten Words

arXiv: https://arxiv.org/abs/2105.04020 · HTML: https://mlsanity.com/paper/2105.04020/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 9 May 2021.

## Builds on (most cited first, 8 of 8)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [BanglaWriting: A multi-purpose offline Bangla handwriting dataset](https://mlsanity.com/paper/2011.07499/) (2020)
- [FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets](https://mlsanity.com/paper/2101.05564/) (2021)
- [Blockchain for Decentralized Multi-Drone to Combat COVID-19](https://mlsanity.com/paper/2102.00969/) (2021)

## Built on by (most cited first, 4 of 4)

- [LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting Recognition](https://mlsanity.com/paper/2205.11420/) (2022)
- [Optical Text Recognition in Nepali and Bengali: A Transformer-based Approach](https://mlsanity.com/paper/2404.02375/) (2024)
- [GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer](https://mlsanity.com/paper/2509.18081/) (2025)
- [An End-to-End Khmer Optical Character Recognition using Sequence-to-Sequence with Attention](https://mlsanity.com/paper/2106.10875/) (2021)

## Abstract (arXiv)

Optical character recognition (OCR) is a process of converting analogue documents into digital using document images. Currently, many commercial and non-commercial OCR systems exist for both handwritten and printed copies for different languages. Despite this, very few works are available in case of recognising Bengali words. Among them, most of the works focused on OCR of printed Bengali characters. This paper introduces an end-to-end OCR system for Bengali language. The proposed architecture implements an end to end strategy that recognises handwritten Bengali words from handwritten word images. We experiment with popular convolutional neural network (CNN) architectures, including DenseNet, Xception, NASNet, and MobileNet to build the OCR architecture. Further, we experiment with two different recurrent neural networks (RNN) methods, LSTM and GRU. We evaluate the proposed architecture using BanglaWritting dataset, which is a peer-reviewed Bengali handwritten image dataset. The proposed method achieves 0.091 character error rate and 0.273 word error rate performed using DenseNet121 model with GRU recurrent layer.