Official code repository for the paper "A Multifaceted Evaluation of Representation of Graphemes for Practically Effective Bangla OCR". In this paper, we have utilized the popular Convolutional Recurrent Neural Network (CRNN) architecture and implemented our grapheme representation strategies to design the final labels of the model. Due to the absence of a large-scale Bangla word-level printed dataset, we created a synthetically generated Bangla corpus containing 2 million samples that are representative and sufficiently varied in terms of fonts, domain, and vocabulary size to train our Bangla OCR model. To test the various aspects of our model, we have also created 6 test protocols. Finally, to establish the generalizability of our grapheme representation methods, we have performed training and testing on external handwriting datasets.
The dataset and test protocols are be made publicly available at figshare.
10 June 2023: The paper has been accepted for publication in International Journal on Document Analysis and Recognition (IJDAR).
If you find this useful, please cite
@article{roy2023multifaceted,
title={A multifaceted evaluation of representation of graphemes for practically effective Bangla OCR},
author={Roy, Koushik and Hossain, Md Sazzad and Saha, Pritom Kumar and Rohan, Shadman and Ashrafi, Imranul and Rezwan, Ifty Mohammad and Rahman, Fuad and Hossain, BM Mainul and Kabir, Ahmedul and Mohammed, Nabeel},
journal={International Journal on Document Analysis and Recognition (IJDAR)},
pages={1--23},
year={2023},
publisher={Springer}
}