**Challenge and dataset summary paper available at [https://arxiv.org/abs/2010.00170](https://arxiv.org/abs/2010.00170)**

Bengali is the 5th most spoken language in the world with hundreds of million of speakers. It’s the official language of Bangladesh and the second most spoken language in India. Considering its reach, there’s significant business and educational interest in developing AI that can optically recognize images of the language handwritten. This challenge hopes to improve on approaches to Bengali recognition.
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1095143%2Fa9a48686e3f385d9456b59bf2035594c%2Fdesc.png?generation=1576531903599785&alt=media)
Optical character recognition is particularly challenging for Bengali. While Bengali has 49 letters (to be more specific 11 vowels and 38 consonants) in its alphabet, there are also 18 potential diacritics, or accents. This means that there are many more graphemes, or the smallest units in a written language. The added complexity results in ~13,000 different grapheme variations (compared to English’s 250 graphemic units).

Bangladesh-based non-profit [Bengali.AI](https://bengali.ai/) is focused on helping to solve this problem. They build and release crowdsourced, metadata-rich datasets and open source them through research competitions. Through this work, Bengali.AI hopes to democratize and accelerate research in Bengali language technologies and to promote machine learning education.

For this competition, you’re given the image of a handwritten Bengali grapheme and are challenged to separately classify three constituent elements in the image: grapheme root, vowel diacritics, and consonant diacritics.

By participating in the competition, you’ll hopefully accelerate Bengali handwritten optical character recognition research and help enable the digitalization of educational resources. Moreover, the methods introduced in the competition will also empower cousin languages in the Indian subcontinent.

Acknowledgements:
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1132983%2F855c588bba1f95466df0d5fab35bf36e%2Fapurba_logo.png?generation=1576881517547084&alt=media)
[Apurba](http://www.apurbatech.com)
:
Apurba is the exclusive sponsor of Bengali.AI for this competition. Apurba Technologies Inc. is founded by a group of technology veterans who have been working at the cutting edge of software development in Silicon Valley for many years. Apart from its many ventures, Apurba is a pioneer in Bengali NLP research today and is accelerating AI research in Bangladesh through its contributions.
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1132983%2Fb96aa3c59828e5766a86d27cf95a63e5%2FIML_logo.png?generation=1576881594739031&alt=media)
Intelligent Machines Limited:
Intelligent Machines Limited is the technical partner of Bengali.AI for this competition and is providing compute support to Bangladeshi students. IML is an Artificial Intelligence and Advanced Analytics startup offering customized solutions to businesses in Bangladesh. IML believes in the strength of Bangladeshi talented resources and in the possibility of a far greater and developed Bangladesh in the coming days.
**If you use this dataset in your research, please cite this paper**
@inproceedings{alam2021large,
  title={A Large Multi-target Dataset of Common Bengali Handwritten Graphemes},
  author={Alam, Samiul and Reasat, Tahsin and Sushmit, Asif Shahriyar and Siddique, Sadi Mohammad and Rahman, Fuad and Hasan, Mahady and Humayun, Ahmed Imtiaz},
  booktitle={International Conference on Document Analysis and Recognition},
  pages={383--398},
  year={2021},
  organization={Springer}
}