# BdSL36: A Dataset for Bangladeshi Sign Letters Recognition

arXiv: https://arxiv.org/abs/2110.00869 · HTML: https://mlsanity.com/paper/2110.00869/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 2 Oct 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [3D Hand Shape and Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1903.00812/) (2019)
- [Dataset Augmentation in Feature Space](https://mlsanity.com/paper/1702.05538/) (2017)
- [Smart Augmentation - Learning an Optimal Data Augmentation Strategy](https://mlsanity.com/paper/1703.08383/) (2017)
- [Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation](https://mlsanity.com/paper/1805.09707/) (2018)
- [Real Time Bangladeshi Sign Language Detection using Faster R-CNN](https://mlsanity.com/paper/1811.12813/) (2018)
- [Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition](https://mlsanity.com/paper/1602.09065/) (2016)

## Built on by (most cited first, 7 of 7)

- [Survey on Hand Gesture Recognition from Visual Input](https://mlsanity.com/paper/2501.11992/) (2025)
- [BdSLW60: A Word-Level Bangla Sign Language Dataset](https://mlsanity.com/paper/2402.08635/) (2024)
- [PerSign: Personalized Bangladeshi Sign Letters Synthesis](https://mlsanity.com/paper/2209.14591/) (2022)
- [Word level Bangla Sign Language Dataset for Continuous BSL Recognition](https://mlsanity.com/paper/2302.11559/) (2023)
- [BdSpell: A YOLO-based Real-time Finger Spelling System for Bangla Sign Language](https://mlsanity.com/paper/2309.13676/) (2023)
- [BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation](https://mlsanity.com/paper/2511.12103/) (2025)
- [Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model](https://mlsanity.com/paper/2608.06252/) (2026)

## Abstract (arXiv)

Bangladeshi Sign Language (BdSL) is a commonly used medium of communication for the hearing-impaired people in Bangladesh. A real-time BdSL interpreter with no controlled lab environment has a broad social impact and an interesting avenue of research as well. Also, it is a challenging task due to the variation in different subjects (age, gender, color, etc.), complex features, and similarities of signs and clustered backgrounds. However, the existing dataset for BdSL classification task is mainly built in a lab friendly setup which limits the application of powerful deep learning technology. In this paper, we introduce a dataset named BdSL36 which incorporates background augmentation to make the dataset versatile and contains over four million images belonging to 36 categories. Besides, we annotate about 40,000 images with bounding boxes to utilize the potentiality of object detection algorithms. Furthermore, several intensive experiments are performed to establish the baseline performance of our BdSL36. Moreover, we employ beta testing of our classifiers at the user level to justify the possibilities of real-world application with this dataset. We believe our BdSL36 will expedite future research on practical sign letter classification. We make the datasets and all the pre-trained models available for further researcher.