BdSL36: A Dataset for Bangladeshi Sign Letters Recognition

TL;DR

This paper introduces BdSL36, a large and versatile dataset for Bangladeshi Sign Language recognition, including images with background augmentation and bounding box annotations, to facilitate real-world sign language applications.

Contribution

The creation of BdSL36 dataset with background augmentation and bounding box annotations for improved sign language recognition research.

Findings

Baseline performance established through experiments.

Beta testing indicates potential for real-world application.

Dataset and models publicly available for research.

Abstract

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.