Recognition of Bangla Sign Language for Letters and Words using Hand Gestures and Predictive Analytics

DOI

10.2991/978-94-6239-664-7_87How to use a DOI?

Keywords

Communication; BdSL; Image Augmentation; Convulational Neural Network (CNN); KPI; MobileNet; VGG16

Abstract

Sign language is the primary means of communication for people who are deaf. Despite the availability of enough research work for English Sign Language, research work on Bangla Sign Language (BdSL), particularly including both the letters and words, is limited. This paper assesses various models for the recognition of BdSL letters, words, and the combination of them through Machine Learning (ML) and Deep Learning (DL) models. Initially, the BdSL47 dataset (47,000 images for 47 different signs) was used to assess all the models. Following that, the 30-word BdSL dataset consisting of 1,200 images was augmented to contain 4,800 images. Finally, the augmented 30-word BdSL dataset was merged together with the BdSL47 dataset. Again, all the various models proposed in the paper were used for model assessment. Models used for the assessment in the proposed paper work include CNN model, MobileNetV2 model, VGG 16 model, KNN model, and Random Forest model. Deep Learning models deliver the best results for the merged vocabulary dataset in the proposed research work by giving 98.44% accuracy compared to the ML models like Random Forest and KNN.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Mohammad Sabbir Musfique
AU  - Asir Ahbab Raiyan
AU  - Munjib Hasan Chowdhury
AU  - Md.Enamul Hoque Marzun
AU  - Md.Abdus Sattar
AU  - Muhammad Nazrul Islam
PY  - 2026
DA  - 2026/06/08
TI  - Recognition of Bangla Sign Language for Letters and Words using Hand Gestures and Predictive Analytics
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 1291
EP  - 1300
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_87
DO  - 10.2991/978-94-6239-664-7_87
ID  - Musfique2026
ER  -