Multilingual sign language translation using image-based classification models for Bangla, American, and Indian languages with ResNet and EfficientNet
| dc.contributor.advisor | Dr. Saadia Binte Alam | en_US |
| dc.contributor.author | Biswas, Sudipto | |
| dc.date.accessioned | 2026-09-13T14:35:28Z | |
| dc.date.available | 2026-09-13T14:35:28Z | |
| dc.date.issued | 2025-12-14 | |
| dc.identifier.other | ID 2222391 | |
| dc.identifier.uri | https://ar.iub.edu.bd/handle/11348/1579 | |
| dc.description | This thesis is submitted in partial fulfilment of the requirements for the degree of Bachelor of Science (BSc) in Computer Science and Engineering (CSC), 2026. | |
| dc.description.abstract | This study proposes a multilingual sign language recognition system for Bangla Sign Language (BdSL), American Sign Language (ASL), and Indian Sign Language (ISL). It uses ResNet50 and EfficientNetB0 to recognize static hand gestures from images. ResNet50 performs well in identifying visually similar signs, while EfficientNetB0 offers lower computational cost, making it suitable for portable applications. The study highlights limitations in recognizing continuous gestures and recommends future research using video data, LSTM or transformer-based models, and real-time mobile/web applications. | en_US |
| dc.format.extent | 47 pages | |
| dc.language.iso | en | en_US |
| dc.publisher | Independent University, Bangladesh (IUB) | en_US |
| dc.rights | Theses submitted to Independent University, Bangladesh, are protected by copyright. They may be accessed for academic and research purposes; however, reproduction, distribution, or use of the material in any form requires prior written permission from the University. | |
| dc.subject | Sign Language Recognition | en_US |
| dc.subject | Multilingual Translation | en_US |
| dc.subject | Bangla Sign Language (BdSL) | en_US |
| dc.subject | American Sign Language (ASL) | en_US |
| dc.subject | Indian Sign Language (ISL) | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Image Classification | en_US |
| dc.subject | ResNet50 | en_US |
| dc.subject | EfficientNetB0 | en_US |
| dc.subject | Computer Vision | en_US |
| dc.title | Multilingual sign language translation using image-based classification models for Bangla, American, and Indian languages with ResNet and EfficientNet | en_US |
| dc.type | Thesis | en_US |
| dc.contributor.department | Department of Computer Science & Engineering |
Files in this item
This item appears in the following Collection(s)
-
Undergraduate Thesis [67]
By CSE Department
Related items
Showing items related by title, author, creator and subject.
-
Role of English language and literature studies in achieving sustainable socio-economic development among tertiary students in Bangladesh
(School of Business and Entrepreneurship, Independent University, Bangladesh (IUB), 2025-11)The curriculum for English language and literature studies at universities in Bangladesh is designed to meet appropriate linguistic and cognitive standards through second language acquisition. This can be achieved through ... -
An Exploratory Approach to Find a Novel Metric Based Optimum Language Model for Automatic Bangla Word Prediction
(International Journal of Intelligent Systems and Applications, 2020-09-27)Word completion and word prediction are two important phenomena in typing that have intense effect on aiding disable people and students while using keyboard or other similar devices. Such auto completion technique also ... -
Teach Yourself NIHONGO
(Anwar Faridee MAGNUM OPUS, 2008-06-01)In Japanese, Japan is called Nihon or Nippon, and the Japanese language is called “Nihon-go” or "Nippon-go" (-go means language). The Japanese language is very different from English and most other European languages. ...
