International Journal of Research and Innovation in Applied Science (IJRIAS)
Indian Sign Language Alphabet Recognition Using Transfer Learning with MobileNetV2
Published February 25, 2026 • Vol. 11, Issue 2, pp. 94–101Open Access
DOI: 10.51584/IJRIAS.2026.11020009
Abstract
Indian Sign Language (ISL) recognition plays a vital role in bridging the communication gap between the hearing-impaired community and the general population. This research presents an efficient deep learning-based approach for static ISL alphabet recognition using transfer learning with MobileNetV2. A dataset consisting of 26,000 images representing 26 alphabet classes (A–Z) was used. The proposed model leverages a pre-trained MobileNetV2 backbone for feature extraction, followed by custom classification layers. Experimental results demonstrate a high validation accuracy of 99% and test accuracy 99.89%, indicating the effectiveness of the approach for real-world ISL recognition tasks.
Keywords: Indian Sign Language, Transfer Learning, MobileNetV2, Deep Learning, Image Classification, Gesture Recognition
| Journal | International Journal of Research and Innovation in Applied Science (IJRIAS) |
|---|---|
| ISSN | 2454-6194 |
| Volume / Issue | Volume 11, Issue 2 |
| Pages | 94–101 |
| Publication date | February 25, 2026 |
| DOI | 10.51584/IJRIAS.2026.11020009 |
| Publisher | RSIS International |
| License | Open Access |
How to cite this article
Shalaka Gaikwad, Dr. Girish Katkar, & Dr. Ajay Ramteke (2026). Indian Sign Language Alphabet Recognition Using Transfer Learning with MobileNetV2. International Journal of Research and Innovation in Applied Science (IJRIAS), 11(2), 94-101. https://doi.org/10.51584/IJRIAS.2026.11020009
BibTeX
@article{Shalaka2026,
title = {Indian Sign Language Alphabet Recognition Using Transfer Learning with MobileNetV2},
author = {Shalaka Gaikwad and Dr. Girish Katkar and Dr. Ajay Ramteke},
journal = {International Journal of Research and Innovation in Applied Science (IJRIAS)},
volume = {11},
number = {2},
pages = {94--101},
year = {2026},
doi = {10.51584/IJRIAS.2026.11020009},
publisher = {RSIS International}
}