Sign language is an important communication method for individuals with hearing and speech impairments. However, communication between sign language users and people who do not understand sign language remains challenging. This paper presents a deep learning–based system for Sign Language to Text Conversion using the MobileNetV2 architecture for efficient feature extraction. Hand gesture images are first preprocessed to improve image quality and then passed through a MobileNetV2-based Convolutional Neural Network (CNN) to extract important features. To improve model performance, hyperparameter optimization techniques such as learning rate tuning, batch size adjustment, optimizer selection, dropout regularization and epoch variation are applied. The extracted features are classified using a Softmax classifier to recognize gestures and convert them into readable text. The system provides an efficient solution for assistive communication and accessibility applications.

The proposed system addresses the communication challenges faced by hearing and speech-impaired individuals by providing an automated sign language recognition solution. The system utilizes deep learning techniques to interpret hand gestures and convert them into meaningful text. By integrating modules such as image acquisition, preprocessing, feature extraction using the MobileNet architecture, hyperparameter optimization and classification, the system ensures efficient and accurate gesture recognition. The use of a lightweight model improves computational efficiency while maintaining reliable performance. Experimental results demonstrate that the system effectively recognizes sign language gestures and generates appropriate text outputs. Overall, the proposed solution contributes to enhancing accessibility and reducing communication barriers through the application of artificial intelligence. Future improvements may include expanding the dataset, supporting real-time continuous recognition and increasing system robustness in diverse environments.

1.Al-Hammadi M., Muhammad G., Abdul W., Alsulaiman M., Bencherif A., Mekhtiche M., “Hand Gesture Recognition for Sign Language Using 3DCNN,” IEEE Access, vol. 8, pp. 79491–79509, 2020. 2.Al-Qurishi M., Khalid T., Souissi R., “Deep Learning for Sign Language Recognition: Current Techniques, Benchmarks, and Open Issues,” IEEE Access, vol. 9, pp. 126917–126945, 2021. 3.Bhat A., Yadav V., Dargan V., Yash Y., “Sign Language to Text Conversion using Deep Learning,” in Proc. 3rd Int. Conf. on Emerging Technology (INCET), 2022. 4.Kumar S., Rani R., Chaudhari U., “Real-time Sign Language Detection: Empowering the Disabled Community,” MethodsX, vol. 13, p. 102901, 2024. 5.Tao T., Zhao Y., Liu T., Zhu J., “Sign Language Recognition: A Comprehensive Review of Traditional and Deep Learning Approaches, Datasets, and Challenges,” IEEE Access, vol. 12, pp. 75034–75060, 2024. 6.Al Abdullah B. A., Amoudi G. A., Alghamdi H. S., “Advancements in Sign Language Recognition: A Comprehensive Review and Future Prospects,” IEEE Access, vol. 12, pp. 128871–128890, 2024. 7.Najib F. M., “A Multi-Lingual Sign Language Recognition System Using Machine Learning,” Multimedia Tools and Applications, vol. 84, pp. 27988–28011, 2025. 8.Tsoplatov M., Wookyeol W., Jun J., Lee S., “Deep Learning Pathways for Automatic Sign Language Processing,” Pattern Recognition, vol. 164, p. 111475, 2025. 9.Karkar A., Khot A., Andure A., Ghosh A., Magadum A., Bahadur A., Pol M., “Real-Time Sign Language to Text Translation using Deep Learning: A Comparative Study of LSTM and 3D CNN,” International Journal of Computer Applications, vol. 187, no. 35, pp. 31–36, 2025. Sharath S. R., Suraj S., Abishek Kumar G. M., P. Siddharth, NalinaDevi K., “Sign Language to Sign Language Translator,” Procedia Computer Science, vol. 260, pp. 373–381, 2025.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close