4. Application of MediaPipe and SVM in sign language recognition to support the hearing impaired
DOI:
https://doi.org/10.61591/jslhu.22.711Từ khóa:
Sign Language Recognition; MediaPipe; Support Vector Machine; Hand Landmark Detection; Vietnamese Sign Language.Tóm tắt
Sign language serves as an essential means of communication for the hearing-impaired community. However, access to and adoption of sign language in Vietnam remain limited due to a lack of resources and supporting tools. To address this issue, this study proposes a Vietnamese Sign Language recognition system that combines MediaPipe technology with the Support Vector Machine (SVM) classification algorithm. The training dataset is constructed from hand gesture images, with MediaPipe responsible for detecting and extracting hand landmark features. These features are then classified using the SVM model. Experimental results demonstrate that the system achieves an accuracy rate between 85% and 90%, confirming its potential to support communication for hearing-impaired individuals through sign language recognition technology.
Tài liệu tham khảo
Tổng cục Thống kê Việt Nam. “Báo cáo Điều tra người khuyết tật năm 2023.” Bộ Kế hoạch và Đầu tư. Hà Nội, Việt Nam.
Zhang, X., Liu, Y., & Wu, J. "Sign Language Recognition: A Comprehensive Review." IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 10, pp. 4302-4320, 2021.
Zhang, Y., Wang, L., & Chen, H. (2021). Sign language recognition based on convolutional neural network and LSTM. Multimedia Tools and Applications, 80(5), 7051–7067.
Kumar, P., Sharma, K., & Kaushik, S. (2020). A deep learning-based framework for real-time sign language recognition using YOLO. Pattern Recognition Letters, 140, 27–34.
Zhang, L., Li, X., & Ma, J. (2022). Real-time sign language recognition using MediaPipe hand tracking and convolutional neural networks. Journal of Visual Communication and Image Representation, 84, 103478.
Abdul, R., Khan, M., & Iqbal, S. (2021). Indian sign language recognition using MediaPipe and KNN. International Journal of Advanced Computer Science and Applications, 12(6), 89–95.
Rahman, F., Hossain, M., & Kim, J. (2019). Hand gesture recognition for sign language using support vector machine with optimal feature selection. Journal of Ambie Intelligence and Humanized Computing, 10(11), 4383–4394.
Nguyen, T. D., Pham, V. H., & Tran, M. Q. (2021). Integrating MediaPipe and SVM for sign language recognition in educational applications. Vietnam Journal of Computer Science, 8(3), 123–135.
Le, H. T., Nguyen, D. K., & Pham, A. T. (2020). Vietnamese sign language recognition using deep learning. Proceedings of the International Conference on Artificial Intelligence and Data Science, 124–129.
Hoang, T. P., Bui, N. H., & Tran, T. D. (2021). A recurrent neural network approach for Vietnamese sign language recognition. Neural Computing and Applications, 33, 10567–10579.
Rane, A., Bhosale, D., Jadhav, S., & Lande, S. (2023). Sign Language Detection of English Alphabets for Deaf and Dumb People. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 11(III), 1743–1747.
Google. (n.d.). *MediaPipe Hands*. Retrieved February 8, 2025, from https://mediapipe.readthedocs.io/en/latest/solutions/hands.html
Schölkopf, B., & Smola, A. J. (2002). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press.
Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques (3rd ed.). Elsevier.
