Abstract
Currently, there are millions of people around the world with speech and hearing impairments, and according to the latest census, there are nearly 70,000 people who use Sri Lankan Sign Language. Sign language is a visual language, and it is the main medium of communication in their daily conversations. But they face obstacles when communicating with people who do not know sign language. There are communication barriers in different contexts, such as in work environments, knowledge exchange, and message sharing. Therefore, technology should play a major role in helping people with these hearing and speech impairments to improve their quality of life. This research aims to suggest models that use Google MediaPipe Hand Pose landmarks to identify Sri Lankan Sign Language. Moreover, this article compares vision-based approaches with convolutional neural network (CNN) and recurrent neural network (RNN). We also considered activation functions (such as ReLU, Linear, and Softmax), loss functions (mean squared error (MSE) and Categorical_crossentropy), and optimizations (Adam and Stochastic Gradient Descent (SGD)). The result showed that most algorithms built with Long Short-Term Memory (LSTM), CNN, and CNN-LSTM achieved an accuracy greater than 95%, both with the training dataset and the test dataset. In particular, models with MSE as the loss function and Adam as the optimizer showed higher accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Deafness and hearing loss. http://www.who.int/mediacentre/factsheets/fs300/en/. Accessed 01 Oct 2021
Fernando, P., Wimalaratne, P.: Sign language translation approach to SinhaleseLanguage. GSTF J. Comput. (JoC) 5(1), 1–9 (2016). https://doi.org/10.7603/s40601-016-0009-8
Nirosha, W., Choolangika, S., Vinodya, S.: Sign language translator for deaf and speech impaired people using convolutional neural network. In: 12th International Research Conference on General Sir John Kotelawala Defence (2019)
Malinda, P., Gayan, M.: Computer interpreter for translating written Sinhala to Sinhala sign language. In: OUSL J. 12(1), 70–90 (2017). https://doi.org/10.4038/ouslj.v12i1.7377
Bach, K., Duong, P., Ha, P., Anh, B., Son, N.: Vietnamese sign language detection using Mediapipe. In: 10th International Conference on Software and Computer Applications (ICSCA 2021) (2021). https://doi.org/10.1145/3457784.3457810
Ashok, S., Kiran, R.: Vision based Indian sign language character recognition. J. Theor. Appl. Inf. Technol. 67(3) (2014)
Kishore, P., Panakala, K.: A video based Indian Sign Language Recognition System (INSLR) using wavelet transform and fuzzy logic. Int. J. Eng. Technol. 4(5) (2012). https://doi.org/10.7763/IJET.2012.V4.427
Deepak, S., Deepak, V., Poras, K.: LabVIEW based sign language trainer cum portable display unit for the speech impaired. In: 2015 Annual IEEE India Conference (INDICON) (2015). https://doi.org/10.1109/INDICON.2015.7443381
Sako, S., Hatano, M., Kitamura, T.: Real-time Japanese sign language recognition based on three phonological elements of sign. In: Stephanidis, C. (ed.) HCI 2016. CCIS, vol. 618, pp. 130–136. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-40542-1_21
Madushanka, A., Senevirathne, R., Wijesekara, L., Arunatilake, S., Sandaruwan, K.: Framework for Sinhala sign language recognition and translation using a wearable armband. In: Sixteenth International Conference on Advances in ICT for Emerging Regions (2016). https://doi.org/10.1109/ICTER.2016.7829898
Griselda, S., Jorge, C., Mario, B., Apolonio, P.: Recognition and classification of sign language for Spanish. Computacion y Sistemas22(1), 271–277 (2018). https://doi.org/10.13053/cys-22-1-2780
Hardik, R., Vishal, D., Dhroov, B., Hema, N.: Automated sign language interpreter. In: Eleventh International Conference on Contemporary Computing (2018). https://doi.org/10.1109/IC3.2018.8530658
Ponlawat, C., Kosin, C.: Backhand-view-based continuous-signed-letter recognition using a rewound video sequence and the previous signed-letter information. IEEE Access 9, 40187–40197 (2021). https://doi.org/10.1109/ACCESS.2021.3063203
Tharwat, A., Gaber, T., Hassanien, A.E., Shahin, M.K., Refaat, B.: SIFT-based arabic sign language recognition system. In: Abraham, A., Krömer, P., Snasel, V. (eds.) Afro-European Conference for Industrial Advancement. AISC, vol. 334, pp. 359–370. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-13572-4_30
Zuzanna, P., Carlos-D, M.: Sign language gesture classification using neural networks. In: IBER SPEECH (2018). https://doi.org/10.21437/IberSPEECH.2018-27
Aulia, P., Erdefi, R., Dadan, H.: Human skeleton feature extraction from 2-dimensional video of Indonesian language sign system (SIBI [Sistem Isyarat Bahasa Indonesia]) gestures. In: 5th International Conference on Computing and Artificial Intelligence, pp. 100–105 (2019). https://doi.org/10.1145/3330482.3330484
Sobia F., Yasar, A.: CNN and traditional classifiers performance for sign language recognition. In: 3rd International Conference on Machine Learning and Soft Computing, pp. 192–196 (2019). https://doi.org/10.1145/3310986.3311011
Darmana, A., Erdefi, R.: Generating of Sign System for Bahasa Indonesia (SIBI) root word gestures using deep temporal sigmoid belief network. In: ICCAI 2019: Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence, pp. 221–225 (2019). https://doi.org/10.1145/3330482.3330494
Pisit, N., Patcharee, M., Tatpong, K.: Thai finger spelling localization and classification under complex background using a YOLO-based deep learning. In: 11th International Conference on Computer Modeling and Simulation, pp. 230–233 (2019). https://doi.org/10.1145/3307363.3307403
Huang, C., Wang, F., Zhang, R.: Sign language recognition based on CBAM-ResNet. In: International Conference on Artificial Intelligence and Advanced Manufacturing, no. 48, pp. 1–6 (2019). https://doi.org/10.1145/3358331.3358379
Kirtee, P., Sreemathy, R., Akshay, V.: Recognition of Indian sign language alphabets for hearing and speech impaired people using deep learning. SSRN Electron. J. (2019). https://doi.org/10.2139/ssrn.3430055
Heike, B., Felix, L., Kazuhiro, N., Yuji, N.: Learning three-dimensional skeleton data from sign language video. ACM Trans. Intell. Syst. Technol. 11(3) (2020). https://doi.org/10.1145/3377552
Neha, N., Saloni, M., Sandhya, A., Ekansh, T.: A dynamic gesture recognition system for mute person. In: Goyal, D., Gupta, A.K., Piuri, V., Ganzha, M., Paprzycki, M. (eds.) Proceedings of the Second International Conference on Information Management and Machine Intelligence. LNNS, vol. 166, pp. 33–39. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-9689-6_4
Amrita, T., Pujan, B., Sarmila, U., Shirish, S., Subarna, S.: Real time sign language recognition and speech generation. J. Innov. Image Process. 2(2), 65–76 (2020). https://doi.org/10.36548/jiip.2020.2.001
Taniya, S., Soumi, P., Subhadip, B., Ayatullah, M.: Hand sign recognition from depth images with multi-scale density features for deaf mute persons. International Conference on Computational Intelligence and Data Science (2019). https://doi.org/10.1016/j.procs.2020.03.243
Biao, X., Shiliang, H., Zhongfu, Y.: Application of tensor train decomposition in S2VT model for sign language recognition. IEEE Access 9, 35646–35653 (2021). https://doi.org/10.1109/ACCESS.2021.3059660
Astri, N., Fairuz, A.: Sign language recognition using principal component analysis and support vector machine. Int. J. Appl. Inf. Technol. 4(1) (2021). https://doi.org/10.25124/ijait.v4i01.3015
Chengcheng, W., Jian, Z., Wengang, Z., Houqiang, Li.: Semantic boundary detection with reinforcement learning for continuous sign language recognition. In: IEEE Trans. Circuits Syst. Video Technol. 31, 1138–1149 (2021). https://doi.org/10.1109/TCSVT.2020.2999384
Mohamed, B., et al.: Arabic Sign language recognition system using 2D hands and body skeleton data. IEEE Access 9, 59612–59627 (2021). https://doi.org/10.1109/ACCESS.2021.3069714
Lu, J., Nguyen, M., Yan, W.Q.: Sign language recognition from digital videos using deep learning methods. In: Nguyen, M., Yan, W.Q., Ho, H. (eds.) ISGV 2021. CCIS, vol. 1386, pp. 108–118. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72073-5_9
Prikhodko, A., Grif, M., Bakaev, M.: Sign language recognition based on notations and neural networks. In: Alexandrov, D.A., Boukhanovsky, A.V., Chugunov, A.V., Kabanov, Y., Koltsova, O., Musabirov, I. (eds.) DTGS 2020. CCIS, vol. 1242, pp. 463–478. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65218-0_34
Anusorn, C., Kritsana, S., Thidalak, Y.: Thai sign language recognition: an application of deep neural network. In: 2021 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering (2021). https://doi.org/10.1109/ECTIDAMTNCON51128.2021.9425711
Acknowledgement
I express my great appreciation to the Department of Computing and Information Systems, Faculty of Applied Sciences, Sabaragamuwa University of Sri Lanka for providing opportunities, guidance, advice, tremendous encouragement, endless experimental recommendations, a lot of precious time, and endless assistance for the success of this study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Herath, R.J., Ishanka, P. (2022). An Approach to Sri Lankan Sign Language Recognition Using Deep Learning with MediaPipe. In: Motahhir, S., Bossoufi, B. (eds) Digital Technologies and Applications. ICDTA 2022. Lecture Notes in Networks and Systems, vol 454. Springer, Cham. https://doi.org/10.1007/978-3-031-01942-5_45
Download citation
DOI: https://doi.org/10.1007/978-3-031-01942-5_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-01941-8
Online ISBN: 978-3-031-01942-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)