Abstract
Sign language recognition is beneficial to help the hearing-impaired and the healthy communicate effectively and help hearing-impaired people integrate into society, making their study, work, and life more convenient, especially in speech therapy and rehabilitation. Fingerspelling identification plays an important role in sign language recognition, which has unique advantages in expressing abstract content, terminology, and specific words, and can also be utilized as the basis of learning gesture recognition based on Pinyin rules. We proposed a WE-kSVM approach, carrying out on 10-fold cross-validation, and achieved an overall accuracy of 88.76 ± 0.59%. Maximum accuracy is 89.40% based on thirty categories. Here, Wavelet entropy technique can reduce the number of features and accelerate the training. Gaussian kernel (RBF) provided excellent classification performance. Meanwhile, 10-fold cross-validation prevented overfitting effectively. The experiment results indicate that our method is superior to the other five state-of-the-art approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cao, X.: Development of Wearable Sign Language Translator. University of Science and Technology of China, Hefei (2015)
Li, T.S., Kao, M., Kuo, P.: Recognition system for home-service-related sign language using entropy-based K-means algorithm and ABC-based HMM. IEEE Trans. Syst. Man Cybern. Syst. 46(1), 150–162 (2016)
Jihai Zhang, W.Z., Li, H.: A threshold-based hmm-DTW approach for continuous sign language recognition. In: Proceedings of ACM International Conference on Internet Multimedia Computing and Service, p. 237 (2014)
Long Wang, H.L., Wang, B., et al.: Gesture recognition method based on skin color model and convolutional neural network. Comput. Eng. Appl. 53(6), 209–214 (2017)
Jiang, X.: Chinese sign language fingerspelling recognition via six-layer convolutional neural network with leaky rectified linear units for therapy and rehabilitation. J. Med. Imaging Health Inform. 9(9), 2031–2038 (2019)
Wu, D., Kindermans, P.J., et al.: Deep dynamic neural networks for multimodal gesture segmentation and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(8), 1583–1597 (2016)
Cui, L.H., Zhang, C.: Recurrent convolutional neural networks for continuous sign language recognition by staged optimization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1610–1618. IEEE (2017)
Huang, J.Z.W., Li, H et al.: Attention based 3D-CNNs for large-vocabulary sign language recognition. IEEE Trans. Circ. Syst. Video Technol. 1, 1 (2018)
Yang, H.-D., Lee, S.-W.: Robust sign language recognition with hierarchical conditional random fields. In: 20th International Conference on Pattern Recognition, Istanbul, Turkey, pp. 2202–2205. IEEE (2010)
Rao, G.A., Kishore, P., Kumar, D.A., Sastry, A.: Neural network classifier for continuous sign language recognition with selfie video. Far East J. Electron. Commun. 17(1), 49 (2017)
Jiang, X.: Isolated Chinese sign language recognition using gray-level co-occurrence matrix and parameter-optimized medium gaussian support vector machine. In: Frontiers in Intelligent Computing: Theory and Applications. Singapore, 2020, pp. 182–193: Springer Singapore
Kumar, P., Saini, R., Roy, P.P.: A position and rotation invariant framework for sign language recognition (SLR) using Kinect. Multimedia Tools Appl. 77, 8823–8846 (2017)
Lee, G.C., Yeh, F., Hsiao, Y.: Kinect-based Taiwanese sign-language recognition system. Multimedia Tools Appl. 75, 261–279 (2016)
Ng, E.Y.K., Kaw, G.J.L., Chang, W.M.: Analysis of IR thermal imager for mass blind fever screening. Microvasc. Res. Article 68(2), 104–109 (2004). (in English)
Ng, E.Y.-K., Acharya, R.U.: Imaging as a diagnostic and therapeutic tool in clinical oncology. World J. Clin. Oncol. 2(4), 169 (2011)
Artoni, A.D.F., Makeig, S.: Applying dimension reduction to EEG data by Principal Component Analysis reduces the quality of its subsequent Independent Component decomposition. NeuroImage 175, 176–187 (2018)
Yang, J.: An adaptive encoding learning for artificial bee colony algorithms. J. Comput. Sci. 30, 11–27 (2019)
Liu, J.: Detecting cerebral microbleeds with transfer learning. Mach. Vis. Appl. https://doi.org/10.1007/s00138-019-01029-5
Lu, S.: Pathological Brain Detection based on AlexNet and transfer learning. J. Comput. Sci. 30, 41–47 (2019)
Acknowledgements
This work was supported from Jiangsu Overseas Visiting Scholar Program for University Prominent Young and Middle-aged Teachers and Presidents of China, The Natural Science Foundation of Jiangsu Higher Education Institutions of China (19KJA310002), The Surface Project of Natural Science Research in Colleges and Universities of Jiangsu China (16KJB520029, 16KJB520026), The Philosophy and Social Science Research Foundation Project of Universities of Jiangsu Province (2017SJB0668).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhu, Z., Zhang, M., Jiang, X. (2021). Fingerspelling Identification for Chinese Sign Language via Wavelet Entropy and Kernel Support Vector Machine. In: Satapathy, S., Zhang, YD., Bhateja, V., Majhi, R. (eds) Intelligent Data Engineering and Analytics. Advances in Intelligent Systems and Computing, vol 1177. Springer, Singapore. https://doi.org/10.1007/978-981-15-5679-1_52
Download citation
DOI: https://doi.org/10.1007/978-981-15-5679-1_52
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-5678-4
Online ISBN: 978-981-15-5679-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)