- Title
- Sign language digits and alphabets recognition by capsule networks
- Creator
- Xiao, Hongwang; Yang, Yun; Yu, Ke; Tian, Jiao; Cai, Xinyi; Muhammad, Usman; Chen, Jinjun
- Date
- 2022
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/186098
- Identifier
- vital:16838
- Identifier
-
https://doi.org/10.1007/s12652-021-02974-8
- Identifier
- ISBN:1868-5137 (ISSN)
- Abstract
- There exist communication barriers between the deaf people and the listeners. Sign language translation is a reasonable and effective way to break these barriers. Recognition of sign language symbols is an essential part of sign language translation. Sign language digits of (0–9) and alphabetic letters of (A–Z) are elementary but important symbols of sign languages of different countries or regions. Capsule networks (CapsNet) are promising alternative to convolutional neural networks (CNN), which take into account of the spatial relationships and orientations of the features of an entity. For sign language digits and alphabets recognition tasks, the proposed SLR-CapsNet architecture achieves a start-of-the-art test accuracy of 99.52% with 100*100 RGB input size and 99.94% with 32*32 RGB input size on Sign Language Digits Dataset and 99.60% with 28*28 Gray-scale input on Sign Language MNIST Dataset. The experimental results also prove that CapsNet has higher generalization and expressiveness capacity on unseen data than CNN dose. Another important finding in our work is that SLR-CapsNet is robust to routing iterations, i.e., its performance will not be affected by various routing iterations. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Relation
- Journal of Ambient Intelligence and Humanized Computing Vol. 13, no. 4 (2022), p. 2131-2141
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright © The Author(s)
- Subject
- 46 Information and computing sciences; Capsule networks; Convolutional neural networks; Dynamic routing; Sign language recognition
- Reviewed
- Funder
- This paper is partly supported by Australian Research Council (ARC) projects DP190101893, DP170100136 and LP180100758.
- Hits: 575
- Visitors: 549
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|