Abstract
AbstractThe automatic interpretation of sign languages is a challenging task, as it requires the usage of high-level vision and high-level motion processing systems for providing accurate image perception. In this paper, we use Convolutional Neural Networks (CNNs) and transfer learning to make computers able to interpret signs of the Swedish Sign Language (SSL) hand alphabet. Our model consists of the implementation of a pre-trained InceptionV3 network, and the usage of the mini-batch gradient descent optimization algorithm. We rely on transfer learning during the pre-training of the model and its data. The final accuracy of the model, based on 8 study subjects and 9400 images, is 85%. Our results indicate that the usage of CNNs is a promising approach to interpret sign languages, and transfer learning can be used to achieve high testing accuracy despite using a small training dataset. Furthermore, we describe the implementation details of our model to interpret signs as a user-friendly web application.
Funder
Knut och Alice Wallenbergs Stiftelse
Royal Institute of Technology
Publisher
Springer Science and Business Media LLC
Reference44 articles.
1. World Health Organization. Addressing the rising prevalence of hearing loss. https://apps.who.int/iris/bitstream/handle/10665/260336/9789241550260-eng.pdf?sequence=1&isAllowed=y, 2018. [Online; accessed 30-April-2020].
2. Paul PV. What’s it like to be deaf? reflections on signed language, sustainable development, and equal opportunities. American Annals of the Deaf Gallaudet University Press, 163, 2018.
3. Emmorey K. Language, Cognition, and the Brain: Insights From Sign Language Research. New Jersy: Lawrence Erlbaum Associates Inc; 2002.
4. Ray S. A quick review of machine learning algorithms. 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), 2019.
5. Kaur T. Implementation of backpropagation algorithm: A neural network approach for pattern recognition. International Journal of Engineering Research and Development, 1, 2012.
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献