Hardware Implementation of Sign Language to Text Converter Using Deep Neural Networks

The exchange of information performed in different ways such as speech, signals, or writing is called communication. Communication in deaf and mute is performed with the use of sign languages; however, they face many difficulties at the time of interacting with the common man and computers. Research is needed in this field to bring deaf-mutes more into the light of society and to increase their interaction with the common man. This paper aims at developing a system that uses Convolutional Neural Networks (CNN) and Faster R-CNN to extract the patterns in the feature vectors of each sign of twenty-six alphabets and further uses the results to recognize those signs. Different methods for the design of neural networks are proposed in this paper to enhance the performance. A standalone device is developed by implementing the pre-trained modified VGGNet models on Pi 3 A+ device.

Keywords: Artificial Neural Network, Hand gesture recognition, Moti- on analysis, Raspberry Pi, Sign Languages, VGGNet

Suggested Citation: Suggested Citation

Guda, Harsha Vardhan and Guntur, Srivenkat and M, Gowri Pratyusha and Gupta, Kunal and Volam, Priyanka and P V, Sudeep, Hardware Implementation of Sign Language to Text Converter Using Deep Neural Networks (April 15, 2020). Proceedings of the International Conference on Advances in Electronics, Electrical & Computational Intelligence (ICAEEC) 2019, Available at SSRN: https://ssrn.com/abstract=3576354 or http://dx.doi.org/10.2139/ssrn.3576354