Sign Language Recognition Based on CNN and Data Augmentation

Sign language recognition is an important assistive communication technology, which is one of the main communication methods for hearing and language impaired individuals. However, the development of sign language recognition technology has been facing issues such as insufficient data and low recognition rates. This paper proposed a sign language recognition method based on convolutional neural networks and data augmentation, which effectively improves the accuracy and robustness of sign language recognition. This paper evaluated the system's performance on sign language MNIST dataset. The experimental results show that the system can achieve average accuracy of 99.32% for the dataset after data augmentation for training dataset and significantly outperformed the models in the literature using the similar dataset. The research findings presented in this study provide valuable technical assistance for the implementation of sign language recognition technology in the fields of assistive communication and human-machine interaction.