Multi-Stream General and Graph-Based Deep Neural Networks for Skeleton-Based Sign Language Recognition

• Published in: Electronics (Basel) Vol. 12; no. 13; p. 2841
• Main Authors: Miah, Abu Saleh Musa, Hasan, Md. Al Mehedi, Jang, Si-Woong, Lee, Hyoun-Sup, Shin, Jungpil
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2023
• Subjects: Accuracy; Annotations; Artificial intelligence; Artificial neural networks; Classification; Communication; Computational efficiency; Computing costs; Datasets; Deafness; Feature recognition; Neural networks; Researchers; Semantics; Sign language; Support vector machines; System effectiveness; Video; Japan
• DOI: 10.3390/electronics12132841
• ISSN: 2079-9292

Sign language recognition (SLR) aims to bridge speech-impaired and general communities by recognizing signs from given videos. However, due to the complex background, light illumination, and subject structures in videos, researchers still face challenges in developing effective SLR systems. Many researchers have recently sought to develop skeleton-based sign language recognition systems to overcome the subject and background variation in hand gesture sign videos. However, skeleton-based SLR is still under exploration, mainly due to a lack of information and hand key point annotations. More recently, researchers have included body and face information along with hand gesture information for SLR; however, the obtained performance accuracy and generalizability properties remain unsatisfactory. In this paper, we propose a multi-stream graph-based deep neural network (SL-GDN) for a skeleton-based SLR system in order to overcome the above-mentioned problems. The main purpose of the proposed SL-GDN approach is to improve the generalizability and performance accuracy of the SLR system while maintaining a low computational cost based on the human body pose in the form of 2D landmark locations. We first construct a skeleton graph based on 27 whole-body key points selected among 67 key points to address the high computational cost problem. Then, we utilize the multi-stream SL-GDN to extract features from the whole-body skeleton graph considering four streams. Finally, we concatenate the four different features and apply a classification module to refine the features and recognize corresponding sign classes. Our data-driven graph construction method increases the system’s flexibility and brings high generalizability, allowing it to adapt to varied data. We use two large-scale benchmark SLR data sets to evaluate the proposed model: The Turkish Sign Language data set (AUTSL) and Chinese Sign Language (CSL). The reported performance accuracy results demonstrate the outstanding ability of the proposed model, and we believe that it will be considered a great innovation in the SLR domain.