Sign Gesture Recognition from Raw Skeleton Information in 3D Using Deep Learning

Abstract

Sign Language Recognition (SLR) minimizes the communication gap when interacting with hearing impaired people, i.e. connects hearing impaired persons and those who require to communicate and don't understand SLR. This paper focuses on an end-to-end deep learning approach for the recognition of sign gestures recorded with a 3D sensor (e.g., Microsoft Kinect). Typical machine learning based SLR systems require feature extractions before applying machine learning models. These features need to be chosen carefully as the recognition performance heavily relies on them. Our proposed end-to-end approach eradicates this problem by eliminating the need to extract handmade features. Deep learning models can directly work on raw data and learn higher level representations (features) by themselves. To test our hypothesis, we have used two latest and promising deep learning models, Gated Recurrent Unit (GRU) and Bidirectional Long Short Term Memory (BiL-STM) and trained them using only raw data. We have performed comparative analysis among both models and also with the base paper results. Conducted experiments reflected that proposed method outperforms the existing work, where GRU successfully concluded with 70.78% average accuracy with front view training.