A review of deep learning approaches in glove-based gesture classification

Data gloves are the optimal data acquisition devices in hand-based gesture classification. Gesture classification involves the interpretation of the acquired raw data into defined gestures by applying machine learning techniques. Recently, the application of deep learning algorithms has improved the accuracy obtained in glove-based gesture classification. This chapter will review these deep learning approaches. In particular, we analyze their current performance, advantages over classical machine learning algorithms and limitations in certain classification scenarios. Furthermore, we present other deep learning approaches that may outperform current algorithms. This chapter will provide readers with an all-encompassing review that will enable a clear understanding of the current trends in glove-based gesture classification and provide new ideas for further research.