Enabling context-aware micro hand gesture recognition using bio-acoustic sensing technique

Abstract

The use of microgestures has improved the robustness and naturalness of subtle hand interactions. However, the conventional approach often neglects the context in which users perform microgestures. Therefore, this thesis proposes context-aware tap and swipe gesture recognition using bio-acoustic sensing. The recognition system in this study adopts both active and passive sensing approaches to recognize finger-based microgestures while also recognizing the associated interaction contexts, including within-hand, surface, and hand grasp. In this study, we investigate the hardware configuration and sensing approach to form a bio-acoustic system with multiple band-pass filter processing. We also validate the accuracy of context-aware tap and swipe gesture recognition and propose a context-aware microgesture recognition pipeline to enable adaptive input controls for rich and affordable hand interactions.