Are mid-air dynamic gestures applicable to user identification?

Heng Liu, Liangliang Dai, Shudong Hou, Jungong Han, Hongshen Liu

Abstract: Highlights•We investigate the feasibility of mid-air dynamic gesture based user identification by providing a Bi-GRU network.•We reveal the relationship between the gesture type features and the gesture user identity characteristics.•We explore the availability of ITQ hash coding on gesture based user identification and gesture classification.•We discuss the effect of different gestures on the performance of user identification through hash ITQ feature representation.