A Novel Gesture Recognition Technique based on sEMG Armband and Leap Motion Controller

With the rapid development of human-computer interaction technology, it has become very common to use various sensors for gesture recognition to control machines or to complete specified tasks. This study proposes a fusion method that uses Leap Motion for gesture recognition and gForcePro+ to evaluate actual force of hands. A three-dimensional (3-D) virtual gesture recognition platform was designed in Unity. Leap Motion was used to control gestures in the virtual environment, and surface electromyography (sEMG) data was used to distinguish different forces of the same gesture. The success of grasping objects was judged by detecting and analyzing the sEMG signals and Leap Motion signals, combined with the size of the grasping objects. Experimental results showed that Leap Motion and gForcePro+ can be used together to control hand motion. In addition, the proposed system can be used to distinguish the same gesture with different force sizes, which can reflect different forces when the hand grasp objects with the same action. It was proved that the fusion technique of gesture recognition system based on Leap Motion and sEMG is effective for online gesture recognition.