Human-computer interaction system based on gesture recognition
Wei Li, Honglei Zhang, Zhilong Zhang, Chuwei Li · 2022
In recent years, hand gesture has been widely used in human-computer interaction, virtual reality and other fields as an input channel. However, there are still some problems in gesture interaction, such as low resolution, occlusion and slow recognition rate, which lead to limited use scenarios. Therefore, based on the real scene of human-computer interaction, this paper builds a gesture recognition and object detection network according to the open source algorithms and frameworks, and constructs a human-computer interaction system based on gesture recognition. Experimental results show that the system can switch different modes according to hand movements and positions to realize interface interaction. The object detection and recognition in entertainment scenarios and the mathematical operations of virtual calculators in office scenarios are simulated respectively, which further improves accuracy and real-time performance of gesture recognition in the practical application scenarios.