Gesture recognition based on human - computer interaction

Abstract

The man-machine interaction technology based on gesture recognition has some problems, such as slow speed and low precision of static gesture recognition, and poor expansibility of gesture action. Yolov4-Tiny algorithm based on attention mechanism was proposed, and action semantics was designed by combining basic gestures with gesture state change, and the application function was called according to action semantics, which realize efficient human-computer interaction. By comparing the methods involved in each process, it can be seen that deep learning has strong fault tolerance, robust-ness, high parallelism, anti-interference, etc., which has achieved great achievements above the traditional learning algorithm in the field of gesture identification.