视觉基础下的手势识别研究OA

Gesture recognition is a very important part of human-computer interaction.In order to accurately recognize gestures,this paper studies gesture recognition algorithms.Firstly,the circular truncation method and length judgment method are used to extract key features,and then the motion information is used for comprehensive analysis of region division and gesture construction.The algorithm is mainly divided into three stages:ROI region extraction,key feature extraction,and gesture modeling.The test results of 5 gestures show that the algorithm has high recognition accuracy for the 5 gestures.