Interactive gesture feature recognition method in 3D virtual laboratory based on mobile terminal

Abstract

In order to further improve the accuracy of laboratory interactive gesture recognition. Therefore, this paper proposes an interactive gesture feature recognition method for 3D virtual laboratory under mobile terminal, which extracts gradient direction histogram and local binary pattern features respectively, and carries out feature fusion. The fusion features include not only the gradient direction information of the local region of the image, but also the texture information, which can more comprehensively describe the gesture features. The fusion feature vector is input into SVM classifier to complete gesture recognition. Experiments show that the method of gesture recognition in 3D virtual laboratory under mobile terminal has higher accuracy than traditional methods. In this experiment, a variety of gestures are recognized, and the maximum recognition rate is significantly improved.