Gesture recognition method for optimizing neural network weight by adopting quantum particle swarm algorithm

The invention provides a gesture recognition method for optimizing a neural network weight by adopting a quantum particle swarm algorithm, and belongs to the technical field of visual gesture recognition in human-computer interaction. According to the method, the network parameters of the BP neural network are optimized by using the quantum particle swarm algorithm on the basis of gesture recognition by using the traditional neural network, and the method comprises the steps that firstly, the convolutional neural network is used for extracting the features of a gesture data set, the extracted feature vectors are input into the BP neural network for gesture recognition, and then the quantum particle swarm algorithm is used for replacing a traditional gradient descent method for updating the parameters of the network, and a better network weight value is obtained. According to the present invention, under the same data set and network structure, the final recognition accuracy can be remarkably improved, and the