Gesture recognition method based on convolutional neural network

The invention discloses a gesture recognition method based on a convolutional neural network, and the method comprises a YOLOV5 feature extraction stage, a classification stripping stage employing OpenCv features, and a feature data deep learning stage, and specifically comprises the steps: constructing a YOLOV5 feature extraction platform, constructing a feature carrier, and debugging a control function; the YOLOV5 acts on a gesture recognition two-dimensional model, features of the gesture recognition two-dimensional model are presented in a matrix and image mode, and the features obtained under the action of an OpenCv database are stripped in an image recognition mode; and taking the stripped features as training data to carry out deep learning training, so that a computer can autonomously recognize the features of gesture recognition. According to the method, the process controllability of gesture recognition autonomous design is enhanced, and the accuracy and efficiency of gesture recognition are improve